SlideShare ist ein Scribd-Unternehmen logo
1 von 52
Md. Asfak Mahamud
m.asfak@yahoo.com
Software Engineer
KAZ Software Ltd.
Bangladesh
Date: Feb 22, 2011
Introduction to HTM
Disclaimer
This theory/technology is a result from research of several decades. This
theory/technology is doing a great job in various practical fields today. Many
companies (for more info http://numenta.com/about-numenta/customers.php ) are using it actively. Many
(e.g. http://www.atl.lmco.com/papers/1597.pdf) are doing research on its various applications.
The speaker has been reading on this technology for a very short time. Any misleading
or wrong explanation may occur due to lack of knowledge of the speaker.
Every slide on this presentation has been tried to serve with source of reference (if
required). For any confusion audiences are requested to visit the reference pages.
The speaker hereby is declaring earnest eagerness to change any content of this
presentation if it violets any code of conduct of any organization or company or
institutions or hurts any individual.
Points
• Ground.
• Rule.
• Ball.
• Bat.
• Umpire.
• Player.
• Powerplay.
This is the first time Bangladesh is one of the
organizing countries of ICC World Cup Cricket.
To keep a remembrance of on going cricket craze, points
are intentionally coined from sports more specifically
from Cricket.
Image url: http://en.wikipedia.org/wiki/File:2011_Cricket_World_Cup_Logo.svg
Points
• Ground. (A rational motive for a belief or action - wordweb)
• Rule.
• Ball.
• Bat.
• Umpire.
• Player.
• Powerplay. Image source: http://www.cricket-for-parents.com/cricket-fielding-positions.html
At 19 Weeks of Fetus
Baby's brain designates specialized
areas for
– smell, taste, hearing, vision, and touch.
Some research suggests that baby
may be able to hear sound now.
Reference: http://www.babycenter.com/fetal-development-images-19-weeks
Image collected and edited from: http://www.babycenter.com/fetal-development-images-19-weeks
Aniya’s Learning
At her two years of old my niece, Aniya somehow knew about dog (in bengali কুকুর, ‘Kukur’). In her
voice it was “Kukun”, কুকুন। She also knew the bengali word বড় ( বড়, ‘Boro’ means Big). In her voice it was
‘Bolo’, বোলো।
কুকুন
Image: http://jaagruti.org/2010/04/18/the-indian-street-dog/
http://www.impactlab.net/2007/04/13/building-brainlike-computers/
Image: http://www.travelblog.org/Photos/1654785
বোলো কুকুন
Supervised Unsupervised
Ambiguity
Vernon B Mountcastle
Formerly University Professor of Neuroscience,
Johns Hopkins University, Baltimore, Maryland, USA
Image: http://www.ibro.org/Pub/Pub_Main_Display.asp?LC_Docs_ID=3561
An organizing principle for
cerebral function: the unit
module and the distributed
system. In The Mindful Brain.
MIT Press, 1978.
Info:
Video: http://tinyurl.com/4n9ux59
Dileep George, Cognitive Computing, 2007
Paper: http://tinyurl.com/464x4yt
Dileep George, Phd Thesis, Stanford University, June, 2008
Same Algorithm for
- Audition,
- Vision,
- Speech
and so on.
Common Cortical Algorithm
No learning algorithm has an inherent
superiority over another algorithm for all
learning problems.
(Wolpert, 1995)
No Free Lunch Theorem
“An algorithm’s superiority comes from the
assumptions that it makes about the problem
at hand.”
Solution
To find Assumptions
– General enough
to large classes of problems.
– Specific enough
to make learning possible.
Info from:
Video: http://tinyurl.com/4n9ux59
Dileep George, Cognitive Computing, 2007
To believe 3 three things
• The principles of brain function can be understood.
• We can build machines that work on these principles.
• Many machine learning, AI and robotics problems can only
be solved this way.
Jeff Hawkins,
November 2010,
“Advances in Modeling Neocortex and its impacts on
machine intelligence”
Link: http://tinyurl.com/4reyyzf
World Cortex
Physics
Statistics
Biology
Anatomy
Structure
Physiological Results
Psychological Results
Info from: video: http://tinyurl.com/4n9ux59 Dileep George, Cognitive Computing, 2007
Comparison of neocortex among mouse,
monkey and human. The neocortical
surfaces are colored blue.
Image ref:
http://www.nibb.ac.jp/brish/Gallery/cortexE.html
Why Neocortex is on focus?
Felleman and Van Essens (1991)
Model of the cortical hierarchy
Image from:
http://thebrain2.wikidot.com/tribal-networks
• 75% of volume of human brain
• All high level vision, audition, motor, language, thought.
• Composed of a repetitive element
– Complex
– Hierarchical
Jeff Hawkins,
November 2010,
“Advances in Modeling Neocortex and
its impacts on machine intelligence”
Link: http://tinyurl.com/4reyyzf
Cells that are vertically
aligned in columns all
respond
to edges with the same
orientation.
Figure: Response properties
of cells in V1, the first cortical
region to process information
from the retina.
Ref: Appendix A: A Comparison between Biological Neurons and HTM cells
Appendix B: A Comparison of Layers in the Neocortex and an HTM Region
Hierarchical Temporal Memory including HTM Cortical Learning Algorithms
http://tinyurl.com/4pr59bv
Biological Neuron and Layers in Neocortex
ApicalDendrite
DistalDendrite
ProximalDendrite
Axon
Layered and Columnar organization
of the neocortex becomes evident when
neural tissue is stained.
Mini-Column: The smallest columnar
Structure of the neocortex.
Diameter: 30um (Approx )
Contains: 80-100 neurons
across all five cellular layers.
Inter Region Major Connections
Ref: Appendix B: A Comparison of Layers in the Neocortex and an HTM Region
Hierarchical Temporal Memory including HTM Cortical Learning Algorithms
http://tinyurl.com/4pr59bv
Indirect
Feed forward
Pathway.
Direct Feed
forward Pathway.
Feed back
Pathway.
Biological Neuron, Simple Artificial Neuron, HTM Cell,
HTM Regions
Ref: Appendix A: A Comparison between Biological Neurons and HTM cells
Hierarchical Temporal Memory including HTM Cortical Learning Algorithms
http://tinyurl.com/4pr59bv
DistalDendrite
Proximal Dendrite
Axon
Jeff Hawkins,
November 2010,
“Advances in Modeling Neocortex and its impacts on machine intelligence”
Link: http://tinyurl.com/4reyyzf
“HOW THE BRAIN MIGHT WORK: A HIERARCHICAL AND
TEMPORAL MODEL FOR LEARNING AND RECOGNITION”,
Dileep George, June 2008,
Stanford University
Old Wine in New Glass?
NO !!
 Hierarchy in space and time.
 Slowness of time, combined with the hierarchy, enables efficient learning of intermediate
levels of the hierarchy.
 Learning of causes by using time continuity and actions.
 Models of attention and specific memories.
 A probabilistic model specified in terms of relations between a hierarchy of causes.
 Belief Propagation in the hierarchy to use temporal and spatial context for inference.
Ref: http://numenta.com/htm-overview/education/HTM_Comparison.pdf
Old Wine in New Glass?
Ref: http://numenta.com/htm-overview/education/HTM_Comparison.pdf
General-
Purpose
Probabilistic
Models
• Baysian Networks
• Energy-based
Models
(HTMs do not treat them as rivals
but tools in its toolbox.)
• HHHMs (Hierarchical Hidden Markov Model, a special
form of Baysian Network)
have hierarchy only in space. HTM has hierarchy in space and time.
• Boltzman Machine and Helhmholtz Machine
do not include temporal aspects of data in the model and do not make
any assumptions about hierarchy.
Non-
Generative
Models
• Support Vector
Machines (SVMs)
• Classic Neural
Networks
• Slow Feature
Analysis (Many properties
similar to HTM)
• They are typically supervised. HTMs are fundamentally
unsupervised.
• They are not able to generate data for predictions. HTM can do
that.
Empirical
Neurobiological
Model
• HMAX Model
(Many properties similar to
HTMs)
• It can not predict forward in time. HTM can do that.
Old Wine in New Glass?
Ref: http://numenta.com/htm-overview/education/HTM_Comparison.pdf
General-
Purpose
Probabilistic
Models
• Baysian Networks
• Energy-based
Models
(HTMs do not treat them as rivals
but tools in its toolbox.)
