SlideShare ist ein Scribd-Unternehmen logo
1 von 65
ngoodman@
                            stanford.edu




        (Reverse)
Engineering Intelligence
      Noah D. Goodman
      Stanford University
           H+ Summit,
          June 12, 2010
What is thought?
What is thought?
• How are thoughts structured?
What is thought?
• How are thoughts structured?
• How does this structure support
 flexible, successful thinking?
What is thought?
       • How are thoughts structured?
       • How does this structure support
         flexible, successful thinking?

What mathematical principles can help us understand
                    thought?
What is thought?
        • How are thoughts structured?
        • How does this structure support
         flexible, successful thinking?
                                         e ngi ne e r
What mathematical principles can help us understand
                    thought?
Composition and probability
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”



..a big green
bear who loves
chocolate..
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”



..a big green
bear who loves
chocolate..
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”




    p=mv
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”




    p=mv
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”




    p=mv
    Compositional
   representations
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”




    Compositional
   representations
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”




    Compositional
   representations
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”




    Compositional
   representations
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”




    Compositional
   representations
Composition and probability

Thought is productive:
 “the infinite use of
    finite means”




    Compositional
   representations
Composition and probability

Thought is productive:   Thought is useful
 “the infinite use of      in an uncertain
    finite means”               world




    Compositional
   representations
Composition and probability

Thought is productive:   Thought is useful
 “the infinite use of      in an uncertain
    finite means”               world




    Compositional
   representations
Composition and probability

Thought is productive:        Thought is useful
 “the infinite use of           in an uncertain
    finite means”                    world
                         Why did he yell at me?




    Compositional
   representations
Composition and probability

Thought is productive:        Thought is useful
 “the infinite use of           in an uncertain
    finite means”                    world
                         Why did he yell at me?




                         He wanted to hurt me.
                         He thought I was a telemarketer.
    Compositional
   representations
Composition and probability

Thought is productive:        Thought is useful
 “the infinite use of           in an uncertain
    finite means”                    world
                         Why did he yell at me?
                                      Belief   Desire


                                           Action

                         He wanted to hurt me.
                         He thought I was a telemarketer.
    Compositional
   representations
Composition and probability

Thought is productive:        Thought is useful
 “the infinite use of           in an uncertain
    finite means”                    world
                         Why did he yell at me?
                                      Belief   Desire


                                           Action

                         He wanted to hurt me.
                         He thought I was a telemarketer.
    Compositional                Probabilistic
   representations                inference
Composition and probability

Thought is productive:   Thought is useful
 “the infinite use of      in an uncertain
    finite means”               world




    Compositional          Probabilistic
   representations          inference
Composition and probability

Thought is productive:   Thought is useful
 “the infinite use of      in an uncertain
    finite means”               world




    Compositional          Probabilistic
   representations          inference
Composition and probability

Thought is productive:    Thought is useful
 “the infinite use of       in an uncertain
    finite means”                world
                         a+b+c =




    Compositional           Probabilistic
   representations           inference
Composition and probability

Thought is productive:    Thought is useful
 “the infinite use of       in an uncertain
    finite means”                world
                         a+b+c =



                           0    1   2   3



    Compositional              Probabilistic
   representations              inference
Composition and probability

Thought is productive:    Thought is useful
 “the infinite use of       in an uncertain
    finite means”                world
                         a+b+c =



                           0     1   2   3
                               P (H|d) ∝ P (d|H)P (H)
    Compositional               Probabilistic
   representations               inference
Composition and probability

Thought is productive:   Thought is useful
 “the infinite use of      in an uncertain
    finite means”               world




    Compositional          Probabilistic
   representations          inference
Composition and probability

Thought is productive:   Thought is useful
 “the infinite use of      in an uncertain
    finite means”               world




    Compositional          Probabilistic
   representations          inference
Composition and probability

Thought is productive:            Thought is useful
 “the infinite use of               in an uncertain
    finite means”                        world




          ∀x King(x) =⇒ M an(x)
      ∀y M an(y) ⇐⇒ ¬W oman(y)

    Compositional                   Probabilistic
   representations                   inference
Composition and probability
                   Probabilistic language of
                     thought hypothesis
Thought is productive:                 Thought is useful
 “the infinite use of                    in an uncertain
    finite means”                             world




          ∀x King(x) =⇒ M an(x)
      ∀y M an(y) ⇐⇒ ¬W oman(y)

    Compositional                         Probabilistic
   representations                         inference
A probabilistic language
A probabilistic language
Lambda calculus:
A probabilistic language
Lambda calculus:
              (define double
                (λ (x) (+ x x)))
A probabilistic language
Lambda calculus:
              (define double
                                 (double 3)   => 6
                (λ (x) (+ x x)))
A probabilistic language
Lambda calculus:
              (define double
                                 (double 3)   => 6
                (λ (x) (+ x x)))
              (define repeat
                (λ (f) (λ (x) (f (f x)))))
A probabilistic language
Lambda calculus:
              (define double
                                 (double 3)   => 6
                (λ (x) (+ x x)))
              (define repeat
                (λ (f) (λ (x) (f (f x)))))
                         ((repeat double) 3) => 12
A probabilistic language
Lambda calculus:
               (define double
                                  (double 3)                   => 6
                 (λ (x) (+ x x)))
               (define repeat
                 (λ (f) (λ (x) (f (f x)))))
                                 ((repeat double) 3) => 12
Probabilistic lambda calculus:




                   Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
A probabilistic language
Lambda calculus:
               (define double
                                  (double 3)                   => 6
                 (λ (x) (+ x x)))
               (define repeat
                 (λ (f) (λ (x) (f (f x)))))
                                 ((repeat double) 3) => 12
Probabilistic lambda calculus:
(define a (flip 0.3))
(define b (flip 0.3))
(define c (flip 0.3))
(+ a b c)

                   Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
A probabilistic language
Lambda calculus:
               (define double
                                  (double 3)                   => 6
                 (λ (x) (+ x x)))
               (define repeat
                 (λ (f) (λ (x) (f (f x)))))
                                 ((repeat double) 3) => 12
Probabilistic lambda calculus:
(define a (flip 0.3)) => 1
(define b (flip 0.3)) => 0
(define c (flip 0.3)) => 1
(+ a b c)             => 2

                   Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
A probabilistic language
Lambda calculus:
               (define double
                                  (double 3)                   => 6
                 (λ (x) (+ x x)))
               (define repeat
                 (λ (f) (λ (x) (f (f x)))))
                                 ((repeat double) 3) => 12
Probabilistic lambda calculus:
(define a (flip 0.3)) => 1 0
(define b (flip 0.3)) => 0 0
(define c (flip 0.3)) => 1 0
(+ a b c)             => 2 0

                   Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
A probabilistic language
Lambda calculus:
               (define double
                                  (double 3)                   => 6
                 (λ (x) (+ x x)))
               (define repeat
                 (λ (f) (λ (x) (f (f x)))))
                                 ((repeat double) 3) => 12
Probabilistic lambda calculus:
(define a (flip 0.3)) => 1 0           0
(define b (flip 0.3)) => 0 0           0
(define c (flip 0.3)) => 1 0           1
(+ a b c)             => 2 0           1

                   Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
A probabilistic language
Lambda calculus:
               (define double
                                  (double 3)                   => 6
                 (λ (x) (+ x x)))
               (define repeat
                 (λ (f) (λ (x) (f (f x)))))
                                 ((repeat double) 3) => 12
Probabilistic lambda calculus:
(define a (flip 0.3)) => 1 0           0
(define b (flip 0.3)) => 0 0           0
(define c (flip 0.3)) => 1 0           1
(+ a b c)             => 2 0           1 ..

