Biological Based Networks

Slides:



Advertisements
Similar presentations
Cognitive Systems, ICANN panel, Q1 What is machine intelligence, as beyond pattern matching, classification and prediction. What is machine intelligence,
Advertisements

Chapter 2: Marr’s theory of vision. Cognitive Science  José Luis Bermúdez / Cambridge University Press 2010 Overview Introduce Marr’s distinction between.
Sparse Coding in Sparse Winner networks Janusz A. Starzyk 1, Yinyin Liu 1, David Vogel 2 1 School of Electrical Engineering & Computer Science Ohio University,
A model of Consciousness With neural networks By: Hadiseh Nowparast.
$ recognition & localization of predators & prey $ feature analyzers in the brain $ from recognition to response $ summary PART 2: SENSORY WORLDS #09:
2002/01/21PSCY , Term 2, Copyright Jason Harrison, The Brain from retina to extrastriate cortex.
Attention Controlling how information flows through the brain.
Artificial Intelligence (CS 461D)
Class Discussion Chapter 2 Neural Networks. Top Down vs Bottom Up What are the differences between the approaches to AI in chapter one and chapter two?
A Summary of the Article “Intelligence Without Representation” by Rodney A. Brooks (1987) Presented by Dain Finn.
[1].Edward G. Jones, Microcolumns in the Cerebral Cortex, Proc. of National Academy of Science of United States of America, vol. 97(10), 2000, pp
Hybrid Pipeline Structure for Self-Organizing Learning Array Yinyin Liu 1, Ding Mingwei 2, Janusz A. Starzyk 1, 1 School of Electrical Engineering & Computer.
EE141 1 Broca’s area Pars opercularis Motor cortexSomatosensory cortex Sensory associative cortex Primary Auditory cortex Wernicke’s area Visual associative.
How does the mind process all the information it receives?
Overview and History of Cognitive Science. How do minds work? What would an answer to this question look like? What is a mind? What is intelligence? How.
On Intelligence Jeff Hawkins –Founder, Palm Computing: Palm Pilot –Founder, Handspring: Treo –Founder: Numenta Redwood Neuroscience Institute Redwood.
Summer 2011 Wednesday, 8/3. Biological Approaches to Understanding the Mind Connectionism is not the only approach to understanding the mind that draws.
Rohit Ray ESE 251. What are Artificial Neural Networks? ANN are inspired by models of the biological nervous systems such as the brain Novel structure.
Check if film is connected Load NRM via Birm Load nrmp6 and use guildford config aks2000 training and run naturally 'Digital Neuromodelling Based on the.
Chapter 14: Artificial Intelligence Invitation to Computer Science, C++ Version, Third Edition.
How We’re Going to Solve the AI Problem Pedro Domingos Dept. Computer Science & Eng. University of Washington.
Psychology: memory. Overview An understanding of human memory is critical to an appreciation of how users will store and use relevant information when.
Artificial Neural Nets and AI Connectionism Sub symbolic reasoning.
Introduction to Neural Networks. Neural Networks in the Brain Human brain “computes” in an entirely different way from conventional digital computers.
IE 585 Introduction to Neural Networks. 2 Modeling Continuum Unarticulated Wisdom Articulated Qualitative Models Theoretic (First Principles) Models Empirical.
Ch 81 Sensation & Perception Ch. 8: Perceiving Movement © Takashi Yamauchi (Dept. of Psychology, Texas A&M University) Main topics The functions of motion.
Artificial Intelligence Introductory Lecture Jennifer J. Burg Department of Mathematics and Computer Science.
Artificial Neural Networks An Overview and Analysis.
Advances in Modeling Neocortex and its impact on machine intelligence Jeff Hawkins Numenta Inc. VS265 Neural Computation December 2, 2010 Documentation.
1 Computational Vision CSCI 363, Fall 2012 Lecture 3 Neurons Central Visual Pathways See Reading Assignment on "Assignments page"
Artificial Neural Networks. Applied Problems: Image, Sound, and Pattern recognition Decision making  Knowledge discovery  Context-Dependent Analysis.
Cognition, Brain and Consciousness: An Introduction to Cognitive Neuroscience Edited by Bernard J. Baars and Nicole M. Gage 2007 Academic Press Chapter.
Outline: Biological Metaphor Biological generalization How AI applied this Ramifications for HRI How the resulting AI architecture relates to automation.
Robotica Lecture 3. 2 Robot Control Robot control is the mean by which the sensing and action of a robot are coordinated The infinitely many possible.
A New Theory of Neocortex and Its Implications for Machine Intelligence TTI/Vanguard, All that Data February 9, 2005 Jeff Hawkins Director The Redwood.
CS621: Artificial Intelligence Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture 41,42– Artificial Neural Network, Perceptron, Capacity 2 nd, 4 th Nov,
Neural Networks Steven Le. Overview Introduction Architectures Learning Techniques Advantages Applications.
© NOKIAmind.body.PPT / / PHa page: 1 Conscious Machines and the Mind-Body Problem Dr. Pentti O A Haikonen, Principal Scientist, Cognitive Technology.
Introduction to Neural Networks and Example Applications in HCI Nick Gentile.
Subsumption Architecture and Nouvelle AI Arpit Maheshwari Nihit Gupta Saransh Gupta Swapnil Srivastava.
Cognitive Modular Neural Architecture
Dr.Abeer Mahmoud ARTIFICIAL INTELLIGENCE (CS 461D) Dr. Abeer Mahmoud Computer science Department Princess Nora University Faculty of Computer & Information.
Why Can't A Computer Be More Like A Brain?. Outline Introduction Turning Test HTM ◦ A. Theory ◦ B. Applications & Limits Conclusion.
Laurent Itti: CS564 - Brain Theory and Artificial Intelligence. Saccades 1 1 L. Itti: CS564 - Brain Theory and Artificial Intelligence University of Southern.
Neural Networks Si Wu Dept. of Informatics PEV III 5c7 Spring 2008.
Functions of Distributed Plasticity in a Biologically-Inspired Adaptive Control Algorithm: From Electrophysiology to Robotics University of Edinburgh University.
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
Robot Intelligence Technology Lab. 10. Complex Hardware Morphologies: Walking Machines Presented by In-Won Park
Learning objectives understand the basics of information processing theory understand the basics of ecological psychology (action systems and dynamical.
Information Processing
Outline Of Today’s Discussion
What is cognitive psychology?
Classification of models
Neural Network Architecture Session 2
Fall 2004 Perceptron CS478 - Machine Learning.
Artificial Intelligence (CS 370D)
Chapter 4 Sensory Contributions to Skilled Performance
Dr. Unnikrishnan P.C. Professor, EEE
Review Session 3: Sensation and Perception
Lecture 22. Saccades 2 Reading Assignments: Reprint
Non-Symbolic AI lecture 4
Sensorimotor Learning and the Development of Position Invariance
Central Visual Pathways
Biologically Based Networks
CS 621 Artificial Intelligence Lecture /10/05 Prof
Biologically Based Networks
Reading Assignments: Lecture 16. Saccades 2 The NSL Book
Introduction to Neural Network
Models of the brain hardware
CS621 : Artificial Intelligence
Presentation transcript:

Biological Based Networks

Why? Modeling of brain function Model of very distributed parallel systems Existence proof for AI

Human Brain Neuron Speed - 10-3 seconds per operation Brain weights about 3 pounds and at rest consumes 20% of the bodies oxygen. Estimates place neuron count at 1012 to 1014 Connectivity can be 10,000

What is the capacity of the brain? Estimate the MIPS of a brain Estimate the MIPS needed by a computer to simulate the brain

Structure The cortex is estimated to be 6 layers The brain does recognition type computations is 100-200 milliseconds The brain clearly uses some specialized structures.

Alan Turing’s Idea X1 X2 1

Turing (Cont) B type link

B type link

Biowall

Structure Cortex is 6 layers A mosaic of hexagons Top three are internal Middle in input Bottom two area output A mosaic of hexagons Lots of feedback Can excite surrounding hexs

Language Language develops from a proto language Full language is structured into clauses and phrases Brains don’t do syntax! Parsing is by thematic roles 7 plus or minus 2

Igor Aleksander “Impossible Minds, My neurons, My consciousness” “Seeing is believing: Depictive Neuromodeling of Visual Awareness”

Igor Aleksander WISARD and MAGNUS Visual input by arrays of sensors Neural systems viewed as having a state transition form Iconic States Iconic states is the brain state upon perceiving an object

Input Z drives learning Atrophies in time

Build a simple creature

Magnus

Vision Mechanisms Superior Colliculus – eye movement has direct input from the retina Vision path goes to V1, V2, V3 Extrastriate Cortex is selected areas of Cortex Pathway X is a hypothesis for this work

Neuro-Physical Model Extrastriate Areas Movable retinal projection Superior Colliculus Main Visual Pathway Movement Primary Areas (V1, V2, …) Extrastriate Areas Auditory Triggers Gaze Locking j Pathway X Non-ocular Motor Activity

Hypothesis Feedback loop in the preceding slide is a state machine with learning memory Recall of detail and shape is related to gaze locking signals

Experimental System 24 neural areas 30,000 neurons

Experimental System

Consciousness What is it? Descartes theater of them mind An answer to the wrong question?

Randall Beer “Intelligence as Adaptive Behavior” A simple creature:

Leg Controller P = pacemaker LC – command (shared)

Pacemaker coupling

Studies Produced the same gaits as real insects Speed control by LC also produced realistic gaits Lesion studies show survivability

M Arbib A two level methodology Neurons at the bottom layer Schema – Functional Entities Example Frogs: Snap a small creatures Run from larger ones Behaviors found to happen in different areas

Naïve Schema Eye Small Obj Large Obj + + Jump Snap Movement

Lesioning Studies Eye All Obj Large Obj + + - Jump Snap Movement

William H. Calvin University of Washington in Seattle ‘The Cerebral Code” “Lingua Ex Machina”

Brain Operation as Darwinian Requires a complex pattern Pattern must be copied Variant patterns by chance Pattern and variant compete Competition based on multi faceted environment Most successful patterns survive

Jeff Hawkens “On Intelligence”

Criterion Inclusion of time in the brain Feedback Physical Architecture must be part of the theory

Mountcastle Proposal The algorithm of the cortex is independent of an particular sense or function The brain uses the same mechanism for all!

State Machines The brain used state machine to sequence patterns of firing Short term memory Visual systems

Summary The brain is the prototype for intelligence Brain structure and brain function are being studied Can a symbol system compete with the brain? How does symbolic behavior arise from the neural level of the brain?