• HHHMs (Hierarchical Hidden Markov Model, a special
form of Baysian Network)
have hierarchy only in space. HTM has hierarchy in space and time.
• Boltzman Machine and Helhmholtz Machine
do not include temporal aspects of data in the model and do not make
any assumptions about hierarchy.
Non-
Generative
Models
• Support Vector
Machines (SVMs)
• Classic Neural
Networks
• Slow Feature
Analysis (Many properties
similar to HTM)
• They are typically supervised. HTMs are fundamentally
unsupervised.
• They are not able to generate data for predictions. HTM can do
that.
Empirical
Neurobiological
Model
• HMAX Model
(Many properties similar to
HTMs)
• It can not predict forward in time. HTM can do that.
Old Wine in New Glass?
Ref: http://numenta.com/htm-overview/education/HTM_Comparison.pdf
General-
Purpose
Probabilistic
Models
• Baysian Networks
• Energy-based
Models
(HTMs do not treat them as rivals
but tools in its toolbox.)
• HHHMs (Hierarchical Hidden Markov Model, a special
form of Baysian Network)
have hierarchy only in space. HTM has hierarchy in space and time.
• Boltzman Machine and Helhmholtz Machine
do not include temporal aspects of data in the model and do not make
any assumptions about hierarchy.
Non-
Generative
Models
• Support Vector
Machines (SVMs)
• Classic Neural
Networks
• Slow Feature
Analysis (Many properties
similar to HTM)
• They are typically supervised. HTMs are fundamentally
unsupervised.
• They are not able to generate data for predictions. HTM can do
that.
Empirical
Neurobiological
Model
• HMAX Model
(Many properties similar to
HTMs)
• It can not predict forward in time. HTM can do that.
HTM in the List of AI Projects
Some AI Projects
Brain simulation
• Blue Brain Project, HNeT (Holographic Neural Technology), Hierarchical Temporal
Memory
Cognitive architectures
• CALO , SHIAI (Semi Human Instinctive Artificial Intelligence) , Virtual Woman
Games
• Chinook, Deep Blue , FreeHAL, TD-Gammon
Knowledge and reasoning
• Cyc , Eurisko, Open Mind Common Sense, Questsin, SNePS, Watson.
Motion and manipulation
• Cog, Grand Challenge 5
Natural language processing
• AIML, A.L.I.C.E., ELIZA, InfoTame, Jabberwacky, KAR-Talk, PARRY, Proverb, SHRDLU, START, CSAIL,
SYSTRAN, Texai
Planning
• O-Plan.
Ref: http://en.wikipedia.org/wiki/List_of_artificial_intelligence_projects
Points
• Ground. (A rational motive for a belief or action - wordweb)
• Rule. (Theory/technology)
• Ball.
• Bat.
• Umpire.
• Player.
• Powerplay.
Image:
http://blogs.trb.com/news/specials/newsillustrated/blog/2009/08/lauderhill_stadium_lets_play_c.html
HTM Algorithm
HTM Cortical Learning Algorithm
Jeff Hawkins,
November 2010,
“Advances in Modeling Neocortex and its impacts on machine intelligence”
Link: http://tinyurl.com/4reyyzf
Zeta 1: First generation node algorithms
Image: “HOW THE BRAIN MIGHT WORK: A HIERARCHICAL AND
TEMPORAL MODEL FOR LEARNING AND RECOGNITION “, Dileep
George, 2008, Stanford University
HTM Network
Zeta 1: First generation node algorithms
Image: “HOW THE BRAIN MIGHT WORK: A HIERARCHICAL AND TEMPORAL MODEL FOR LEARNING
AND RECOGNITION “, Dileep George, 2008, Stanford University
HTM Cortical Learning Algorithm
Some Terminologies
– Cell States
• 3 output states
– Active from feed-forward input
– Active from lateral input
– Inactive
– Dendrite Segments
• Proximal dendrite segment
• Distal dendrite segments
– Synapses
• Potential Synapses
• Permanence
Reference: Chapter 2: HTM Cortical Learning Algorithms
http://numenta.com/htm-overview/education/HTM_CorticalLearningAlgorithms.pdf
HTM Cortical Learning Algorithm
Each HTM region does 3 things
1. Form a sparse distributed
representation of the input.
2. Form a representation of the
input in the context of
the previous inputs.
3. Form a prediction based on
the current input in the context
of previous inputs.
Reference: Chapter 2: HTM Cortical Learning Algorithms.
http://numenta.com/htm-overview/education/HTM_CorticalLearningAlgorithms.pdf
HTM Cortical Learning Algorithm
Context
Representation of the input in the context of the previous inputs.
Reference: Chapter 2: HTM Cortical Learning Algorithms.
http://numenta.com/htm-overview/education/HTM_CorticalLearningAlgorithms.pdf
The image has 70 columns.
Each column has 4 cells. So it can save 470
Contexts
by graying any combination of its columns’ cells.
িকর্েকট বল ।
বাংলায় বল ।
I have eight oranges.
I ate eggs.
SpatialPoolerTemporalPooler
Region
An HTM Region
Idea Reference: Chapter 2: HTM Cortical Learning Algorithms.
http://numenta.com/htm-overview/education/HTM_CorticalLearningAlgorithms.pdf
Input Sensory Data or Output from Lower Region
Input
Input Sensory Data or Output from Lower Region
Input&HTMRegion
Input Sensory Data or Output from Lower Region
FeedForwardInput
Input Sensory Data or Output from Lower Region
InhibitionRadius
Input Sensory Data or Output from Lower Region
InhibitionRadius
Predictive State No Predictive States
InputtoPredictiveState
Active State Active All Cells in Column
InputtoPredictiveState
InputtoPredictiveState
Points
• Ground. (A rational motive for a belief or action - wordweb)
• Rule. (Theory/technology.)
• Ball. (Problems that fit.)
• Bat.
• Umpire.
• Player.
• Powerplay.
Image source: http://www.gettyimages.com/detail/89127087/Photographers-Choice
Problem Properties
Spatial Hierarchy
Data generated by common
sub-causes are highly
correlated.
In image, adjacent pixels more highly
correlated than distant pixels.
Ref: http://numenta.com/htm-overview/education/ProblemsThatFitHTMs.pdf
Image: http://www.impactlab.net/2007/04/13/building-brainlike-computers/
Temporal Hierarchy
Higher level causes vary more slowly
compared to lower-level causes.
In music:
– Lower level individual notes changes very rapidly.
– Notes are combined into musical phrase.
– Phrases are combined into musical section.
– Sections are combined into a symphony.
Points
• Ground. (A rational motive for a belief or action – wordweb.)
• Rule. (Theory/technology.)
• Ball. (Problems that fit.)
• Bat. (Existing tools.)
• Umpire.
• Player.
• Powerplay.
A display depicting the history of the cricket bat
http://www.south-africa-tours-and-travel.com/cricket-south-africa.html
Numenta Legacy Software
2 Categories
• NuPIC (Numenta Platform for Intelligent Computing)
– Numenta Runtime Engine.
– NuPIC Tools.
– Vision Framework.
• Vision Software
– Vision demo applications
• People tracking demo
• Sample vision networks
– Creating your own vision system
• Vision Toolkit
• Numenta Web Services
Ref: http://numenta.com/legacysoftware.php
Points
• Ground. (A rational motive for a belief or action – wordweb.)
• Rule. (Theory/technology.)
• Ball. (Problems that fit.)
• Bat. (Existing tools.)
• Umpire. (People behind.)
• Player.
• Powerplay.
David Shepherd on dreaded Nelson.
http://www.espncricinfo.com/magazine/content/story/149880.html
Numenta Leadership Team
Subutai Ahmad
VP of Engineering
BS, Computer Science, Cornell
University
PhD, Computer Science, University of
Illinois, Urbana-Champaign.
Donna Dubinsky
Founder,
Chief Executive
Officer,
Board Chair
B.A. Yale University,
History.
M.B.A., Harvard
Business School.
Jeff Hawkins
Founder
Co-founder: Palm and Handspring,
Architect: PalmPilot and Treo
smartphone.
Book: On Intelligence. (2004)
With Dileep George and Donna Dubinsky,
founded Numenta in 2005.
B.S. Electrical Engineering, Cornell
University, 1979.
Elected to the National Academy of
Engineering in 2003.
Dileep George
Founder
Led the development of
the first generation of
algorithms for
Numenta's HTM
technology. 2005 - 2010
Stanford UniversityPh.D in
Electrical Engineering, 2008
Redwood Neuroscience
InstituteResearch Fellow,
2003 - 2005
Numenta Board of Directors
Donna Dubinsky
Founder
Jeff Hawkins
Founder
Ed Colligan
Former President & Chief Executive Officer, Palm, Inc
Mike Farmwald
General Partner, 
Skymoon Ventures
Harry Saal
Chairman of the Technical Committee
USDOJ v. Microsoft Consent Decree
         