                   Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
A probabilistic language
Lambda calculus:
               (define double
                                  (double 3)                                        => 6
                 (λ (x) (+ x x)))
               (define repeat
                 (λ (f) (λ (x) (f (f x)))))
                                 ((repeat double) 3) => 12
Probabilistic lambda calculus:



                                              probability / frequency
(define a (flip 0.3)) => 1 0           0
(define b (flip 0.3)) => 0 0           0
(define c (flip 0.3)) => 1 0           1
(+ a b c)             => 2 0           1 ..
                                                                        0   1   2     3
                   Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
Hypothesis

• The probabilistic language of thought
 hypothesis:
 Mental representations are functions
 in a probabilistic lambda calculus.
 • Thoughts are built compositionally (like molecules).
 • Thinking is probabilistic inference.
       http://projects.csail.mit.edu/church
Bob’s box




   Goodman, Baker, Tenenbaum (2009; in prep.)
Bob’s box

• Bob has a box with two
 buttons and a light.
                                           A      B




                           Goodman, Baker, Tenenbaum (2009; in prep.)
Bob’s box

• Bob has a box with two
  buttons and a light.
                                            A      B


• He presses both buttons,
  and the light comes on.




                            Goodman, Baker, Tenenbaum (2009; in prep.)
Bob’s box

• Bob has a box with two
  buttons and a light.
                                                      A           B


• He presses both buttons,
  and the light comes on.
• How does the
  box work?          A               A            A               A            A
                              B               B               B            B            B



                          C               C               C            C            C


                     A alone         B alone      A or B          A and B       Nothing
                     causes C.       causes C.    cause C.        causes C.    causes C.


                                  Goodman, Baker, Tenenbaum (2009; in prep.)
Human judgements
                                             Social
                50
                                                    *
                40   Social condition
Mean Bets ($)




                30
                                                                                         Physical
                                                                            50
                20                                                             Physical condition
                                                                            40              ns
                                                                            30
                10
                                                                            20

                0
                          A         B        AorB       A&B      none       10


   N=15                                                                     0
                                                                                 A   B    AorB      A&B   none

                       A alone B alone       A or B A and B Nothing
                       causes C. causes C.   cause C. causes C. causes C.
Purely causal learning
                                                                           Causal!only model
                                                        0.5
              (query
Causal-only


               (define world-cs (cs-prior))             0.4

               (define action (uniform))




                                              Probability
                                                        0.3
               (define outcome (world-cs
                                 init-state             0.2

                                 action))
                                                        0.1
               world-cs
               (and (press-A action)                        0
                                                                  A       B         AorB       A&B   none




                                                                                    A or B
                                                                                               A&B
                                                                         B only




                                                                                                     none
                                                                A only
                    (press-B action)                                              Cause of C

                    (light-on outcome)))




                                       No conclusion is possible.
                                      The evidence is confounded.
Explaining actions
Beliefs:                     Desires:
 A         B



      C
                  Decision




                                        Rational action:
               Actions:                 (define decide
                                         (λ (state causal-model utility)
                                          (query
                                           (define action (action-prior))
                                           action
                                           (flip (utility
                                                  (causal-model
                                                     state action))))))
Causal learning models                                     Causal!only model
                                                               0.5


                                                                     Causal-only model
                                                                      Causal-only
Causal-only


                  (define world-cs (cs-prior))                 0.4

                  (define action (uniform))                            model




                                                 Probability
                  (define outcome (world-cs                    0.3


                                    init-state                 0.2

                                    action))
                                                               0.1



                                                                0
                                                                        A       B         AorB       A&B   none




                                                                                          A or B
                                                                                                     A&B
                                                                               B only




                                                                                                           none
                                                                      A only
                                                                                        Cause of C
                  (define world-cs (cs-prior))
                  (define utility (uniform))
Social & causal




                  (define cs-belief world-cs)     Knowledgeable
                  (define action (decide
                                   init-state
                                                 agent assumption
                                   cs-belief         Rational
                                   utility))
                  (define outcome (world-cs      agent assumption
                                    init-state
                                    action))
Causal learning models                                     Causal!only model
                                                               0.5


                                                                     Causal-only model
                                                                      Causal-only
Causal-only


                  (define world-cs (cs-prior))                 0.4

                  (define action (uniform))                            model




                                                 Probability
                  (define outcome (world-cs                    0.3


                                    init-state                 0.2

                                    action))
                                                               0.1



                                                                0
                                                                        A       B         AorB       A&B   none




                                                                                          A or B
                                                                                                     A&B
                                                                               B only




                                                                                                           none
                                                                      A only
                                                                                        Cause of C
                  (define world-cs (cs-prior))
                  (define utility (uniform))
Social & causal




                  (define cs-belief world-cs)
                  (define action (decide
                                   init-state
                                   cs-belief
                                   utility))
                  (define outcome (world-cs
                                    init-state
                                    action))
Causal learning models                                    Causal!only model
                                                               0.5


                                                                     Causal-only model
Causal-only


                  (define world-cs (cs-prior))                 0.4

                  (define action (uniform))




                                                 Probability
                  (define outcome (world-cs                    0.3


                                    init-state                 0.2

                                    action))
                                                               0.1



                                                                0
                                                                       A       B         AorB       A&B   none




                                                                                         A or B
                                                                                                    A&B
                                                                              B only




                                                                                                          none
                                                                     A only
                                                                                       Cause of C
                  (define world-cs (cs-prior))
                  (define utility (uniform))
Social & causal




                  (define cs-belief world-cs)
                  (define action (decide
                                   init-state
                                   cs-belief
                                   utility))
                  (define outcome (world-cs
                                    init-state
                                    action))
Causal learning models                                                    Causal!only model
                                                                             0.5


                                                                                    Causal-only model
Causal-only


                  (define world-cs (cs-prior))                               0.4

                  (define action (uniform))




                                                 Probability
                  (define outcome (world-cs                                  0.3


                                    init-state                               0.2

                                    action))
                                                                             0.1



                                                                               0
                                                                                       A       B         AorB       A&B   none




                                                                                                         A or B
                                                                                                                    A&B
                                                                                              B only




                                                                                                                          none
                                                                                     A only
                                                                                                       Cause of C
                  (define world-cs (cs-prior))
                  (define utility (uniform))
Social & causal




                                                                                               Social!causal model
                                                                             0.5
                  (define cs-belief world-cs)                                      Social + causal model
                  (define action (decide                                     0.4

                                   init-state
                                                     Posterior probability
                                                 Probability
                                                                             0.3
                                   cs-belief
                                   utility))                                 0.2

                  (define outcome (world-cs
                                    init-state                               0.1


                                    action))                                  0
                                                                                      A        B         AorB       A&B   none
Scalar implicature




 Some of the plants
   have sprouted



(Plants usually sprout.)   Goodman, et al (in prep)
Scalar implicature
                      Desires:
                      -informative
Beliefs               -parsimonious




          Actions:
              “...”




