SlideShare ist ein Scribd-Unternehmen logo
1 von 24
Downloaden Sie, um offline zu lesen
FORR
A Cognitive Architecture for Expertise
Susan L. Epstein
The Graduate Center and Hunter College of
The City University of New York
Executive summary
•  FORR (FOr the Right Reasons) is an architecture
•  FORR-based systems develop expertise
•  FORR-based systems learn quickly from problem solving experience
•  FORR-based systems are built from
§  World knowledge (descriptives)
§  Good reasons for making decisions (Advisors)
•  FORR-based systems can restructure their decision process
•  FORR confirmed cognitively plausible on human subjects
2Background • FORR • Applications
People, agents and expertise
•  People are our best model of intelligent agents
§  Some human approaches work well on really hard problems
§  Their methods are robust to imperfect data
§  They pursue multiple goals
•  If an agent is to collaborate with people, it is necessary to understand
human decision processes
•  A cognitively plausible agent simulates significant human characteristics
•  Expert does things faster and better than the rest of us [D’Andrade 1990]
3Background • FORR • Applications
Characteristics of human experts
•  They work in a domain (set of related problem classes)
•  They satisfice = make good enough decisions
•  They entertain multiple decision-making heuristics [Ratterman
& Epstein 1995]
•  They access multiple representations
•  They do situation-based reasoning [Klein & Calderwood 1991]
•  Human experts are made, not born
4
Learning is the hallmark of human intelligence
Background • FORR • Applications
Agent architecture
•  Postulates general principles
•  System shell for diverse domains
•  Requirements for cognitive plausibility
§  Display reasonable behavior
•  Make obvious decisions
•  Avoid obvious errors
•  Solve easy problems quickly
§  Balance accuracy and speed
§  Be robust to error
§  Tolerate and reason with inconsistent, incomplete, noisy data
§  Learn
5Background • FORR • Applications
Do forever
Sense the world
Select an action
Execute that action
Fundamental issues for a learning architecture
•  What is there to learn?
•  From whom to learn?
•  When to learn?
•  How to learn?
•  How to use learned knowledge to make decisions?
•  How to manage reality and noise?
6Background • FORR • Applications
Cornerstones of FORR’s pragmatic approach
•  Expertise is learned, that is, it develops with experience
•  Easy questions should have fast (reactive) answers
•  Satisfice = make good enough decisions in a simplified model of a complex
world (and recover if need be)
•  Exploit synergy inherent in multiplicity
§  Multiple domain-dependent representations
§  Multiple domain-dependent heuristics for decision making
§  Multiple learning methods
•  Maintain flexibility
§  Decouple data, learning methods, and decision methods
§  Restructure its own decision-making process
•  Transparency: explain decisions
FORR's building blocks are descriptives and Advisors
7Background • FORR • Applications
Multiple representations
•  Descriptive = a shared data object
§  Value provided on demand
§  Defined with functions that determine how and when to update it
§  Value may be learned
•  Although a descriptive has a single representation, many descriptives can
represent the same world state
•  Examples:
X-O-blank
empty/occupied
lines on the board
8Background • FORR • Applications
Multiple ways to use knowledge
•  Operationalization = how to use a data object
•  Although a descriptive has a single representation, it can be
operationalized in many ways
Ways to reason about the empty/occupied squares
Calculate possible actions
Predict opponent's move
Ways to reason about the lines
Report a result
Finish a winning line
Block your opponent’s winning line
Create a fork
Plan a win on a specific line
9Background • FORR • Applications
An Advisor operationalizes descriptives
•  Implements a class-independent, action-selection rationale
•  Limitedly-rational (resource-limited) procedure
•  Input: state of the world + descriptives + possible actions
•  Output: comments whose strengths express intensity of support or
opposition to individual actions (or sets of actions)
•  Domain-specific
< Advisor, action, strength>
Advisor
current state possible actions
relevant descriptives
10Background • FORR • Applications
Often, Advisors disagree
11
O
X X
O Panic
(prevent
immediate
loss)
Worried
(prevent long-
range loss)
Victory
(win!)
And rely on learned descriptives
•  Good openings
•  Endgame play
•  Strategies
…
Background • FORR • Applications
More about Advisors
•  Advisors have different properties
§  Some are always right
§  Some need more time to decide
§  Some would like to make a sequence of decisions, not just one
•  Comments are opinions from the perspective of the Advisor's rationale
§  On a single action
do x x is better than y
don’t do z do x or y
x is a 10, y is an 8, but z is a –3
§  On an (unordered or fully or partially ordered) set of actions
do x and y do p and then q
do p and then do q and r
12Background • FORR • Applications
FORR (FOr the Right Reasons)
•  Premise: synergy among domain-specific rationales solves problems
•  Descriptives isolate representation from reasoning