Gill Bejerano
Assistant Professor
Developmental Biology and Computer Science
Stanford University
                   
James J. DiCarlo M.D., Ph.D.
Associate Professor of Neuroscience 
Massachussetts Institute of Technology
                      
William T. Freeman
Professor
Electrical Engineering and Computer Science 
Massachussetts Institute of Technology
                      
Andrew Y. Ng
Assistant Professor
Computer Science 
Stanford University
                      
Tomaso A. Poggio
Eugene McDermott Professor, McGovern Institute 
Massachussetts Institute of Technology
Ref: http://numenta.com/about-numenta/people.php
Numenta Technical Advisory Board
Points
• Ground. (A rational motive for a belief or action – wordweb.)
• Rule. (Theory/technology.)
• Ball. (Problems that fit.)
• Bat. (Existing tools.)
• Umpire. (People behind.)
• Player. (Customers)
• Powerplay. Bangladesh Cricket Team on a Victory Lap
Image:
http://www.criclounge.com/news/1637/New-Zealand-is-Bangla-washed.
Some Customers
http://www.vitamindinc.com
http://www.edsa.com/
http://www.forbes.com/
Other development partners are working on
- detecting financial fraud,
- creating new web analytical tools, and
- analyzing images for digital pathology.
To learn more: video from Numenta's 2009 HTM Workshop.
For more info: http://numenta.com/about-numenta/customers.php
EDSA Power Analytics
http://www.edsa.com/
Ref: http://www.edsa.com/pa_articles/self_learning.php
http://www.atl.lmco.com/papers/1597.pdf
Lockheed Martin has been using and modifying HTM technology for several applications 
http://www.atl.lmco.com/papers/1597.pdf
Multimodal Pattern Recognition with Hierarchical Temporal Memory (MPR-HTM)
Points
• Ground. (A rational motive for a belief or action – wordweb.)
• Rule. (Theory/technology.)
• Ball. (Problems that fit.)
• Bat. (Existing tools.)
• Umpire. (People behind.)
• Player. (Customers)
• Powerplay. (Demo)
Image: http://www.cricketupdates.org/what-is-meant-by-powerplaypp-in-cricket.html
Application Demo
vitamind
Site: www.vitamindinc.com
White Paper: http://www.vitamindinc.com/downloads/Vitamin%20D%20white%20paper.pdf
For press review: http://www.vitamindinc.com/press.html
Application Demo
vitamind
Site: www.vitamindinc.com
White Paper: http://www.vitamindinc.com/downloads/Vitamin%20D%20white%20paper.pdf
For press review: http://www.vitamindinc.com/press.html
Vitamind
Outlook
Picasa
Webcam/Network Cam
People
Detected Mail,
With detection image
By macro attached images
from the mails are saved in a directory.
Tools Demo
• NuPIC (Numenta Platform for Intelligent Computing)
• Numenta Vission Software
Vision Framework demo Vision Toolkit demo
Java Demo
Courtesy: teddybot http://numenta.com/phpBB2/viewtopic.php?t=1368
vincentvanrijn
Courtesy: vincentvanrijn http://numenta.com/phpBB2/viewtopic.php?t=1368
Hierarchical Temporal Memory
• Ground. (A rational motive for a belief or action – wordweb.)
• Rule. (Theory/technology.)
• Ball. (Problems that fit.)
• Bat. (Existing tools.)
• Umpire. (People behind.)
• Player. (Customers)
• Powerplay. (Demo)
Let’sPlay
Thanks
www.numenta.com
www.onintelligence.org

Weitere ähnliche Inhalte

Was ist angesagt?