      Some of the plants
        have sprouted



    (Plants usually sprout.)          Goodman, et al (in prep)
Scalar implicature
                      Desires:          Model:
                      -informative
Beliefs               -parsimonious




                                      Plausibility (Z-score)
                                                               2
                                                               1
                                                               0
                                                               -1
          Actions:
                                                               -2
              “...”                                                 0:5 1:5 2:5 3:5 4:5 5:5
                                                                     Number sprouted


      Some of the plants
        have sprouted



    (Plants usually sprout.)                                                  Goodman, et al (in prep)
Scalar implicature
                      Desires:          Model:
                      -informative
Beliefs               -parsimonious




                                      Plausibility (Z-score)
                                                               2
                                                               1
                                                               0
                                                               -1
          Actions:
                                                               -2
              “...”                                                 0:5 1:5 2:5 3:5 4:5 5:5
                                                                     Number sprouted


      Some of the plants
        have sprouted



    (Plants usually sprout.)                                                  Goodman, et al (in prep)
Scalar implicature
                      Desires:          Model:                                                    Partial
                      -informative         Full knowledge                                       knowledge
Beliefs               -parsimonious




                                      Plausibility (Z-score)
                                                               2
                                                               1
                                                               0
                                                               -1
          Actions:
                                                               -2
              “...”                                                 0:5 1:5 2:5 3:5 4:5 5:5   0:5 1:5 2:5 3:5 4:5 5:5
                                                                     Number sprouted


      Some of the plants
        have sprouted



    (Plants usually sprout.)                                                  Goodman, et al (in prep)
Scalar implicature
                      Desires:          Model:                                                    Partial
                      -informative         Full knowledge                                       knowledge
Beliefs               -parsimonious




                                      Plausibility (Z-score)
                                                               2
                                                               1
                                                               0
                                                               -1
          Actions:
                                                               -2
              “...”                                                 0:5 1:5 2:5 3:5 4:5 5:5   0:5 1:5 2:5 3:5 4:5 5:5
                                                                     Number sprouted
                                        Human:
      Some of the plants
        have sprouted



    (Plants usually sprout.)                                                  Goodman, et al (in prep)
Summary

• The probabilistic language of thought
 combines composition and probability.
• We can explain complex, flexible human
 thinking...
• And engineer flexible computer
 intelligence.

Weitere ähnliche Inhalte

Andere mochten auch

Probabilistic Reasoning
Probabilistic ReasoningProbabilistic Reasoning
Probabilistic ReasoningTameem Ahmad
 
Probabilistic Abductive Logic Programming using Possible Worlds
Probabilistic Abductive Logic Programming using Possible WorldsProbabilistic Abductive Logic Programming using Possible Worlds
Probabilistic Abductive Logic Programming using Possible WorldsFulvio Rotella
 
Manifesting futures
Manifesting futuresManifesting futures
Manifesting futuresFrances Ting
 
Presentation -Intelligence Enhancer and Genius 3.0 智能增长以及天才3.0
Presentation -Intelligence Enhancer and Genius 3.0 智能增长以及天才3.0Presentation -Intelligence Enhancer and Genius 3.0 智能增长以及天才3.0
Presentation -Intelligence Enhancer and Genius 3.0 智能增长以及天才3.0Hang Wu
 
Alexandra Basford, InCoB 2011: A Journal’s Perspective on Data Standards and ...
Alexandra Basford, InCoB 2011: A Journal’s Perspective on Data Standards and ...Alexandra Basford, InCoB 2011: A Journal’s Perspective on Data Standards and ...
Alexandra Basford, InCoB 2011: A Journal’s Perspective on Data Standards and ...GigaScience, BGI Hong Kong
 
Engineering Innovation - Electronic
Engineering Innovation - ElectronicEngineering Innovation - Electronic
Engineering Innovation - ElectronicJohn Breslin
 
Magneto-Inductive NEtworked Rescue System (MINERS): Taking Sensor Networks Un...
Magneto-Inductive NEtworked Rescue System (MINERS): Taking Sensor Networks Un...Magneto-Inductive NEtworked Rescue System (MINERS): Taking Sensor Networks Un...
Magneto-Inductive NEtworked Rescue System (MINERS): Taking Sensor Networks Un...acmarkham
 
Scaling citizen science genomics
Scaling citizen science genomicsScaling citizen science genomics
Scaling citizen science genomicsMelanie Swan
 
How Design Triggers Transformation presented by Tjeerd Hoek
How Design Triggers Transformation presented by Tjeerd HoekHow Design Triggers Transformation presented by Tjeerd Hoek
How Design Triggers Transformation presented by Tjeerd Hoekfrog
 
Imagineering - Virtual Worlds
Imagineering - Virtual WorldsImagineering - Virtual Worlds
Imagineering - Virtual WorldsPrithwis Mukerjee
 
14.40 o1 i neupane
14.40 o1 i neupane14.40 o1 i neupane
14.40 o1 i neupaneNZIP
 
Discovering knowledge using web structure mining
Discovering knowledge using web structure miningDiscovering knowledge using web structure mining
Discovering knowledge using web structure miningAtul Khanna
 
Thoughts On The Future Of Human Evolution
Thoughts On The Future Of Human EvolutionThoughts On The Future Of Human Evolution
Thoughts On The Future Of Human EvolutionWeaver D. R. Weinbaum
 
Engineering Ambient Intelligence Systems using Agent Technology
Engineering Ambient Intelligence Systems using Agent TechnologyEngineering Ambient Intelligence Systems using Agent Technology
Engineering Ambient Intelligence Systems using Agent TechnologyNikolaos Spanoudakis
 

Andere mochten auch (16)

Probabilistic Reasoning
Probabilistic ReasoningProbabilistic Reasoning
Probabilistic Reasoning
 
Probabilistic Abductive Logic Programming using Possible Worlds
Probabilistic Abductive Logic Programming using Possible WorldsProbabilistic Abductive Logic Programming using Possible Worlds
Probabilistic Abductive Logic Programming using Possible Worlds
 
Manifesting futures
Manifesting futuresManifesting futures
Manifesting futures
 
Presentation -Intelligence Enhancer and Genius 3.0 智能增长以及天才3.0
Presentation -Intelligence Enhancer and Genius 3.0 智能增长以及天才3.0Presentation -Intelligence Enhancer and Genius 3.0 智能增长以及天才3.0
Presentation -Intelligence Enhancer and Genius 3.0 智能增长以及天才3.0
 
Alexandra Basford, InCoB 2011: A Journal’s Perspective on Data Standards and ...
Alexandra Basford, InCoB 2011: A Journal’s Perspective on Data Standards and ...Alexandra Basford, InCoB 2011: A Journal’s Perspective on Data Standards and ...
Alexandra Basford, InCoB 2011: A Journal’s Perspective on Data Standards and ...
 