•  Advisor hierarchy
§  Tier 1: correct, quick, pre-sequenced
§  Tier 2: reactive plan rationales
§  Tier 3: voting among heuristics based on
their comment strengths and learned weights
13
<AdvisorA, action2, 10>
<AdvisorA, action4, 8>
<AdvisorA, action7, 6>
<AdvisorB, action2, 7>
<AdvisorB, action3, 9>
<AdvisorC, action1, 9>
<AdvisorC, action2, 7>
<AdvisorC, action3, 9>
<AdvisorC, action7, 9>
…
Voting
For Advisor i and action j
argmax
j
diwicij∑
Background • FORR • Applications
The FORR decision cycle
14
take actionyes
Tier 1: Reaction from
perfect knowledge
Victory T-11 T-1n…
Decision?
no
Background • FORR • Applications
state actions
descriptives
The FORR decision cycle
15
take actionyes
Tier 1: Reaction from
perfect knowledge
Victory T-11 T-1n…
Decision?
begin planyes
Tier 2: Plans triggered by
situation recognition
no
T-21 T-22 T-2m…
Decision?
Background • FORR • Applications
state actions
descriptives
The FORR decision cycle
16
take actionyes
Tier 1: Reaction from
perfect knowledge
Victory T-11 T-1n…
Decision?
begin planyes
no
T-32T-31 T-3k…
…Tier 3: Heuristic reactions
Voting take action
Tier 2: Plans triggered by
situation recognition
no
T-21 T-22 T-2m…
Decision?
Background • FORR • Applications
state actions
descriptives
How to develop a problem solver
17
•  Specialize FORR with domain knowledge
§  Problem classes
§  Advisors
§  Descriptives with learning methods
•  To solve a class of problems robustly, FORR learns
§  Descriptives’ values
§  Rationales’ relative utility
§  New Advisors
§  How to reorganize tier 3
Domain
knowledge
FORR
FORR-based
problem solver
Learned
problem solver
Problem class
Experience
WARNING: problem solving
often provides noisy data
Background • FORR • Applications
FORR-based single agents
18
•  Hoyle learned to play 19 two-person, perfect-information, finite-board
games as well or better than human / machine expert [Epstein, 2001]
•  Ariadne learned to navigate efficiently in grid worlds, despite perceptual
limitations and no map [Epstein, 1995]
•  ACE learned to solve constraint satisfaction problems and rediscovered
the BrĂŠlaz heuristic [ Epstein & Freuder, 2005]
•  SemaFORR: controls an autonomous search-and-rescue robot [Epstein,
Schneider, Ozgelen, Munoz, Costantino, Sklar & Parsons, 2012]
Background • FORR • Applications
Lessons learned
19
•  Reactive plans work well
•  Elimination of inaccurate heuristics produces substantial speedup
•  Lazy descriptive computation also provides speedup
•  Self-awareness supports transparency
•  Advisor weights may have problem-stage context
•  Weight learning has subtle pitfalls (example extraction)
•  Autonomous restructuring must balance accuracy against risk
•  Sometimes it is more efficient not to reason at all
Background • FORR • Applications
FORR-based collaborating agents
20
•  Co-FORR: 5 collaborating agents for 2D park design [Epstein, 1998]
•  FORRSooth: learned to conduct a spoken dialogue with a library patron
who orders books [Epstein, Passonneau, Gordon, & Ligorio, 2012]
•  SemaFORR: controls autonomous search-and-rescue robot team [Epstein,
Aroor, Evanusa, Sklar & Parsons, 2015]
Each new domain poses new challenges whose solution strengthens FORR
Background • FORR • Applications
FORR-based results
21
•  PhD theses
§  Shih on learning multiple behavior sequences, 2000
§  Lock on learning multiple plans from behavior sequences, 2003
§  Petrovic on weight learning for multiple Advisors, 2008
§  Ligorio on learning to select attributes, 2011
§  Li on representation and exploitation of multiple complex relationships, 2011
§  Yun on parallelization of multiple solvers, 2013
§  Osisek on application of multiple relationships in recommendation (in progress)
§  Aroor on reactive planning for multiple robots (in progress)
•  Applications to bioinformatics (with Dr. Lei Xie)
§  Protein-protein interaction networks
§  Virtual drug screening
Background • FORR • Applications
Take home message
To develop expertise
FORR learns to harness the synergy of
multiplicity in representation and reasoning
22Background • FORR • Applications
Acknowledgements
We gratefully acknowledge the support of
The National Science Foundation
CUNY’s High Performance Computing Center
Continued thanks to my collaborators
Gene Freuder Rebecca Passonneau
Rick Wallace Lei Xie
Elizabeth Sklar Simon Parsons
and a host of undergraduate and graduate students
with whom I continue to learn
23
Selected references
•  Epstein, S. L. 2001. Learning to Play Expertly: A Tutorial on Hoyle. In
Machine Learning in Game Playing
•  Epstein, S. L. 1998. Pragmatic Navigation: Reactivity, Heuristics, and
Search. Artificial Intelligence, 100 (1-2): 275-322.
•  Epstein, S. L., E. C. Freuder and M. Wallace 2005. Learning to Support
Constraint Programmers. Computational Intelligence 21(4): 337-371.
•  Epstein, S. L., R. J. Passonneau, T. Ligorio and J. Gordon. 2012. Data
Mining to Support Human-Machine Dialogue for Autonomous Agents. In
Proceedings of Agents and Data Mining Interaction (ADMI2011).
•  Epstein, S.L., Aroor, A., Evanusa, M., Sklar, E.I., Simon, S. 2015. Navigation
with Learned Spatial Affordances. In Proceedings of CogSci 2015.
http://www.cs.hunter.cuny.edu/~epstein/
24