Hierarchical Temporal Memory for Real-time Anomaly Detection
Hierarchical Temporal Memory for Real-time Anomaly DetectionHierarchical Temporal Memory for Real-time Anomaly Detection
Hierarchical Temporal Memory for Real-time Anomaly DetectionIhor Bobak
 
Numenta Brain Theory Discoveries of 2016/2017 by Jeff Hawkins
Numenta Brain Theory Discoveries of 2016/2017 by Jeff HawkinsNumenta Brain Theory Discoveries of 2016/2017 by Jeff Hawkins
Numenta Brain Theory Discoveries of 2016/2017 by Jeff HawkinsNumenta
 
An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)Thomas da Silva Paula
 
Introduction of Deep Learning
Introduction of Deep LearningIntroduction of Deep Learning
Introduction of Deep LearningMyungjin Lee
 
The Biological Path Towards Strong AI Strange Loop 2017, St. Louis
The Biological Path Towards Strong AI Strange Loop 2017, St. LouisThe Biological Path Towards Strong AI Strange Loop 2017, St. Louis
The Biological Path Towards Strong AI Strange Loop 2017, St. LouisNumenta
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learningJörgen Sandig
 
Deep learning frameworks v0.40
Deep learning frameworks v0.40Deep learning frameworks v0.40
Deep learning frameworks v0.40Jessica Willis
 
Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Ha Phuong
 
Deep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image ProcessingDeep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image ProcessingGrigory Sapunov
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerPoo Kuan Hoong
 
Deep learning tutorial 9/2019
Deep learning tutorial 9/2019Deep learning tutorial 9/2019
Deep learning tutorial 9/2019Amr Rashed
 
Artificial Intelligence, Machine Learning and Deep Learning with CNN
Artificial Intelligence, Machine Learning and Deep Learning with CNNArtificial Intelligence, Machine Learning and Deep Learning with CNN
Artificial Intelligence, Machine Learning and Deep Learning with CNNmojammel43
 
Generating Natural-Language Text with Neural Networks
Generating Natural-Language Text with Neural NetworksGenerating Natural-Language Text with Neural Networks
Generating Natural-Language Text with Neural NetworksJonathan Mugan
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual IntroductionLukas Masuch
 
ML DL AI DS BD - An Introduction
ML DL AI DS BD - An IntroductionML DL AI DS BD - An Introduction
ML DL AI DS BD - An IntroductionDony Riyanto
 
Deep Learning Class #0 - You Can Do It
Deep Learning Class #0 - You Can Do ItDeep Learning Class #0 - You Can Do It
Deep Learning Class #0 - You Can Do ItHolberton School
 

Was ist angesagt? (20)

Hierarchical Temporal Memory for Real-time Anomaly Detection
Hierarchical Temporal Memory for Real-time Anomaly DetectionHierarchical Temporal Memory for Real-time Anomaly Detection
Hierarchical Temporal Memory for Real-time Anomaly Detection
 
Numenta Brain Theory Discoveries of 2016/2017 by Jeff Hawkins
Numenta Brain Theory Discoveries of 2016/2017 by Jeff HawkinsNumenta Brain Theory Discoveries of 2016/2017 by Jeff Hawkins
Numenta Brain Theory Discoveries of 2016/2017 by Jeff Hawkins
 
An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)An introduction to Machine Learning (and a little bit of Deep Learning)
An introduction to Machine Learning (and a little bit of Deep Learning)
 
Introduction of Deep Learning
Introduction of Deep LearningIntroduction of Deep Learning
Introduction of Deep Learning
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
The Biological Path Towards Strong AI Strange Loop 2017, St. Louis
The Biological Path Towards Strong AI Strange Loop 2017, St. LouisThe Biological Path Towards Strong AI Strange Loop 2017, St. Louis
The Biological Path Towards Strong AI Strange Loop 2017, St. Louis
 
Tutorial on Deep Learning
Tutorial on Deep LearningTutorial on Deep Learning
Tutorial on Deep Learning
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
 
Deep learning frameworks v0.40
Deep learning frameworks v0.40Deep learning frameworks v0.40
Deep learning frameworks v0.40
 
Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)
 
Deep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image ProcessingDeep Learning Cases: Text and Image Processing
Deep Learning Cases: Text and Image Processing
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
 
Deep learning tutorial 9/2019
Deep learning tutorial 9/2019Deep learning tutorial 9/2019
Deep learning tutorial 9/2019
 
Deep Learning
Deep LearningDeep Learning
Deep Learning
 
Artificial Intelligence, Machine Learning and Deep Learning with CNN
Artificial Intelligence, Machine Learning and Deep Learning with CNNArtificial Intelligence, Machine Learning and Deep Learning with CNN
Artificial Intelligence, Machine Learning and Deep Learning with CNN
 
Generating Natural-Language Text with Neural Networks
Generating Natural-Language Text with Neural NetworksGenerating Natural-Language Text with Neural Networks
Generating Natural-Language Text with Neural Networks
 
Deep learning
Deep learningDeep learning
Deep learning
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
 
ML DL AI DS BD - An Introduction
ML DL AI DS BD - An IntroductionML DL AI DS BD - An Introduction
ML DL AI DS BD - An Introduction
 
Deep Learning Class #0 - You Can Do It
Deep Learning Class #0 - You Can Do ItDeep Learning Class #0 - You Can Do It
Deep Learning Class #0 - You Can Do It
 

Andere mochten auch

Applications of Hierarchical Temporal Memory (HTM)
Applications of Hierarchical Temporal Memory (HTM)Applications of Hierarchical Temporal Memory (HTM)
Applications of Hierarchical Temporal Memory (HTM)Numenta
 
State of NuPIC
State of NuPICState of NuPIC
State of NuPICNumenta
 
Beginner's Guide to NuPIC
Beginner's Guide to NuPICBeginner's Guide to NuPIC
Beginner's Guide to NuPICNumenta
 
Temporal memory in racket
Temporal memory in racketTemporal memory in racket
Temporal memory in racketNumenta
 
Hybrid STM/HTM for Nested Transactions on OpenJDK
Hybrid STM/HTM for Nested Transactions on OpenJDKHybrid STM/HTM for Nested Transactions on OpenJDK
Hybrid STM/HTM for Nested Transactions on OpenJDKAntony Hosking
 
El Mapa de la Conciencia de Hernan Saavedra
El Mapa de la Conciencia de Hernan SaavedraEl Mapa de la Conciencia de Hernan Saavedra
El Mapa de la Conciencia de Hernan SaavedraHernan Saavedra
 
Getting Started with Numenta Technology
Getting Started with Numenta Technology Getting Started with Numenta Technology
Getting Started with Numenta Technology Numenta
 
Predictive Analytics with Numenta Machine Intelligence
Predictive Analytics with Numenta Machine IntelligencePredictive Analytics with Numenta Machine Intelligence
Predictive Analytics with Numenta Machine IntelligenceNumenta
 
Perovskite Solar Cells - an Introduction
Perovskite Solar Cells - an IntroductionPerovskite Solar Cells - an Introduction
Perovskite Solar Cells - an IntroductionDawn John Mullassery
 
Fabrication of perovskite solar cell
Fabrication of perovskite solar cellFabrication of perovskite solar cell
Fabrication of perovskite solar cellakash arya
 
OLED technology Seminar Ppt
OLED technology Seminar PptOLED technology Seminar Ppt
OLED technology Seminar PptAshly Liza
 

Andere mochten auch (14)

Applications of Hierarchical Temporal Memory (HTM)
Applications of Hierarchical Temporal Memory (HTM)Applications of Hierarchical Temporal Memory (HTM)
Applications of Hierarchical Temporal Memory (HTM)
 