Engineering Innovation - Electronic
Engineering Innovation - ElectronicEngineering Innovation - Electronic
Engineering Innovation - Electronic
 
The Sixth Sense
The Sixth SenseThe Sixth Sense
The Sixth Sense
 
Magneto-Inductive NEtworked Rescue System (MINERS): Taking Sensor Networks Un...
Magneto-Inductive NEtworked Rescue System (MINERS): Taking Sensor Networks Un...Magneto-Inductive NEtworked Rescue System (MINERS): Taking Sensor Networks Un...
Magneto-Inductive NEtworked Rescue System (MINERS): Taking Sensor Networks Un...
 
Scaling citizen science genomics
Scaling citizen science genomicsScaling citizen science genomics
Scaling citizen science genomics
 
How Design Triggers Transformation presented by Tjeerd Hoek
How Design Triggers Transformation presented by Tjeerd HoekHow Design Triggers Transformation presented by Tjeerd Hoek
How Design Triggers Transformation presented by Tjeerd Hoek
 
Imagineering - Virtual Worlds
Imagineering - Virtual WorldsImagineering - Virtual Worlds
Imagineering - Virtual Worlds
 
14.40 o1 i neupane
14.40 o1 i neupane14.40 o1 i neupane
14.40 o1 i neupane
 
Discovering knowledge using web structure mining
Discovering knowledge using web structure miningDiscovering knowledge using web structure mining
Discovering knowledge using web structure mining
 
Soft computing01
Soft computing01Soft computing01
Soft computing01
 
Thoughts On The Future Of Human Evolution
Thoughts On The Future Of Human EvolutionThoughts On The Future Of Human Evolution
Thoughts On The Future Of Human Evolution
 
Engineering Ambient Intelligence Systems using Agent Technology
Engineering Ambient Intelligence Systems using Agent TechnologyEngineering Ambient Intelligence Systems using Agent Technology
Engineering Ambient Intelligence Systems using Agent Technology
 

Ähnlich wie (Reverse) Engineering Intelligence - Noah Goodman - H+ Summit @ Harvard

Lesson 9: The Product and Quotient Rules
Lesson 9: The Product and Quotient RulesLesson 9: The Product and Quotient Rules
Lesson 9: The Product and Quotient RulesMatthew Leingang
 
Using model-based statistical inference to learn about evolution
Using model-based statistical inference to learn about evolutionUsing model-based statistical inference to learn about evolution
Using model-based statistical inference to learn about evolutionErick Matsen
 
MLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
MLIP - Chapter 6 - Generation, Super-Resolution, Style transferMLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
MLIP - Chapter 6 - Generation, Super-Resolution, Style transferCharles Deledalle
 
Lecture9 - Bayesian-Decision-Theory
Lecture9 - Bayesian-Decision-TheoryLecture9 - Bayesian-Decision-Theory
Lecture9 - Bayesian-Decision-TheoryAlbert Orriols-Puig
 
Variational Autoencoders VAE - Santiago Pascual - UPC Barcelona 2018
Variational Autoencoders VAE - Santiago Pascual - UPC Barcelona 2018Variational Autoencoders VAE - Santiago Pascual - UPC Barcelona 2018
Variational Autoencoders VAE - Santiago Pascual - UPC Barcelona 2018Universitat Politècnica de Catalunya
 
Class 22: Stateful Evaluation Rules
Class 22: Stateful Evaluation RulesClass 22: Stateful Evaluation Rules
Class 22: Stateful Evaluation RulesDavid Evans
 

Ähnlich wie (Reverse) Engineering Intelligence - Noah Goodman - H+ Summit @ Harvard (10)

Logic 2
Logic 2Logic 2
Logic 2
 
Lesson 9: The Product and Quotient Rules
Lesson 9: The Product and Quotient RulesLesson 9: The Product and Quotient Rules
Lesson 9: The Product and Quotient Rules
 
Per3 logika
Per3 logikaPer3 logika
Per3 logika
 
Using model-based statistical inference to learn about evolution
Using model-based statistical inference to learn about evolutionUsing model-based statistical inference to learn about evolution
Using model-based statistical inference to learn about evolution
 
MLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
MLIP - Chapter 6 - Generation, Super-Resolution, Style transferMLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
MLIP - Chapter 6 - Generation, Super-Resolution, Style transfer
 
Lecture9 - Bayesian-Decision-Theory
Lecture9 - Bayesian-Decision-TheoryLecture9 - Bayesian-Decision-Theory
Lecture9 - Bayesian-Decision-Theory
 
Probability Homework Help
Probability Homework Help Probability Homework Help
Probability Homework Help
 
Midterm I Review
Midterm I ReviewMidterm I Review
Midterm I Review
 
Variational Autoencoders VAE - Santiago Pascual - UPC Barcelona 2018
Variational Autoencoders VAE - Santiago Pascual - UPC Barcelona 2018Variational Autoencoders VAE - Santiago Pascual - UPC Barcelona 2018
Variational Autoencoders VAE - Santiago Pascual - UPC Barcelona 2018
 
Class 22: Stateful Evaluation Rules
Class 22: Stateful Evaluation RulesClass 22: Stateful Evaluation Rules
Class 22: Stateful Evaluation Rules
 

Mehr von Humanity Plus

How WE create I - Heather Schlegel - H+ Summit @ Harvard
How WE create I - Heather Schlegel - H+ Summit @ HarvardHow WE create I - Heather Schlegel - H+ Summit @ Harvard
How WE create I - Heather Schlegel - H+ Summit @ HarvardHumanity Plus
 
Superconducting Quantum Circuits That Learn - Geordie Rose - H+ Summit @ Harvard
Superconducting Quantum Circuits That Learn - Geordie Rose - H+ Summit @ HarvardSuperconducting Quantum Circuits That Learn - Geordie Rose - H+ Summit @ Harvard
Superconducting Quantum Circuits That Learn - Geordie Rose - H+ Summit @ HarvardHumanity Plus
 
The Power of Hierarchical Thinking - Ray Kurzweil - H+ Summit @ Harvard
The Power of Hierarchical Thinking - Ray Kurzweil - H+ Summit @ HarvardThe Power of Hierarchical Thinking - Ray Kurzweil - H+ Summit @ Harvard
The Power of Hierarchical Thinking - Ray Kurzweil - H+ Summit @ HarvardHumanity Plus
 