Weitere ähnliche Inhalte

Andere mochten auch

Holographic Memory
Holographic MemoryHolographic Memory
Holographic Memorysajayonline
 
Cognitive Psychology in UX
Cognitive Psychology in UXCognitive Psychology in UX
Cognitive Psychology in UXHany Rizk
 
Social information processing theory
Social information processing theorySocial information processing theory
Social information processing theoryWhitireia New Zealand
 
Social Cognitive Theory
Social Cognitive Theory Social Cognitive Theory
Social Cognitive Theory mhonjo1
 
Social Constructivism & Cognitive Development Theory
Social Constructivism & Cognitive Development TheorySocial Constructivism & Cognitive Development Theory
Social Constructivism & Cognitive Development TheorySinky Zh
 
How cognitive services can be used in various industries
How cognitive services can be used in various industriesHow cognitive services can be used in various industries
How cognitive services can be used in various industriesSoftweb Solutions
 
The ins and outs of project based learning
The ins and outs of project based learningThe ins and outs of project based learning
The ins and outs of project based learningMontse Irun
 
Learning theories and their implications on educational technology
Learning theories  and their implications on educational technologyLearning theories  and their implications on educational technology
Learning theories and their implications on educational technologyRONNIE PASIGUI
 
Theories of Learning
Theories of LearningTheories of Learning
Theories of Learningsantiniescolini
 

Andere mochten auch (10)

Theory collaborative learning
Theory collaborative learningTheory collaborative learning
Theory collaborative learning
 
Holographic Memory
Holographic MemoryHolographic Memory
Holographic Memory
 
Cognitive Psychology in UX
Cognitive Psychology in UXCognitive Psychology in UX
Cognitive Psychology in UX
 
Social information processing theory
Social information processing theorySocial information processing theory
Social information processing theory
 
Social Cognitive Theory
Social Cognitive Theory Social Cognitive Theory
Social Cognitive Theory
 
Social Constructivism & Cognitive Development Theory
Social Constructivism & Cognitive Development TheorySocial Constructivism & Cognitive Development Theory
Social Constructivism & Cognitive Development Theory
 
How cognitive services can be used in various industries
How cognitive services can be used in various industriesHow cognitive services can be used in various industries
How cognitive services can be used in various industries
 
The ins and outs of project based learning
The ins and outs of project based learningThe ins and outs of project based learning
The ins and outs of project based learning
 
Learning theories and their implications on educational technology
Learning theories  and their implications on educational technologyLearning theories  and their implications on educational technology
Learning theories and their implications on educational technology
 
Theories of Learning
Theories of LearningTheories of Learning
Theories of Learning
 

Ähnlich wie Susan epstein at ibm csig speaker series

Operational research ppt
Operational research pptOperational research ppt
Operational research pptDhrubajyotiBora1
 