State of NuPIC
State of NuPICState of NuPIC
State of NuPIC
 
Beginner's Guide to NuPIC
Beginner's Guide to NuPICBeginner's Guide to NuPIC
Beginner's Guide to NuPIC
 
Temporal memory in racket
Temporal memory in racketTemporal memory in racket
Temporal memory in racket
 
Hybrid STM/HTM for Nested Transactions on OpenJDK
Hybrid STM/HTM for Nested Transactions on OpenJDKHybrid STM/HTM for Nested Transactions on OpenJDK
Hybrid STM/HTM for Nested Transactions on OpenJDK
 
Hybrid Swtiching dyk04
Hybrid Swtiching dyk04Hybrid Swtiching dyk04
Hybrid Swtiching dyk04
 
MRS poster (5)
MRS poster (5)MRS poster (5)
MRS poster (5)
 
El Mapa de la Conciencia de Hernan Saavedra
El Mapa de la Conciencia de Hernan SaavedraEl Mapa de la Conciencia de Hernan Saavedra
El Mapa de la Conciencia de Hernan Saavedra
 
Getting Started with Numenta Technology
Getting Started with Numenta Technology Getting Started with Numenta Technology
Getting Started with Numenta Technology
 
Predictive Analytics with Numenta Machine Intelligence
Predictive Analytics with Numenta Machine IntelligencePredictive Analytics with Numenta Machine Intelligence
Predictive Analytics with Numenta Machine Intelligence
 
Perovskite Solar Cells - an Introduction
Perovskite Solar Cells - an IntroductionPerovskite Solar Cells - an Introduction
Perovskite Solar Cells - an Introduction
 
Fabrication of perovskite solar cell
Fabrication of perovskite solar cellFabrication of perovskite solar cell
Fabrication of perovskite solar cell
 
OLED technology Seminar Ppt
OLED technology Seminar PptOLED technology Seminar Ppt
OLED technology Seminar Ppt
 
oled ppt
oled pptoled ppt
oled ppt
 

Ähnlich wie HTM Theory

ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMS
ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMSANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMS
ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMSIAEME Publication
 
Interpretable Machine Learning
Interpretable Machine LearningInterpretable Machine Learning
Interpretable Machine LearningSri Ambati
 
Using construction grammar in conversational systems
Using construction grammar in conversational systemsUsing construction grammar in conversational systems
Using construction grammar in conversational systemsCJ Jenkins
 
Applied Artificial Intelligence Unit 1 Semester 3 MSc IT Part 2 Mumbai Univer...
Applied Artificial Intelligence Unit 1 Semester 3 MSc IT Part 2 Mumbai Univer...Applied Artificial Intelligence Unit 1 Semester 3 MSc IT Part 2 Mumbai Univer...
Applied Artificial Intelligence Unit 1 Semester 3 MSc IT Part 2 Mumbai Univer...Madhav Mishra
 
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018Sri Ambati
 
Numenta ACM Data Min - PowerPoint Presentation
Numenta ACM Data Min - PowerPoint PresentationNumenta ACM Data Min - PowerPoint Presentation
Numenta ACM Data Min - PowerPoint Presentationbutest
 
Tsinghua invited talk_zhou_xing_v2r0
Tsinghua invited talk_zhou_xing_v2r0Tsinghua invited talk_zhou_xing_v2r0
Tsinghua invited talk_zhou_xing_v2r0Joe Xing
 
Topic Pages. From articles to answers.
Topic Pages. From articles to answers.Topic Pages. From articles to answers.
Topic Pages. From articles to answers.Deep Kayal
 
Experiences in building an ontology driven image database for ...
Experiences in building an ontology driven image database for ...Experiences in building an ontology driven image database for ...
Experiences in building an ontology driven image database for ...Carla Lima
 
How Does Generative AI Actually Work? (a quick semi-technical introduction to...
How Does Generative AI Actually Work? (a quick semi-technical introduction to...How Does Generative AI Actually Work? (a quick semi-technical introduction to...
How Does Generative AI Actually Work? (a quick semi-technical introduction to...ssuser4edc93
 
Brain metaphor
Brain metaphorBrain metaphor
Brain metaphoraly_ayk
 
Computer Aided Development of Fuzzy, Neural and Neuro-Fuzzy Systems
Computer Aided Development of Fuzzy, Neural and Neuro-Fuzzy SystemsComputer Aided Development of Fuzzy, Neural and Neuro-Fuzzy Systems
Computer Aided Development of Fuzzy, Neural and Neuro-Fuzzy SystemsIJEACS
 
INTERACTIVITY and EM..
INTERACTIVITY and EM..INTERACTIVITY and EM..
INTERACTIVITY and EM..butest
 
INTERACTIVITY and EM..
INTERACTIVITY and EM..INTERACTIVITY and EM..
INTERACTIVITY and EM..butest
 
Soft Computing
Soft ComputingSoft Computing
Soft ComputingMANISH T I
 
Cognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - Lieto
Cognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - LietoCognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - Lieto
Cognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - LietoAntonio Lieto
 

Ähnlich wie HTM Theory (20)

ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMS
ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMSANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMS
ANALYSIS ON MACHINE CELL RECOGNITION AND DETACHING FROM NEURAL SYSTEMS
 
Interpretable Machine Learning
Interpretable Machine LearningInterpretable Machine Learning
Interpretable Machine Learning
 
Using construction grammar in conversational systems
Using construction grammar in conversational systemsUsing construction grammar in conversational systems
Using construction grammar in conversational systems
 
Applied Artificial Intelligence Unit 1 Semester 3 MSc IT Part 2 Mumbai Univer...
Applied Artificial Intelligence Unit 1 Semester 3 MSc IT Part 2 Mumbai Univer...Applied Artificial Intelligence Unit 1 Semester 3 MSc IT Part 2 Mumbai Univer...
Applied Artificial Intelligence Unit 1 Semester 3 MSc IT Part 2 Mumbai Univer...
 
Knowledge Representation in AI.pptx
Knowledge Representation in AI.pptxKnowledge Representation in AI.pptx
Knowledge Representation in AI.pptx
 
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
 
ML.pdf
ML.pdfML.pdf
ML.pdf
 
Lesson 19
Lesson 19Lesson 19
Lesson 19
 
AI Lesson 19
AI Lesson 19AI Lesson 19
AI Lesson 19
 
Numenta ACM Data Min - PowerPoint Presentation
Numenta ACM Data Min - PowerPoint PresentationNumenta ACM Data Min - PowerPoint Presentation
Numenta ACM Data Min - PowerPoint Presentation
 
Tsinghua invited talk_zhou_xing_v2r0
Tsinghua invited talk_zhou_xing_v2r0Tsinghua invited talk_zhou_xing_v2r0
Tsinghua invited talk_zhou_xing_v2r0
 
Topic Pages. From articles to answers.
Topic Pages. From articles to answers.Topic Pages. From articles to answers.
Topic Pages. From articles to answers.
 
Experiences in building an ontology driven image database for ...
Experiences in building an ontology driven image database for ...Experiences in building an ontology driven image database for ...
Experiences in building an ontology driven image database for ...
 