The Rise of Citizen-Scientists in the Eversmarter World - Alex Lightman - H+ ...
The Rise of Citizen-Scientists in the Eversmarter World - Alex Lightman - H+ ...The Rise of Citizen-Scientists in the Eversmarter World - Alex Lightman - H+ ...
The Rise of Citizen-Scientists in the Eversmarter World - Alex Lightman - H+ ...Humanity Plus
 
50 years of Invention and Entrepreneurship - Nolan Bushnell - H+ Summit @ Har...
50 years of Invention and Entrepreneurship - Nolan Bushnell - H+ Summit @ Har...50 years of Invention and Entrepreneurship - Nolan Bushnell - H+ Summit @ Har...
50 years of Invention and Entrepreneurship - Nolan Bushnell - H+ Summit @ Har...Humanity Plus
 
The Evolving Data Sphere - David Orban - H+ Summit @ Harvard
The Evolving Data Sphere - David Orban - H+ Summit @ HarvardThe Evolving Data Sphere - David Orban - H+ Summit @ Harvard
The Evolving Data Sphere - David Orban - H+ Summit @ HarvardHumanity Plus
 
Humanity 2020: The Next 10 Years of Human Development - Ramez Naam - H+ Summi...
Humanity 2020: The Next 10 Years of Human Development - Ramez Naam - H+ Summi...Humanity 2020: The Next 10 Years of Human Development - Ramez Naam - H+ Summi...
Humanity 2020: The Next 10 Years of Human Development - Ramez Naam - H+ Summi...Humanity Plus
 
Do-it-yourself Transhuman Tech - Bryan Bishop - H+ Summit @ Harvard
Do-it-yourself Transhuman Tech - Bryan Bishop - H+ Summit @ HarvardDo-it-yourself Transhuman Tech - Bryan Bishop - H+ Summit @ Harvard
Do-it-yourself Transhuman Tech - Bryan Bishop - H+ Summit @ HarvardHumanity Plus
 
Transhumanism & Education - Kevin Jain - H+ Summit @ Harvard
Transhumanism & Education - Kevin Jain - H+ Summit @ HarvardTranshumanism & Education - Kevin Jain - H+ Summit @ Harvard
Transhumanism & Education - Kevin Jain - H+ Summit @ HarvardHumanity Plus
 
Can we extract a mind from a plastic-embedded brain? - Kenneth Hayworth - H+ ...
Can we extract a mind from a plastic-embedded brain? - Kenneth Hayworth - H+ ...Can we extract a mind from a plastic-embedded brain? - Kenneth Hayworth - H+ ...
Can we extract a mind from a plastic-embedded brain? - Kenneth Hayworth - H+ ...Humanity Plus
 
Computation of Things - Justyna Zander, Pieter Mosterman - H+ Summit @ Harvard
Computation of Things - Justyna Zander, Pieter Mosterman - H+ Summit @ HarvardComputation of Things - Justyna Zander, Pieter Mosterman - H+ Summit @ Harvard
Computation of Things - Justyna Zander, Pieter Mosterman - H+ Summit @ HarvardHumanity Plus
 
Far Beyond Smartphones - David Wood - H+ Summit @ Harvard
Far Beyond Smartphones - David Wood - H+ Summit @ HarvardFar Beyond Smartphones - David Wood - H+ Summit @ Harvard
Far Beyond Smartphones - David Wood - H+ Summit @ HarvardHumanity Plus
 
UX Rocks - Mei Li - H+ Summit @ Harvard
UX Rocks - Mei Li - H+ Summit @ HarvardUX Rocks - Mei Li - H+ Summit @ Harvard
UX Rocks - Mei Li - H+ Summit @ HarvardHumanity Plus
 
Stepping Stones - Mikhail Shapiro - H+ Summit @ Harvard
Stepping Stones - Mikhail Shapiro - H+ Summit @ HarvardStepping Stones - Mikhail Shapiro - H+ Summit @ Harvard
Stepping Stones - Mikhail Shapiro - H+ Summit @ HarvardHumanity Plus
 
Military 2.0 - Patrick Lin - H+ Summit @ Harvard
Military 2.0 - Patrick Lin - H+ Summit @ HarvardMilitary 2.0 - Patrick Lin - H+ Summit @ Harvard
Military 2.0 - Patrick Lin - H+ Summit @ HarvardHumanity Plus
 
Sparking Our Neural Humanity - M. A. Greenstein - H+ Summit - Humanity+
Sparking Our Neural Humanity - M. A. Greenstein - H+ Summit - Humanity+Sparking Our Neural Humanity - M. A. Greenstein - H+ Summit - Humanity+
Sparking Our Neural Humanity - M. A. Greenstein - H+ Summit - Humanity+Humanity Plus
 
Democratizing The Genome - Melanie Swan - H+ Summit @ Harvard
Democratizing The Genome - Melanie Swan - H+ Summit @ HarvardDemocratizing The Genome - Melanie Swan - H+ Summit @ Harvard
Democratizing The Genome - Melanie Swan - H+ Summit @ HarvardHumanity Plus
 
Altered Carbon - Andrew Hessel - H+ Summit @ Harvard
Altered Carbon - Andrew Hessel - H+ Summit @ HarvardAltered Carbon - Andrew Hessel - H+ Summit @ Harvard
Altered Carbon - Andrew Hessel - H+ Summit @ HarvardHumanity Plus
 
Do We Click? - Laurent Silbert - H+ Summit @ Harvard
Do We Click? - Laurent Silbert - H+ Summit @ HarvardDo We Click? - Laurent Silbert - H+ Summit @ Harvard
Do We Click? - Laurent Silbert - H+ Summit @ HarvardHumanity Plus
 
HACCP as a Lifespan Extension Management System - Morris Johnson - H+Summit @...
HACCP as a Lifespan Extension Management System - Morris Johnson - H+Summit @...HACCP as a Lifespan Extension Management System - Morris Johnson - H+Summit @...
HACCP as a Lifespan Extension Management System - Morris Johnson - H+Summit @...Humanity Plus
 

Mehr von Humanity Plus (20)

How WE create I - Heather Schlegel - H+ Summit @ Harvard
How WE create I - Heather Schlegel - H+ Summit @ HarvardHow WE create I - Heather Schlegel - H+ Summit @ Harvard
How WE create I - Heather Schlegel - H+ Summit @ Harvard
 
Superconducting Quantum Circuits That Learn - Geordie Rose - H+ Summit @ Harvard
Superconducting Quantum Circuits That Learn - Geordie Rose - H+ Summit @ HarvardSuperconducting Quantum Circuits That Learn - Geordie Rose - H+ Summit @ Harvard
Superconducting Quantum Circuits That Learn - Geordie Rose - H+ Summit @ Harvard
 
The Power of Hierarchical Thinking - Ray Kurzweil - H+ Summit @ Harvard
The Power of Hierarchical Thinking - Ray Kurzweil - H+ Summit @ HarvardThe Power of Hierarchical Thinking - Ray Kurzweil - H+ Summit @ Harvard
The Power of Hierarchical Thinking - Ray Kurzweil - H+ Summit @ Harvard
 
The Rise of Citizen-Scientists in the Eversmarter World - Alex Lightman - H+ ...
The Rise of Citizen-Scientists in the Eversmarter World - Alex Lightman - H+ ...The Rise of Citizen-Scientists in the Eversmarter World - Alex Lightman - H+ ...
The Rise of Citizen-Scientists in the Eversmarter World - Alex Lightman - H+ ...
 