LESSON 8 EXPERT SYSTEMS BASICS.ppt
LESSON 8 EXPERT SYSTEMS BASICS.pptLESSON 8 EXPERT SYSTEMS BASICS.ppt
LESSON 8 EXPERT SYSTEMS BASICS.pptJoyleenChemutai1
 
Lec 4 expert systems
Lec 4  expert systemsLec 4  expert systems
Lec 4 expert systemsEyob Sisay
 
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?krisztianbalog
 
5 ai lecture-05 expert system
5  ai lecture-05 expert system5  ai lecture-05 expert system
5 ai lecture-05 expert systemAhmad sohail Kakar
 
Ai lecture 05 expert system
Ai lecture 05 expert systemAi lecture 05 expert system
Ai lecture 05 expert systemAhmad sohail Kakar
 
Methodology 4 both sides of the pond
Methodology 4 both sides of the pondMethodology 4 both sides of the pond
Methodology 4 both sides of the pondDoctoralNet Limited
 
4_6_Expert Systems_1.pptx
4_6_Expert Systems_1.pptx4_6_Expert Systems_1.pptx
4_6_Expert Systems_1.pptxshwetadubey244305
 
Advanced topics research
Advanced topics researchAdvanced topics research
Advanced topics researchkieran122
 
Delphi Method by Amr Ali
Delphi Method  by Amr AliDelphi Method  by Amr Ali
Delphi Method by Amr AliAmr Ali
 
ICS3211_lecture 9_2022.pdf
ICS3211_lecture 9_2022.pdfICS3211_lecture 9_2022.pdf
ICS3211_lecture 9_2022.pdfVanessa Camilleri
 
Requirement elicitation
Requirement elicitationRequirement elicitation
Requirement elicitationvivacemente
 
Developing affective constructs
Developing affective constructsDeveloping affective constructs
Developing affective constructsCarlo Magno
 
Technological Problem Solving Seminar
Technological Problem Solving SeminarTechnological Problem Solving Seminar
Technological Problem Solving SeminarDavid Morrison-Love
 

Ähnlich wie Susan epstein at ibm csig speaker series (20)

Operational research ppt
Operational research pptOperational research ppt
Operational research ppt
 
LESSON 8 EXPERT SYSTEMS BASICS.ppt
LESSON 8 EXPERT SYSTEMS BASICS.pptLESSON 8 EXPERT SYSTEMS BASICS.ppt
LESSON 8 EXPERT SYSTEMS BASICS.ppt
 
Iti week 10 (3)
Iti week 10 (3)Iti week 10 (3)
Iti week 10 (3)
 
MIS Unit-2.pptx
MIS Unit-2.pptxMIS Unit-2.pptx
MIS Unit-2.pptx
 
Lec 4 expert systems
Lec 4  expert systemsLec 4  expert systems
Lec 4 expert systems
 
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
 
5 ai lecture-05 expert system
5  ai lecture-05 expert system5  ai lecture-05 expert system
5 ai lecture-05 expert system
 
Ai lecture 05 expert system
Ai lecture 05 expert systemAi lecture 05 expert system
Ai lecture 05 expert system
 
Methodology 4 both sides of the pond
Methodology 4 both sides of the pondMethodology 4 both sides of the pond
Methodology 4 both sides of the pond
 
The art of project estimation
The art of project estimationThe art of project estimation
The art of project estimation
 
4_6_Expert Systems_1.pptx
4_6_Expert Systems_1.pptx4_6_Expert Systems_1.pptx
4_6_Expert Systems_1.pptx
 
5. the perception process
5. the perception process5. the perception process
5. the perception process
 
ICS3211 lecture 10
ICS3211 lecture 10ICS3211 lecture 10
ICS3211 lecture 10
 
Advanced topics research
Advanced topics researchAdvanced topics research
Advanced topics research
 
Swarm intelligence
Swarm intelligenceSwarm intelligence
Swarm intelligence
 
Delphi Method by Amr Ali
Delphi Method  by Amr AliDelphi Method  by Amr Ali
Delphi Method by Amr Ali
 
ICS3211_lecture 9_2022.pdf
ICS3211_lecture 9_2022.pdfICS3211_lecture 9_2022.pdf
ICS3211_lecture 9_2022.pdf
 
Requirement elicitation
Requirement elicitationRequirement elicitation
Requirement elicitation
 
Developing affective constructs
Developing affective constructsDeveloping affective constructs
Developing affective constructs
 