How Does Generative AI Actually Work? (a quick semi-technical introduction to...
How Does Generative AI Actually Work? (a quick semi-technical introduction to...How Does Generative AI Actually Work? (a quick semi-technical introduction to...
How Does Generative AI Actually Work? (a quick semi-technical introduction to...
 
Brain metaphor
Brain metaphorBrain metaphor
Brain metaphor
 
Computer Aided Development of Fuzzy, Neural and Neuro-Fuzzy Systems
Computer Aided Development of Fuzzy, Neural and Neuro-Fuzzy SystemsComputer Aided Development of Fuzzy, Neural and Neuro-Fuzzy Systems
Computer Aided Development of Fuzzy, Neural and Neuro-Fuzzy Systems
 
INTERACTIVITY and EM..
INTERACTIVITY and EM..INTERACTIVITY and EM..
INTERACTIVITY and EM..
 
INTERACTIVITY and EM..
INTERACTIVITY and EM..INTERACTIVITY and EM..
INTERACTIVITY and EM..
 
Soft Computing
Soft ComputingSoft Computing
Soft Computing
 
Cognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - Lieto
Cognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - LietoCognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - Lieto
Cognitive Paradigm in AI - Invited Lecture - Kyiv/Kyev - Lieto
 

Kürzlich hochgeladen

What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxhariprasad279825
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfSeasiaInfotech2
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 

Kürzlich hochgeladen (20)

What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdf
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 