50 years of Invention and Entrepreneurship - Nolan Bushnell - H+ Summit @ Har...
50 years of Invention and Entrepreneurship - Nolan Bushnell - H+ Summit @ Har...50 years of Invention and Entrepreneurship - Nolan Bushnell - H+ Summit @ Har...
50 years of Invention and Entrepreneurship - Nolan Bushnell - H+ Summit @ Har...
 
The Evolving Data Sphere - David Orban - H+ Summit @ Harvard
The Evolving Data Sphere - David Orban - H+ Summit @ HarvardThe Evolving Data Sphere - David Orban - H+ Summit @ Harvard
The Evolving Data Sphere - David Orban - H+ Summit @ Harvard
 
Humanity 2020: The Next 10 Years of Human Development - Ramez Naam - H+ Summi...
Humanity 2020: The Next 10 Years of Human Development - Ramez Naam - H+ Summi...Humanity 2020: The Next 10 Years of Human Development - Ramez Naam - H+ Summi...
Humanity 2020: The Next 10 Years of Human Development - Ramez Naam - H+ Summi...
 
Do-it-yourself Transhuman Tech - Bryan Bishop - H+ Summit @ Harvard
Do-it-yourself Transhuman Tech - Bryan Bishop - H+ Summit @ HarvardDo-it-yourself Transhuman Tech - Bryan Bishop - H+ Summit @ Harvard
Do-it-yourself Transhuman Tech - Bryan Bishop - H+ Summit @ Harvard
 
Transhumanism & Education - Kevin Jain - H+ Summit @ Harvard
Transhumanism & Education - Kevin Jain - H+ Summit @ HarvardTranshumanism & Education - Kevin Jain - H+ Summit @ Harvard
Transhumanism & Education - Kevin Jain - H+ Summit @ Harvard
 
Can we extract a mind from a plastic-embedded brain? - Kenneth Hayworth - H+ ...
Can we extract a mind from a plastic-embedded brain? - Kenneth Hayworth - H+ ...Can we extract a mind from a plastic-embedded brain? - Kenneth Hayworth - H+ ...
Can we extract a mind from a plastic-embedded brain? - Kenneth Hayworth - H+ ...
 
Computation of Things - Justyna Zander, Pieter Mosterman - H+ Summit @ Harvard
Computation of Things - Justyna Zander, Pieter Mosterman - H+ Summit @ HarvardComputation of Things - Justyna Zander, Pieter Mosterman - H+ Summit @ Harvard
Computation of Things - Justyna Zander, Pieter Mosterman - H+ Summit @ Harvard
 
Far Beyond Smartphones - David Wood - H+ Summit @ Harvard
Far Beyond Smartphones - David Wood - H+ Summit @ HarvardFar Beyond Smartphones - David Wood - H+ Summit @ Harvard
Far Beyond Smartphones - David Wood - H+ Summit @ Harvard
 
UX Rocks - Mei Li - H+ Summit @ Harvard
UX Rocks - Mei Li - H+ Summit @ HarvardUX Rocks - Mei Li - H+ Summit @ Harvard
UX Rocks - Mei Li - H+ Summit @ Harvard
 
Stepping Stones - Mikhail Shapiro - H+ Summit @ Harvard
Stepping Stones - Mikhail Shapiro - H+ Summit @ HarvardStepping Stones - Mikhail Shapiro - H+ Summit @ Harvard
Stepping Stones - Mikhail Shapiro - H+ Summit @ Harvard
 
Military 2.0 - Patrick Lin - H+ Summit @ Harvard
Military 2.0 - Patrick Lin - H+ Summit @ HarvardMilitary 2.0 - Patrick Lin - H+ Summit @ Harvard
Military 2.0 - Patrick Lin - H+ Summit @ Harvard
 
Sparking Our Neural Humanity - M. A. Greenstein - H+ Summit - Humanity+
Sparking Our Neural Humanity - M. A. Greenstein - H+ Summit - Humanity+Sparking Our Neural Humanity - M. A. Greenstein - H+ Summit - Humanity+
Sparking Our Neural Humanity - M. A. Greenstein - H+ Summit - Humanity+
 
Democratizing The Genome - Melanie Swan - H+ Summit @ Harvard
Democratizing The Genome - Melanie Swan - H+ Summit @ HarvardDemocratizing The Genome - Melanie Swan - H+ Summit @ Harvard
Democratizing The Genome - Melanie Swan - H+ Summit @ Harvard
 
Altered Carbon - Andrew Hessel - H+ Summit @ Harvard
Altered Carbon - Andrew Hessel - H+ Summit @ HarvardAltered Carbon - Andrew Hessel - H+ Summit @ Harvard
Altered Carbon - Andrew Hessel - H+ Summit @ Harvard
 
Do We Click? - Laurent Silbert - H+ Summit @ Harvard
Do We Click? - Laurent Silbert - H+ Summit @ HarvardDo We Click? - Laurent Silbert - H+ Summit @ Harvard
Do We Click? - Laurent Silbert - H+ Summit @ Harvard
 
HACCP as a Lifespan Extension Management System - Morris Johnson - H+Summit @...
HACCP as a Lifespan Extension Management System - Morris Johnson - H+Summit @...HACCP as a Lifespan Extension Management System - Morris Johnson - H+Summit @...
HACCP as a Lifespan Extension Management System - Morris Johnson - H+Summit @...
 

Kürzlich hochgeladen

MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsNanddeep Nachan
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...apidays
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxRustici Software
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Victor Rentea
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Bhuvaneswari Subramani
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityWSO2
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelDeepika Singh
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Zilliz
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusZilliz
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...Zilliz
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...apidays
 

Kürzlich hochgeladen (20)

MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering Developers
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
 