Technological Problem Solving Seminar
Technological Problem Solving SeminarTechnological Problem Solving Seminar
Technological Problem Solving Seminar
 

Mehr von diannepatricia

Teaching cognitive computing with ibm watson
Teaching cognitive computing with ibm watsonTeaching cognitive computing with ibm watson
Teaching cognitive computing with ibm watsondiannepatricia
 
Cognitive systems institute talk 8 june 2017 - v.1.0
Cognitive systems institute talk   8 june 2017 - v.1.0Cognitive systems institute talk   8 june 2017 - v.1.0
Cognitive systems institute talk 8 june 2017 - v.1.0diannepatricia
 
Building Compassionate Conversational Systems
Building Compassionate Conversational SystemsBuilding Compassionate Conversational Systems
Building Compassionate Conversational Systemsdiannepatricia
 
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”diannepatricia
 
Cognitive Insights drive self-driving Accessibility
Cognitive Insights drive self-driving AccessibilityCognitive Insights drive self-driving Accessibility
Cognitive Insights drive self-driving Accessibilitydiannepatricia
 
Artificial Intellingence in the Car
Artificial Intellingence in the CarArtificial Intellingence in the Car
Artificial Intellingence in the Cardiannepatricia
 
“Semantic PDF Processing & Document Representation”
“Semantic PDF Processing & Document Representation”“Semantic PDF Processing & Document Representation”
“Semantic PDF Processing & Document Representation”diannepatricia
 
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...diannepatricia
 
170330 cognitive systems institute speaker series mark sherman - watson pr...
170330 cognitive systems institute speaker series    mark sherman - watson pr...170330 cognitive systems institute speaker series    mark sherman - watson pr...
170330 cognitive systems institute speaker series mark sherman - watson pr...diannepatricia
 
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”diannepatricia
 
Cognitive Assistance for the Aging
Cognitive Assistance for the AgingCognitive Assistance for the Aging
Cognitive Assistance for the Agingdiannepatricia
 
From complex Systems to Networks: Discovering and Modeling the Correct Network"
From complex Systems to Networks: Discovering and Modeling the Correct Network"From complex Systems to Networks: Discovering and Modeling the Correct Network"
From complex Systems to Networks: Discovering and Modeling the Correct Network"diannepatricia
 
The Role of Dialog in Augmented Intelligence
The Role of Dialog in Augmented IntelligenceThe Role of Dialog in Augmented Intelligence
The Role of Dialog in Augmented Intelligencediannepatricia
 
Developing Cognitive Systems to Support Team Cognition
Developing Cognitive Systems to Support Team CognitionDeveloping Cognitive Systems to Support Team Cognition
Developing Cognitive Systems to Support Team Cognitiondiannepatricia
 
Cyber-Social Learning Systems
Cyber-Social Learning SystemsCyber-Social Learning Systems
Cyber-Social Learning Systemsdiannepatricia
 
“IT Technology Trends in 2017… and Beyond”
“IT Technology Trends in 2017… and Beyond”“IT Technology Trends in 2017… and Beyond”
“IT Technology Trends in 2017… and Beyond”diannepatricia
 
"Curious Learning: using a mobile platform for early literacy education as a ...
"Curious Learning: using a mobile platform for early literacy education as a ..."Curious Learning: using a mobile platform for early literacy education as a ...
"Curious Learning: using a mobile platform for early literacy education as a ...diannepatricia
 
Embodied Cognition - Booch HICSS50
Embodied Cognition - Booch HICSS50Embodied Cognition - Booch HICSS50
Embodied Cognition - Booch HICSS50diannepatricia
 
KATE - a Platform for Machine Learning
KATE - a Platform for Machine LearningKATE - a Platform for Machine Learning
KATE - a Platform for Machine Learningdiannepatricia
 
Cognitive Computing for Aging Society
Cognitive Computing for Aging SocietyCognitive Computing for Aging Society
Cognitive Computing for Aging Societydiannepatricia
 

Mehr von diannepatricia (20)

Teaching cognitive computing with ibm watson
Teaching cognitive computing with ibm watsonTeaching cognitive computing with ibm watson
Teaching cognitive computing with ibm watson
 
Cognitive systems institute talk 8 june 2017 - v.1.0
Cognitive systems institute talk   8 june 2017 - v.1.0Cognitive systems institute talk   8 june 2017 - v.1.0
Cognitive systems institute talk 8 june 2017 - v.1.0
 