HTM Theory

  • 1. Md. Asfak Mahamud m.asfak@yahoo.com Software Engineer KAZ Software Ltd. Bangladesh Date: Feb 22, 2011 Introduction to HTM
  • 2. Disclaimer This theory/technology is a result from research of several decades. This theory/technology is doing a great job in various practical fields today. Many companies (for more info http://numenta.com/about-numenta/customers.php ) are using it actively. Many (e.g. http://www.atl.lmco.com/papers/1597.pdf) are doing research on its various applications. The speaker has been reading on this technology for a very short time. Any misleading or wrong explanation may occur due to lack of knowledge of the speaker. Every slide on this presentation has been tried to serve with source of reference (if required). For any confusion audiences are requested to visit the reference pages. The speaker hereby is declaring earnest eagerness to change any content of this presentation if it violets any code of conduct of any organization or company or institutions or hurts any individual.
  • 3. Points • Ground. • Rule. • Ball. • Bat. • Umpire. • Player. • Powerplay. This is the first time Bangladesh is one of the organizing countries of ICC World Cup Cricket. To keep a remembrance of on going cricket craze, points are intentionally coined from sports more specifically from Cricket. Image url: http://en.wikipedia.org/wiki/File:2011_Cricket_World_Cup_Logo.svg
  • 4. Points • Ground. (A rational motive for a belief or action - wordweb) • Rule. • Ball. • Bat. • Umpire. • Player. • Powerplay. Image source: http://www.cricket-for-parents.com/cricket-fielding-positions.html
  • 5. At 19 Weeks of Fetus Baby's brain designates specialized areas for – smell, taste, hearing, vision, and touch. Some research suggests that baby may be able to hear sound now. Reference: http://www.babycenter.com/fetal-development-images-19-weeks Image collected and edited from: http://www.babycenter.com/fetal-development-images-19-weeks
  • 6. Aniya’s Learning At her two years of old my niece, Aniya somehow knew about dog (in bengali কুকুর, ‘Kukur’). In her voice it was “Kukun”, কুকুন। She also knew the bengali word বড় ( বড়, ‘Boro’ means Big). In her voice it was ‘Bolo’, বোলো। কুকুন Image: http://jaagruti.org/2010/04/18/the-indian-street-dog/ http://www.impactlab.net/2007/04/13/building-brainlike-computers/ Image: http://www.travelblog.org/Photos/1654785 বোলো কুকুন Supervised Unsupervised
  • 7. Ambiguity Vernon B Mountcastle Formerly University Professor of Neuroscience, Johns Hopkins University, Baltimore, Maryland, USA Image: http://www.ibro.org/Pub/Pub_Main_Display.asp?LC_Docs_ID=3561 An organizing principle for cerebral function: the unit module and the distributed system. In The Mindful Brain. MIT Press, 1978. Info: Video: http://tinyurl.com/4n9ux59 Dileep George, Cognitive Computing, 2007 Paper: http://tinyurl.com/464x4yt Dileep George, Phd Thesis, Stanford University, June, 2008 Same Algorithm for - Audition, - Vision, - Speech and so on. Common Cortical Algorithm No learning algorithm has an inherent superiority over another algorithm for all learning problems. (Wolpert, 1995) No Free Lunch Theorem “An algorithm’s superiority comes from the assumptions that it makes about the problem at hand.”
  • 8. Solution To find Assumptions – General enough to large classes of problems. – Specific enough to make learning possible. Info from: Video: http://tinyurl.com/4n9ux59 Dileep George, Cognitive Computing, 2007 To believe 3 three things • The principles of brain function can be understood. • We can build machines that work on these principles. • Many machine learning, AI and robotics problems can only be solved this way. Jeff Hawkins, November 2010, “Advances in Modeling Neocortex and its impacts on machine intelligence” Link: http://tinyurl.com/4reyyzf World Cortex Physics Statistics Biology Anatomy Structure Physiological Results Psychological Results Info from: video: http://tinyurl.com/4n9ux59 Dileep George, Cognitive Computing, 2007
  • 9. Comparison of neocortex among mouse, monkey and human. The neocortical surfaces are colored blue. Image ref: http://www.nibb.ac.jp/brish/Gallery/cortexE.html Why Neocortex is on focus? Felleman and Van Essens (1991) Model of the cortical hierarchy Image from: http://thebrain2.wikidot.com/tribal-networks • 75% of volume of human brain • All high level vision, audition, motor, language, thought. • Composed of a repetitive element – Complex – Hierarchical Jeff Hawkins, November 2010, “Advances in Modeling Neocortex and its impacts on machine intelligence” Link: http://tinyurl.com/4reyyzf
  • 10. Cells that are vertically aligned in columns all respond to edges with the same orientation. Figure: Response properties of cells in V1, the first cortical region to process information from the retina. Ref: Appendix A: A Comparison between Biological Neurons and HTM cells Appendix B: A Comparison of Layers in the Neocortex and an HTM Region Hierarchical Temporal Memory including HTM Cortical Learning Algorithms http://tinyurl.com/4pr59bv Biological Neuron and Layers in Neocortex ApicalDendrite DistalDendrite ProximalDendrite Axon Layered and Columnar organization of the neocortex becomes evident when neural tissue is stained. Mini-Column: The smallest columnar Structure of the neocortex. Diameter: 30um (Approx ) Contains: 80-100 neurons across all five cellular layers.
  • 11. Inter Region Major Connections Ref: Appendix B: A Comparison of Layers in the Neocortex and an HTM Region Hierarchical Temporal Memory including HTM Cortical Learning Algorithms http://tinyurl.com/4pr59bv Indirect Feed forward Pathway. Direct Feed forward Pathway. Feed back Pathway.
  • 12. Biological Neuron, Simple Artificial Neuron, HTM Cell, HTM Regions Ref: Appendix A: A Comparison between Biological Neurons and HTM cells Hierarchical Temporal Memory including HTM Cortical Learning Algorithms http://tinyurl.com/4pr59bv DistalDendrite Proximal Dendrite Axon Jeff Hawkins, November 2010, “Advances in Modeling Neocortex and its impacts on machine intelligence” Link: http://tinyurl.com/4reyyzf “HOW THE BRAIN MIGHT WORK: A HIERARCHICAL AND TEMPORAL MODEL FOR LEARNING AND RECOGNITION”, Dileep George, June 2008, Stanford University
  • 13. Old Wine in New Glass? NO !!  Hierarchy in space and time.  Slowness of time, combined with the hierarchy, enables efficient learning of intermediate levels of the hierarchy.  Learning of causes by using time continuity and actions.  Models of attention and specific memories.  A probabilistic model specified in terms of relations between a hierarchy of causes.  Belief Propagation in the hierarchy to use temporal and spatial context for inference. Ref: http://numenta.com/htm-overview/education/HTM_Comparison.pdf
  • 14. Old Wine in New Glass? Ref: http://numenta.com/htm-overview/education/HTM_Comparison.pdf General- Purpose Probabilistic Models • Baysian Networks • Energy-based Models (HTMs do not treat them as rivals but tools in its toolbox.) • HHHMs (Hierarchical Hidden Markov Model, a special form of Baysian Network) have hierarchy only in space. HTM has hierarchy in space and time. • Boltzman Machine and Helhmholtz Machine do not include temporal aspects of data in the model and do not make any assumptions about hierarchy. Non- Generative Models • Support Vector Machines (SVMs) • Classic Neural Networks • Slow Feature Analysis (Many properties similar to HTM) • They are typically supervised. HTMs are fundamentally unsupervised. • They are not able to generate data for predictions. HTM can do that. Empirical Neurobiological Model • HMAX Model (Many properties similar to HTMs) • It can not predict forward in time. HTM can do that.
  • 15. Old Wine in New Glass? Ref: http://numenta.com/htm-overview/education/HTM_Comparison.pdf General- Purpose Probabilistic Models • Baysian Networks • Energy-based Models (HTMs do not treat them as rivals but tools in its toolbox.) • HHHMs (Hierarchical Hidden Markov Model, a special form of Baysian Network) have hierarchy only in space. HTM has hierarchy in space and time. • Boltzman Machine and Helhmholtz Machine do not include temporal aspects of data in the model and do not make any assumptions about hierarchy. Non- Generative Models • Support Vector Machines (SVMs) • Classic Neural Networks • Slow Feature Analysis (Many properties similar to HTM) • They are typically supervised. HTMs are fundamentally unsupervised. • They are not able to generate data for predictions. HTM can do that. Empirical Neurobiological Model • HMAX Model (Many properties similar to HTMs) • It can not predict forward in time. HTM can do that.
  • 16. Old Wine in New Glass? Ref: http://numenta.com/htm-overview/education/HTM_Comparison.pdf General- Purpose Probabilistic Models • Baysian Networks • Energy-based Models (HTMs do not treat them as rivals but tools in its toolbox.) • HHHMs (Hierarchical Hidden Markov Model, a special form of Baysian Network) have hierarchy only in space. HTM has hierarchy in space and time. • Boltzman Machine and Helhmholtz Machine do not include temporal aspects of data in the model and do not make any assumptions about hierarchy. Non- Generative Models • Support Vector Machines (SVMs) • Classic Neural Networks • Slow Feature Analysis (Many properties similar to HTM) • They are typically supervised. HTMs are fundamentally unsupervised. • They are not able to generate data for predictions. HTM can do that. Empirical Neurobiological Model • HMAX Model (Many properties similar to HTMs) • It can not predict forward in time. HTM can do that.