(Reverse) Engineering Intelligence - Noah Goodman - H+ Summit @ Harvard

  • 1. ngoodman@ stanford.edu (Reverse) Engineering Intelligence Noah D. Goodman Stanford University H+ Summit, June 12, 2010
  • 3. What is thought? • How are thoughts structured?
  • 4. What is thought? • How are thoughts structured? • How does this structure support flexible, successful thinking?
  • 5. What is thought? • How are thoughts structured? • How does this structure support flexible, successful thinking? What mathematical principles can help us understand thought?
  • 6. What is thought? • How are thoughts structured? • How does this structure support flexible, successful thinking? e ngi ne e r What mathematical principles can help us understand thought?
  • 8. Composition and probability Thought is productive: “the infinite use of finite means”
  • 9. Composition and probability Thought is productive: “the infinite use of finite means” ..a big green bear who loves chocolate..
  • 10. Composition and probability Thought is productive: “the infinite use of finite means” ..a big green bear who loves chocolate..
  • 11. Composition and probability Thought is productive: “the infinite use of finite means” p=mv
  • 12. Composition and probability Thought is productive: “the infinite use of finite means” p=mv
  • 13. Composition and probability Thought is productive: “the infinite use of finite means” p=mv Compositional representations
  • 14. Composition and probability Thought is productive: “the infinite use of finite means” Compositional representations
  • 15. Composition and probability Thought is productive: “the infinite use of finite means” Compositional representations
  • 16. Composition and probability Thought is productive: “the infinite use of finite means” Compositional representations
  • 17. Composition and probability Thought is productive: “the infinite use of finite means” Compositional representations
  • 18. Composition and probability Thought is productive: “the infinite use of finite means” Compositional representations
  • 19. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world Compositional representations
  • 20. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world Compositional representations
  • 21. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world Why did he yell at me? Compositional representations
  • 22. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world Why did he yell at me? He wanted to hurt me. He thought I was a telemarketer. Compositional representations
  • 23. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world Why did he yell at me? Belief Desire Action He wanted to hurt me. He thought I was a telemarketer. Compositional representations
  • 24. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world Why did he yell at me? Belief Desire Action He wanted to hurt me. He thought I was a telemarketer. Compositional Probabilistic representations inference
  • 25. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world Compositional Probabilistic representations inference
  • 26. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world Compositional Probabilistic representations inference
  • 27. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world a+b+c = Compositional Probabilistic representations inference
  • 28. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world a+b+c = 0 1 2 3 Compositional Probabilistic representations inference
  • 29. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world a+b+c = 0 1 2 3 P (H|d) ∝ P (d|H)P (H) Compositional Probabilistic representations inference
  • 30. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world Compositional Probabilistic representations inference
  • 31. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world Compositional Probabilistic representations inference
  • 32. Composition and probability Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world ∀x King(x) =⇒ M an(x) ∀y M an(y) ⇐⇒ ¬W oman(y) Compositional Probabilistic representations inference
  • 33. Composition and probability Probabilistic language of thought hypothesis Thought is productive: Thought is useful “the infinite use of in an uncertain finite means” world ∀x King(x) =⇒ M an(x) ∀y M an(y) ⇐⇒ ¬W oman(y) Compositional Probabilistic representations inference
  • 36. A probabilistic language Lambda calculus: (define double (λ (x) (+ x x)))
  • 37. A probabilistic language Lambda calculus: (define double (double 3) => 6 (λ (x) (+ x x)))
  • 38. A probabilistic language Lambda calculus: (define double (double 3) => 6 (λ (x) (+ x x))) (define repeat (λ (f) (λ (x) (f (f x)))))
  • 39. A probabilistic language Lambda calculus: (define double (double 3) => 6 (λ (x) (+ x x))) (define repeat (λ (f) (λ (x) (f (f x))))) ((repeat double) 3) => 12
  • 40. A probabilistic language Lambda calculus: (define double (double 3) => 6 (λ (x) (+ x x))) (define repeat (λ (f) (λ (x) (f (f x))))) ((repeat double) 3) => 12 Probabilistic lambda calculus: Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
  • 41. A probabilistic language Lambda calculus: (define double (double 3) => 6 (λ (x) (+ x x))) (define repeat (λ (f) (λ (x) (f (f x))))) ((repeat double) 3) => 12 Probabilistic lambda calculus: (define a (flip 0.3)) (define b (flip 0.3)) (define c (flip 0.3)) (+ a b c) Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
  • 42. A probabilistic language Lambda calculus: (define double (double 3) => 6 (λ (x) (+ x x))) (define repeat (λ (f) (λ (x) (f (f x))))) ((repeat double) 3) => 12 Probabilistic lambda calculus: (define a (flip 0.3)) => 1 (define b (flip 0.3)) => 0 (define c (flip 0.3)) => 1 (+ a b c) => 2 Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
  • 43. A probabilistic language Lambda calculus: (define double (double 3) => 6 (λ (x) (+ x x))) (define repeat (λ (f) (λ (x) (f (f x))))) ((repeat double) 3) => 12 Probabilistic lambda calculus: (define a (flip 0.3)) => 1 0 (define b (flip 0.3)) => 0 0 (define c (flip 0.3)) => 1 0 (+ a b c) => 2 0 Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
  • 44. A probabilistic language Lambda calculus: (define double (double 3) => 6 (λ (x) (+ x x))) (define repeat (λ (f) (λ (x) (f (f x))))) ((repeat double) 3) => 12 Probabilistic lambda calculus: (define a (flip 0.3)) => 1 0 0 (define b (flip 0.3)) => 0 0 0 (define c (flip 0.3)) => 1 0 1 (+ a b c) => 2 0 1 Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
  • 45. A probabilistic language Lambda calculus: (define double (double 3) => 6 (λ (x) (+ x x))) (define repeat (λ (f) (λ (x) (f (f x))))) ((repeat double) 3) => 12 Probabilistic lambda calculus: (define a (flip 0.3)) => 1 0 0 (define b (flip 0.3)) => 0 0 0 (define c (flip 0.3)) => 1 0 1 (+ a b c) => 2 0 1 .. Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
  • 46. A probabilistic language Lambda calculus: (define double (double 3) => 6 (λ (x) (+ x x))) (define repeat (λ (f) (λ (x) (f (f x))))) ((repeat double) 3) => 12 Probabilistic lambda calculus: probability / frequency (define a (flip 0.3)) => 1 0 0 (define b (flip 0.3)) => 0 0 0 (define c (flip 0.3)) => 1 0 1 (+ a b c) => 2 0 1 .. 0 1 2 3 Goodman, Mansinghka, Roy, Bonawitz, Tenenabum (2008)
  • 47. Hypothesis • The probabilistic language of thought hypothesis: Mental representations are functions in a probabilistic lambda calculus. • Thoughts are built compositionally (like molecules). • Thinking is probabilistic inference. http://projects.csail.mit.edu/church
  • 48. Bob’s box Goodman, Baker, Tenenbaum (2009; in prep.)
  • 49. Bob’s box • Bob has a box with two buttons and a light. A B Goodman, Baker, Tenenbaum (2009; in prep.)
  • 50. Bob’s box • Bob has a box with two buttons and a light. A B • He presses both buttons, and the light comes on. Goodman, Baker, Tenenbaum (2009; in prep.)
  • 51. Bob’s box • Bob has a box with two buttons and a light. A B • He presses both buttons, and the light comes on. • How does the box work? A A A A A B B B B B C C C C C A alone B alone A or B A and B Nothing causes C. causes C. cause C. causes C. causes C. Goodman, Baker, Tenenbaum (2009; in prep.)
  • 52. Human judgements Social 50 * 40 Social condition Mean Bets ($) 30 Physical 50 20 Physical condition 40 ns 30 10 20 0 A B AorB A&B none 10 N=15 0 A B AorB A&B none A alone B alone A or B A and B Nothing causes C. causes C. cause C. causes C. causes C.
  • 53. Purely causal learning Causal!only model 0.5 (query Causal-only (define world-cs (cs-prior)) 0.4 (define action (uniform)) Probability 0.3 (define outcome (world-cs init-state 0.2 action)) 0.1 world-cs (and (press-A action) 0 A B AorB A&B none A or B A&B B only none A only (press-B action) Cause of C (light-on outcome))) No conclusion is possible. The evidence is confounded.
  • 54. Explaining actions Beliefs: Desires: A B C Decision Rational action: Actions: (define decide (λ (state causal-model utility) (query (define action (action-prior)) action (flip (utility (causal-model state action))))))
  • 55. Causal learning models Causal!only model 0.5 Causal-only model Causal-only Causal-only (define world-cs (cs-prior)) 0.4 (define action (uniform)) model Probability (define outcome (world-cs 0.3 init-state 0.2 action)) 0.1 0 A B AorB A&B none A or B A&B B only none A only Cause of C (define world-cs (cs-prior)) (define utility (uniform)) Social & causal (define cs-belief world-cs) Knowledgeable (define action (decide init-state agent assumption cs-belief Rational utility)) (define outcome (world-cs agent assumption init-state action))
  • 56. Causal learning models Causal!only model 0.5 Causal-only model Causal-only Causal-only (define world-cs (cs-prior)) 0.4 (define action (uniform)) model Probability (define outcome (world-cs 0.3 init-state 0.2 action)) 0.1 0 A B AorB A&B none A or B A&B B only none A only Cause of C (define world-cs (cs-prior)) (define utility (uniform)) Social & causal (define cs-belief world-cs) (define action (decide init-state cs-belief utility)) (define outcome (world-cs init-state action))
  • 57. Causal learning models Causal!only model 0.5 Causal-only model Causal-only (define world-cs (cs-prior)) 0.4 (define action (uniform)) Probability (define outcome (world-cs 0.3 init-state 0.2 action)) 0.1 0 A B AorB A&B none A or B A&B B only none A only Cause of C (define world-cs (cs-prior)) (define utility (uniform)) Social & causal (define cs-belief world-cs) (define action (decide init-state cs-belief utility)) (define outcome (world-cs init-state action))
  • 58. Causal learning models Causal!only model 0.5 Causal-only model Causal-only (define world-cs (cs-prior)) 0.4 (define action (uniform)) Probability (define outcome (world-cs 0.3 init-state 0.2 action)) 0.1 0 A B AorB A&B none A or B A&B B only none A only Cause of C (define world-cs (cs-prior)) (define utility (uniform)) Social & causal Social!causal model 0.5 (define cs-belief world-cs) Social + causal model (define action (decide 0.4 init-state Posterior probability Probability 0.3 cs-belief utility)) 0.2 (define outcome (world-cs init-state 0.1 action)) 0 A B AorB A&B none
  • 59. Scalar implicature Some of the plants have sprouted (Plants usually sprout.) Goodman, et al (in prep)
  • 60. Scalar implicature Desires: -informative Beliefs -parsimonious Actions: “...” Some of the plants have sprouted (Plants usually sprout.) Goodman, et al (in prep)
  • 61. Scalar implicature Desires: Model: -informative Beliefs -parsimonious Plausibility (Z-score) 2 1 0 -1 Actions: -2 “...” 0:5 1:5 2:5 3:5 4:5 5:5 Number sprouted Some of the plants have sprouted (Plants usually sprout.) Goodman, et al (in prep)
  • 62. Scalar implicature Desires: Model: -informative Beliefs -parsimonious Plausibility (Z-score) 2 1 0 -1 Actions: -2 “...” 0:5 1:5 2:5 3:5 4:5 5:5 Number sprouted Some of the plants have sprouted (Plants usually sprout.) Goodman, et al (in prep)
  • 63. Scalar implicature Desires: Model: Partial -informative Full knowledge knowledge Beliefs -parsimonious Plausibility (Z-score) 2 1 0 -1 Actions: -2 “...” 0:5 1:5 2:5 3:5 4:5 5:5 0:5 1:5 2:5 3:5 4:5 5:5 Number sprouted Some of the plants have sprouted (Plants usually sprout.) Goodman, et al (in prep)
  • 64. Scalar implicature Desires: Model: Partial -informative Full knowledge knowledge Beliefs -parsimonious Plausibility (Z-score) 2 1 0 -1 Actions: -2 “...” 0:5 1:5 2:5 3:5 4:5 5:5 0:5 1:5 2:5 3:5 4:5 5:5 Number sprouted Human: Some of the plants have sprouted (Plants usually sprout.) Goodman, et al (in prep)
  • 65. Summary • The probabilistic language of thought combines composition and probability. • We can explain complex, flexible human thinking... • And engineer flexible computer intelligence.