Building Compassionate Conversational Systems
Building Compassionate Conversational SystemsBuilding Compassionate Conversational Systems
Building Compassionate Conversational Systems
 
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
 
Cognitive Insights drive self-driving Accessibility
Cognitive Insights drive self-driving AccessibilityCognitive Insights drive self-driving Accessibility
Cognitive Insights drive self-driving Accessibility
 
Artificial Intellingence in the Car
Artificial Intellingence in the CarArtificial Intellingence in the Car
Artificial Intellingence in the Car
 
“Semantic PDF Processing & Document Representation”
“Semantic PDF Processing & Document Representation”“Semantic PDF Processing & Document Representation”
“Semantic PDF Processing & Document Representation”
 
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
 
170330 cognitive systems institute speaker series mark sherman - watson pr...
170330 cognitive systems institute speaker series    mark sherman - watson pr...170330 cognitive systems institute speaker series    mark sherman - watson pr...
170330 cognitive systems institute speaker series mark sherman - watson pr...
 
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”
 
Cognitive Assistance for the Aging
Cognitive Assistance for the AgingCognitive Assistance for the Aging
Cognitive Assistance for the Aging
 
From complex Systems to Networks: Discovering and Modeling the Correct Network"
From complex Systems to Networks: Discovering and Modeling the Correct Network"From complex Systems to Networks: Discovering and Modeling the Correct Network"
From complex Systems to Networks: Discovering and Modeling the Correct Network"
 
The Role of Dialog in Augmented Intelligence
The Role of Dialog in Augmented IntelligenceThe Role of Dialog in Augmented Intelligence
The Role of Dialog in Augmented Intelligence
 
Developing Cognitive Systems to Support Team Cognition
Developing Cognitive Systems to Support Team CognitionDeveloping Cognitive Systems to Support Team Cognition
Developing Cognitive Systems to Support Team Cognition
 
Cyber-Social Learning Systems
Cyber-Social Learning SystemsCyber-Social Learning Systems
Cyber-Social Learning Systems
 
“IT Technology Trends in 2017… and Beyond”
“IT Technology Trends in 2017… and Beyond”“IT Technology Trends in 2017… and Beyond”
“IT Technology Trends in 2017… and Beyond”
 
"Curious Learning: using a mobile platform for early literacy education as a ...
"Curious Learning: using a mobile platform for early literacy education as a ..."Curious Learning: using a mobile platform for early literacy education as a ...
"Curious Learning: using a mobile platform for early literacy education as a ...
 
Embodied Cognition - Booch HICSS50
Embodied Cognition - Booch HICSS50Embodied Cognition - Booch HICSS50
Embodied Cognition - Booch HICSS50
 
KATE - a Platform for Machine Learning
KATE - a Platform for Machine LearningKATE - a Platform for Machine Learning
KATE - a Platform for Machine Learning
 
Cognitive Computing for Aging Society
Cognitive Computing for Aging SocietyCognitive Computing for Aging Society
Cognitive Computing for Aging Society
 

KĂźrzlich hochgeladen

Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
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
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
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
 
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
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 

KĂźrzlich hochgeladen (20)

Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
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
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
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
 
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
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 