  • 17. HTM in the List of AI Projects Some AI Projects Brain simulation • Blue Brain Project, HNeT (Holographic Neural Technology), Hierarchical Temporal Memory Cognitive architectures • CALO , SHIAI (Semi Human Instinctive Artificial Intelligence) , Virtual Woman Games • Chinook, Deep Blue , FreeHAL, TD-Gammon Knowledge and reasoning • Cyc , Eurisko, Open Mind Common Sense, Questsin, SNePS, Watson. Motion and manipulation • Cog, Grand Challenge 5 Natural language processing • AIML, A.L.I.C.E., ELIZA, InfoTame, Jabberwacky, KAR-Talk, PARRY, Proverb, SHRDLU, START, CSAIL, SYSTRAN, Texai Planning • O-Plan. Ref: http://en.wikipedia.org/wiki/List_of_artificial_intelligence_projects
  • 18. Points • Ground. (A rational motive for a belief or action - wordweb) • Rule. (Theory/technology) • Ball. • Bat. • Umpire. • Player. • Powerplay. Image: http://blogs.trb.com/news/specials/newsillustrated/blog/2009/08/lauderhill_stadium_lets_play_c.html
  • 19. HTM Algorithm HTM Cortical Learning Algorithm Jeff Hawkins, November 2010, “Advances in Modeling Neocortex and its impacts on machine intelligence” Link: http://tinyurl.com/4reyyzf Zeta 1: First generation node algorithms Image: “HOW THE BRAIN MIGHT WORK: A HIERARCHICAL AND TEMPORAL MODEL FOR LEARNING AND RECOGNITION “, Dileep George, 2008, Stanford University
  • 20. HTM Network Zeta 1: First generation node algorithms Image: “HOW THE BRAIN MIGHT WORK: A HIERARCHICAL AND TEMPORAL MODEL FOR LEARNING AND RECOGNITION “, Dileep George, 2008, Stanford University
  • 21. HTM Cortical Learning Algorithm Some Terminologies – Cell States • 3 output states – Active from feed-forward input – Active from lateral input – Inactive – Dendrite Segments • Proximal dendrite segment • Distal dendrite segments – Synapses • Potential Synapses • Permanence Reference: Chapter 2: HTM Cortical Learning Algorithms http://numenta.com/htm-overview/education/HTM_CorticalLearningAlgorithms.pdf
  • 22. HTM Cortical Learning Algorithm Each HTM region does 3 things 1. Form a sparse distributed representation of the input. 2. Form a representation of the input in the context of the previous inputs. 3. Form a prediction based on the current input in the context of previous inputs. Reference: Chapter 2: HTM Cortical Learning Algorithms. http://numenta.com/htm-overview/education/HTM_CorticalLearningAlgorithms.pdf
  • 23. HTM Cortical Learning Algorithm Context Representation of the input in the context of the previous inputs. Reference: Chapter 2: HTM Cortical Learning Algorithms. http://numenta.com/htm-overview/education/HTM_CorticalLearningAlgorithms.pdf The image has 70 columns. Each column has 4 cells. So it can save 470 Contexts by graying any combination of its columns’ cells. িকর্েকট বল । বাংলায় বল । I have eight oranges. I ate eggs.
  • 24. SpatialPoolerTemporalPooler Region An HTM Region Idea Reference: Chapter 2: HTM Cortical Learning Algorithms. http://numenta.com/htm-overview/education/HTM_CorticalLearningAlgorithms.pdf
  • 25. Input Sensory Data or Output from Lower Region Input
  • 26. Input Sensory Data or Output from Lower Region Input&HTMRegion
  • 27. Input Sensory Data or Output from Lower Region FeedForwardInput
  • 28. Input Sensory Data or Output from Lower Region InhibitionRadius
  • 29. Input Sensory Data or Output from Lower Region InhibitionRadius
  • 30. Predictive State No Predictive States InputtoPredictiveState
  • 31. Active State Active All Cells in Column InputtoPredictiveState
  • 33. Points • Ground. (A rational motive for a belief or action - wordweb) • Rule. (Theory/technology.) • Ball. (Problems that fit.) • Bat. • Umpire. • Player. • Powerplay. Image source: http://www.gettyimages.com/detail/89127087/Photographers-Choice
  • 34. Problem Properties Spatial Hierarchy Data generated by common sub-causes are highly correlated. In image, adjacent pixels more highly correlated than distant pixels. Ref: http://numenta.com/htm-overview/education/ProblemsThatFitHTMs.pdf Image: http://www.impactlab.net/2007/04/13/building-brainlike-computers/ Temporal Hierarchy Higher level causes vary more slowly compared to lower-level causes. In music: – Lower level individual notes changes very rapidly. – Notes are combined into musical phrase. – Phrases are combined into musical section. – Sections are combined into a symphony.
  • 35. Points • Ground. (A rational motive for a belief or action – wordweb.) • Rule. (Theory/technology.) • Ball. (Problems that fit.) • Bat. (Existing tools.) • Umpire. • Player. • Powerplay. A display depicting the history of the cricket bat http://www.south-africa-tours-and-travel.com/cricket-south-africa.html
  • 36. Numenta Legacy Software 2 Categories • NuPIC (Numenta Platform for Intelligent Computing) – Numenta Runtime Engine. – NuPIC Tools. – Vision Framework. • Vision Software – Vision demo applications • People tracking demo • Sample vision networks – Creating your own vision system • Vision Toolkit • Numenta Web Services Ref: http://numenta.com/legacysoftware.php
  • 37. Points • Ground. (A rational motive for a belief or action – wordweb.) • Rule. (Theory/technology.) • Ball. (Problems that fit.) • Bat. (Existing tools.) • Umpire. (People behind.) • Player. • Powerplay. David Shepherd on dreaded Nelson. http://www.espncricinfo.com/magazine/content/story/149880.html
  • 38. Numenta Leadership Team Subutai Ahmad VP of Engineering BS, Computer Science, Cornell University PhD, Computer Science, University of Illinois, Urbana-Champaign. Donna Dubinsky Founder, Chief Executive Officer, Board Chair B.A. Yale University, History. M.B.A., Harvard Business School. Jeff Hawkins Founder Co-founder: Palm and Handspring, Architect: PalmPilot and Treo smartphone. Book: On Intelligence. (2004) With Dileep George and Donna Dubinsky, founded Numenta in 2005. B.S. Electrical Engineering, Cornell University, 1979. Elected to the National Academy of Engineering in 2003. Dileep George Founder Led the development of the first generation of algorithms for Numenta's HTM technology. 2005 - 2010 Stanford UniversityPh.D in Electrical Engineering, 2008 Redwood Neuroscience InstituteResearch Fellow, 2003 - 2005
  • 39. Numenta Board of Directors Donna Dubinsky Founder Jeff Hawkins Founder Ed Colligan Former President & Chief Executive Officer, Palm, Inc Mike Farmwald General Partner,  Skymoon Ventures Harry Saal Chairman of the Technical Committee USDOJ v. Microsoft Consent Decree
  • 40.           Gill Bejerano Assistant Professor Developmental Biology and Computer Science Stanford University                     James J. DiCarlo M.D., Ph.D. Associate Professor of Neuroscience  Massachussetts Institute of Technology                        William T. Freeman Professor Electrical Engineering and Computer Science  Massachussetts Institute of Technology                        Andrew Y. Ng Assistant Professor Computer Science  Stanford University                        Tomaso A. Poggio Eugene McDermott Professor, McGovern Institute  Massachussetts Institute of Technology Ref: http://numenta.com/about-numenta/people.php Numenta Technical Advisory Board
  • 41. Points • Ground. (A rational motive for a belief or action – wordweb.) • Rule. (Theory/technology.) • Ball. (Problems that fit.) • Bat. (Existing tools.) • Umpire. (People behind.) • Player. (Customers) • Powerplay. Bangladesh Cricket Team on a Victory Lap Image: http://www.criclounge.com/news/1637/New-Zealand-is-Bangla-washed.
  • 42. Some Customers http://www.vitamindinc.com http://www.edsa.com/ http://www.forbes.com/ Other development partners are working on - detecting financial fraud, - creating new web analytical tools, and - analyzing images for digital pathology. To learn more: video from Numenta's 2009 HTM Workshop. For more info: http://numenta.com/about-numenta/customers.php
  • 43. EDSA Power Analytics http://www.edsa.com/ Ref: http://www.edsa.com/pa_articles/self_learning.php
  • 44. http://www.atl.lmco.com/papers/1597.pdf Lockheed Martin has been using and modifying HTM technology for several applications 
  • 45. http://www.atl.lmco.com/papers/1597.pdf Multimodal Pattern Recognition with Hierarchical Temporal Memory (MPR-HTM)
  • 46. Points • Ground. (A rational motive for a belief or action – wordweb.) • Rule. (Theory/technology.) • Ball. (Problems that fit.) • Bat. (Existing tools.) • Umpire. (People behind.) • Player. (Customers) • Powerplay. (Demo) Image: http://www.cricketupdates.org/what-is-meant-by-powerplaypp-in-cricket.html
  • 47. Application Demo vitamind Site: www.vitamindinc.com White Paper: http://www.vitamindinc.com/downloads/Vitamin%20D%20white%20paper.pdf For press review: http://www.vitamindinc.com/press.html
  • 48. Application Demo vitamind Site: www.vitamindinc.com White Paper: http://www.vitamindinc.com/downloads/Vitamin%20D%20white%20paper.pdf For press review: http://www.vitamindinc.com/press.html Vitamind Outlook Picasa Webcam/Network Cam People Detected Mail, With detection image By macro attached images from the mails are saved in a directory.
  • 49. Tools Demo • NuPIC (Numenta Platform for Intelligent Computing) • Numenta Vission Software Vision Framework demo Vision Toolkit demo
  • 50. Java Demo Courtesy: teddybot http://numenta.com/phpBB2/viewtopic.php?t=1368 vincentvanrijn Courtesy: vincentvanrijn http://numenta.com/phpBB2/viewtopic.php?t=1368
  • 51. Hierarchical Temporal Memory • Ground. (A rational motive for a belief or action – wordweb.) • Rule. (Theory/technology.) • Ball. (Problems that fit.) • Bat. (Existing tools.) • Umpire. (People behind.) • Player. (Customers) • Powerplay. (Demo) Let’sPlay