Hinweis der Redaktion

  1. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  2. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  3. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  4. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  5. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  6. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  7. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  8. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  9. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  10. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  11. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  12. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  13. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  14. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  15. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  16. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  17. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  18. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  19. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  20. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  21. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  22. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  23. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  24. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  25. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  26. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  27. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  28. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  29. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  30. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  31. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  32. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  33. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  34. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  35. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  36. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  37. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  38. History: Two computational principles... To explain real cognition we need both. My research: unify these ideas, Tackle new areas - the real payoff.
  39. Named for Alonzo Church
  40. Named for Alonzo Church
  41. Named for Alonzo Church
  42. Named for Alonzo Church
  43. Named for Alonzo Church
  44. Named for Alonzo Church
  45. Named for Alonzo Church
  46. Named for Alonzo Church
  47. Named for Alonzo Church
  48. Named for Alonzo Church
  49. Named for Alonzo Church
  50. Named for Alonzo Church
  51. Named for Alonzo Church
  52. Named for Alonzo Church
  53. Named for Alonzo Church
  54. Named for Alonzo Church
  55. Named for Alonzo Church
  56. Named for Alonzo Church
  57. Named for Alonzo Church
  58. Named for Alonzo Church
  59. Named for Alonzo Church
  60. Named for Alonzo Church
  61. Named for Alonzo Church
  62. Named for Alonzo Church
  63. We have a formalism for stochastic functions ..church is universal for both representation and inference. rest of talk -- schematic church.. broader framework..
  64. Intuition: why would he have pressed both buttons unless he had to?
  65. Intuition: why would he have pressed both buttons unless he had to?
  66. Intuition: why would he have pressed both buttons unless he had to?
  67. Intuition: why would he have pressed both buttons unless he had to?
  68. Intuition: why would he have pressed both buttons unless he had to?
  69. Intuition: why would he have pressed both buttons unless he had to?
  70. Intuition: why would he have pressed both buttons unless he had to?
  71. But where do actions come from, and why are actions diagnostic of cs-world?
  72. B-D-A: remember this from BN?