Susan epstein at ibm csig speaker series

  • 1. FORR A Cognitive Architecture for Expertise Susan L. Epstein The Graduate Center and Hunter College of The City University of New York
  • 2. Executive summary •  FORR (FOr the Right Reasons) is an architecture •  FORR-based systems develop expertise •  FORR-based systems learn quickly from problem solving experience •  FORR-based systems are built from §  World knowledge (descriptives) §  Good reasons for making decisions (Advisors) •  FORR-based systems can restructure their decision process •  FORR confirmed cognitively plausible on human subjects 2Background • FORR • Applications
  • 3. People, agents and expertise •  People are our best model of intelligent agents §  Some human approaches work well on really hard problems §  Their methods are robust to imperfect data §  They pursue multiple goals •  If an agent is to collaborate with people, it is necessary to understand human decision processes •  A cognitively plausible agent simulates significant human characteristics •  Expert does things faster and better than the rest of us [D’Andrade 1990] 3Background • FORR • Applications
  • 4. Characteristics of human experts •  They work in a domain (set of related problem classes) •  They satisfice = make good enough decisions •  They entertain multiple decision-making heuristics [Ratterman & Epstein 1995] •  They access multiple representations •  They do situation-based reasoning [Klein & Calderwood 1991] •  Human experts are made, not born 4 Learning is the hallmark of human intelligence Background • FORR • Applications
  • 5. Agent architecture •  Postulates general principles •  System shell for diverse domains •  Requirements for cognitive plausibility §  Display reasonable behavior •  Make obvious decisions •  Avoid obvious errors •  Solve easy problems quickly §  Balance accuracy and speed §  Be robust to error §  Tolerate and reason with inconsistent, incomplete, noisy data §  Learn 5Background • FORR • Applications Do forever Sense the world Select an action Execute that action
  • 6. Fundamental issues for a learning architecture •  What is there to learn? •  From whom to learn? •  When to learn? •  How to learn? •  How to use learned knowledge to make decisions? •  How to manage reality and noise? 6Background • FORR • Applications
  • 7. Cornerstones of FORR’s pragmatic approach •  Expertise is learned, that is, it develops with experience •  Easy questions should have fast (reactive) answers •  Satisfice = make good enough decisions in a simplified model of a complex world (and recover if need be) •  Exploit synergy inherent in multiplicity §  Multiple domain-dependent representations §  Multiple domain-dependent heuristics for decision making §  Multiple learning methods •  Maintain flexibility §  Decouple data, learning methods, and decision methods §  Restructure its own decision-making process •  Transparency: explain decisions FORR's building blocks are descriptives and Advisors 7Background • FORR • Applications
  • 8. Multiple representations •  Descriptive = a shared data object §  Value provided on demand §  Defined with functions that determine how and when to update it §  Value may be learned •  Although a descriptive has a single representation, many descriptives can represent the same world state •  Examples: X-O-blank empty/occupied lines on the board 8Background • FORR • Applications
  • 9. Multiple ways to use knowledge •  Operationalization = how to use a data object •  Although a descriptive has a single representation, it can be operationalized in many ways Ways to reason about the empty/occupied squares Calculate possible actions Predict opponent's move Ways to reason about the lines Report a result Finish a winning line Block your opponent’s winning line Create a fork Plan a win on a specific line 9Background • FORR • Applications
  • 10. An Advisor operationalizes descriptives •  Implements a class-independent, action-selection rationale •  Limitedly-rational (resource-limited) procedure •  Input: state of the world + descriptives + possible actions •  Output: comments whose strengths express intensity of support or opposition to individual actions (or sets of actions) •  Domain-specific < Advisor, action, strength> Advisor current state possible actions relevant descriptives 10Background • FORR • Applications
  • 11. Often, Advisors disagree 11 O X X O Panic (prevent immediate loss) Worried (prevent long- range loss) Victory (win!) And rely on learned descriptives •  Good openings •  Endgame play •  Strategies … Background • FORR • Applications
  • 12. More about Advisors •  Advisors have different properties §  Some are always right §  Some need more time to decide §  Some would like to make a sequence of decisions, not just one •  Comments are opinions from the perspective of the Advisor's rationale §  On a single action do x x is better than y don’t do z do x or y x is a 10, y is an 8, but z is a –3 §  On an (unordered or fully or partially ordered) set of actions do x and y do p and then q do p and then do q and r 12Background • FORR • Applications
  • 13. FORR (FOr the Right Reasons) •  Premise: synergy among domain-specific rationales solves problems •  Descriptives isolate representation from reasoning •  Advisor hierarchy §  Tier 1: correct, quick, pre-sequenced §  Tier 2: reactive plan rationales §  Tier 3: voting among heuristics based on their comment strengths and learned weights 13 <AdvisorA, action2, 10> <AdvisorA, action4, 8> <AdvisorA, action7, 6> <AdvisorB, action2, 7> <AdvisorB, action3, 9> <AdvisorC, action1, 9> <AdvisorC, action2, 7> <AdvisorC, action3, 9> <AdvisorC, action7, 9> … Voting For Advisor i and action j argmax j diwicij∑ Background • FORR • Applications
  • 14. The FORR decision cycle 14 take actionyes Tier 1: Reaction from perfect knowledge Victory T-11 T-1n… Decision? no Background • FORR • Applications state actions descriptives
  • 15. The FORR decision cycle 15 take actionyes Tier 1: Reaction from perfect knowledge Victory T-11 T-1n… Decision? begin planyes Tier 2: Plans triggered by situation recognition no T-21 T-22 T-2m… Decision? Background • FORR • Applications state actions descriptives
  • 16. The FORR decision cycle 16 take actionyes Tier 1: Reaction from perfect knowledge Victory T-11 T-1n… Decision? begin planyes no T-32T-31 T-3k… …Tier 3: Heuristic reactions Voting take action Tier 2: Plans triggered by situation recognition no T-21 T-22 T-2m… Decision? Background • FORR • Applications state actions descriptives
  • 17. How to develop a problem solver 17 •  Specialize FORR with domain knowledge §  Problem classes §  Advisors §  Descriptives with learning methods •  To solve a class of problems robustly, FORR learns §  Descriptives’ values §  Rationales’ relative utility §  New Advisors §  How to reorganize tier 3 Domain knowledge FORR FORR-based problem solver Learned problem solver Problem class Experience WARNING: problem solving often provides noisy data Background • FORR • Applications
  • 18. FORR-based single agents 18 •  Hoyle learned to play 19 two-person, perfect-information, finite-board games as well or better than human / machine expert [Epstein, 2001] •  Ariadne learned to navigate efficiently in grid worlds, despite perceptual limitations and no map [Epstein, 1995] •  ACE learned to solve constraint satisfaction problems and rediscovered the BrĂŠlaz heuristic [ Epstein & Freuder, 2005] •  SemaFORR: controls an autonomous search-and-rescue robot [Epstein, Schneider, Ozgelen, Munoz, Costantino, Sklar & Parsons, 2012] Background • FORR • Applications
  • 19. Lessons learned 19 •  Reactive plans work well •  Elimination of inaccurate heuristics produces substantial speedup •  Lazy descriptive computation also provides speedup •  Self-awareness supports transparency •  Advisor weights may have problem-stage context •  Weight learning has subtle pitfalls (example extraction) •  Autonomous restructuring must balance accuracy against risk •  Sometimes it is more efficient not to reason at all Background • FORR • Applications
  • 20. FORR-based collaborating agents 20 •  Co-FORR: 5 collaborating agents for 2D park design [Epstein, 1998] •  FORRSooth: learned to conduct a spoken dialogue with a library patron who orders books [Epstein, Passonneau, Gordon, & Ligorio, 2012] •  SemaFORR: controls autonomous search-and-rescue robot team [Epstein, Aroor, Evanusa, Sklar & Parsons, 2015] Each new domain poses new challenges whose solution strengthens FORR Background • FORR • Applications
  • 21. FORR-based results 21 •  PhD theses §  Shih on learning multiple behavior sequences, 2000 §  Lock on learning multiple plans from behavior sequences, 2003 §  Petrovic on weight learning for multiple Advisors, 2008 §  Ligorio on learning to select attributes, 2011 §  Li on representation and exploitation of multiple complex relationships, 2011 §  Yun on parallelization of multiple solvers, 2013 §  Osisek on application of multiple relationships in recommendation (in progress) §  Aroor on reactive planning for multiple robots (in progress) •  Applications to bioinformatics (with Dr. Lei Xie) §  Protein-protein interaction networks §  Virtual drug screening Background • FORR • Applications
  • 22. Take home message To develop expertise FORR learns to harness the synergy of multiplicity in representation and reasoning 22Background • FORR • Applications
  • 23. Acknowledgements We gratefully acknowledge the support of The National Science Foundation CUNY’s High Performance Computing Center Continued thanks to my collaborators Gene Freuder Rebecca Passonneau Rick Wallace Lei Xie Elizabeth Sklar Simon Parsons and a host of undergraduate and graduate students with whom I continue to learn 23
  • 24. Selected references •  Epstein, S. L. 2001. Learning to Play Expertly: A Tutorial on Hoyle. In Machine Learning in Game Playing •  Epstein, S. L. 1998. Pragmatic Navigation: Reactivity, Heuristics, and Search. Artificial Intelligence, 100 (1-2): 275-322. •  Epstein, S. L., E. C. Freuder and M. Wallace 2005. Learning to Support Constraint Programmers. Computational Intelligence 21(4): 337-371. •  Epstein, S. L., R. J. Passonneau, T. Ligorio and J. Gordon. 2012. Data Mining to Support Human-Machine Dialogue for Autonomous Agents. In Proceedings of Agents and Data Mining Interaction (ADMI2011). •  Epstein, S.L., Aroor, A., Evanusa, M., Sklar, E.I., Simon, S. 2015. Navigation with Learned Spatial Affordances. In Proceedings of CogSci 2015. http://www.cs.hunter.cuny.edu/~epstein/ 24