Design of self organizing learning array for intelligent machines
Download
1 / 48

Design of Self-Organizing Learning Array for Intelligent Machines - PowerPoint PPT Presentation


  • 136 Views
  • Uploaded on

Design of Self-Organizing Learning Array for Intelligent Machines. Janusz Starzyk School of Electrical Engineering and Computer Science Heidi Meeting June 3 2005. Motivation: How a new understanding of the brain will lead to the creation of truly intelligent machines

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' Design of Self-Organizing Learning Array for Intelligent Machines' - leah-joyner


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
Design of self organizing learning array for intelligent machines
Design of Self-Organizing Learning Array for Intelligent Machines

Janusz Starzyk

School of Electrical Engineering and Computer Science

Heidi Meeting June 3 2005

Motivation:

How a new understanding of the brain will lead

to the creation of truly intelligent machines

from J. Hawkins “On Intelligence”


Elements of Intelligence Machines

  • Abstract thinking and action planning

  • Capacity to learn and memorize useful things

  • Spatio-temporal memories

  • Ability to talk and communicate

  • Intuition and creativity

  • Consciousness

  • Emotions and understanding others

  • Surviving in complex environment and adaptation

  • Perception

  • Motor skills in relation to sensing and anticipation


Problems of classical ai
Problems of Classical AI Machines

  • Lack of robustness and generalization

  • No real-time processing

  • Central processing of information by a single processor

  • No natural interface to environment

  • No self-organization

  • Need to write software


Intelligent behavior
Intelligent Behavior Machines

  • Emergent from interaction with environment

  • Based on large number of sparsely connected neurons

  • Asynchronous

  • Self-timed

  • Interact with environment through sensory-motor system

  • Value driven

  • Adaptive


Design principles of intelligent systems
Design principles of intelligent systems Machines

from Rolf Pfeifer “Understanding of Intelligence”

Design principles

  • synthetic methodology

  • time perspectives

  • emergence

  • diversity/compliance

  • frame-of-reference

Agent design

complete agent principle

cheap design

ecological balance

redundancy principle

parallel, loosely coupled processes

sensory-motor coordination

value principle


The principle of cheap design
The principle of “cheap design” Machines

  • intelligent agents: “cheap”

    • exploitation of ecological niche

    • economical (but redundant)

    • exploitation of specific physical properties of interaction with real world


Principle of ecological balance
Principle of “ecological balance” Machines

  • balance / task distribution between

    • morphology

    • neuronal processing (nervous system)

    • materials

    • environment

  • balance in complexity

    • given task environment

    • match in complexity of sensory, motor, and neural system


The redundancy principle
The redundancy principle Machines

  • redundancy prerequisite for adaptive behavior

  • partial overlap of functionality in different subsystems

  • sensory systems: different physical processes with “information overlap”


Generation of sensory stimulation through interaction with environment
Generation of sensory stimulation through interaction with environment

  • multiple modalities

  • constraints from morphology and materials

  • generation of correlations through physical process

  • basis for cross-modal associations


The principle of sensory motor coordination
The principle of sensory-motor coordination environment

  • Holk Cruse

    • •no central control

    • •only local neuronal communication

    • •global communication through environment

    • neuronal connections

  • self-structuring of sensory data through interaction with environment

  • physical process —not „computational“

  • prerequisite for learning


The principle of parallel loosely coupled processes
The principle of parallel, loosely coupled processes environment

  • Intelligent behavior emergent from agent-environment interaction

  • Large number of parallel, loosely coupled processes

  • Asynchronous

  • Coordinated through agent’s

    –sensory-motor system

    –neural system

    –interaction with environment


The value principle
The “value principle” environment

  • about motivation

  • evaluation of actions

  • frame-of-reference: explicit and implicit values

  • recent theorizing: information theoretic

  • (organism tries to mainting “flow of information”)


Human Brain environmentat Birth

14 Years Old

6 Years Old

Neuron Structure and Self-Organizing Principles

13



Motor cortex environment

Somatosensory cortex

Sensory associative

cortex

Pars

opercularis

Visual associative

cortex

Broca’s

area

Visual

cortex

Primary

Auditory cortex

Wernicke’s

area

Brain Organization


Minicolumn organization and self organizing learning arrays
Minicolumn Organization and environmentSelf Organizing Learning Arrays

  • V. Mountcastle argues that all regions of the brain perform the same algorithm

  • SOLAR combines many groups of neurons (minicolumns) in a pseudorandom way

  • Each microcolumn has the same structure

  • Thus it performs the same computational algorithm satisfying Mountcastle’s principle

  • VB Mountcastle (2003). Introduction [to a special issue of Cerebral Cortex on columns]. Cerebral Cortex, 13, 2-4.


Cortical Minicolumns environment

“The basic unit of cortical operation is the minicolumn… It contains of the order of 80-100 neurons except in the primate striate cortex, where the number is more than doubled. The minicolumn measures of the order of 40-50 m in transverse diameter, separated from adjacent minicolumns by vertical, cell-sparse zones … The minicolumn is produced by the iterative division of a small number of progenitor cells in the neuroepithelium.” (Mountcastle, p. 2)

Stain of cortex in planum temporale.


Groupping of Minicolumns environment

Groupings of minicolumns seem to form the physiologically observed functional columns. Best known example is orientation columns in V1.

They are significantly bigger than minicolumns, typically around 0.3-0.5 mm and have 4000-8000 neurons

Mountcastle’s summation:

“Cortical columns are formed by the binding together of many minicolumns by common input and short range horizontal connections. … The number of minicolumns per column varies … between 50 and 80. Long range intracortical projections link columns with similar functional properties.” (p. 3)


Sparse connectivity
Sparse Connectivity environment

The brain is sparsely connected.

(Unlike most neural nets.)

A neuron in cortex may have on the order of 100,000 synapses. There are more than 1010 neurons in the brain. Fractional connectivity is very low: 0.001%.

Implications: 

  • Connections are expensive biologically since they take up space, use energy, and are hard to wire up correctly.

  • Therefore, connections are valuable.

  • The pattern of connection is under tight control.

  • Short local connections are cheaper than long ones.

    Our approximation makes extensive use of local connections for computation.


Introducing Self-Organizing Learning Array SOLAR environment

  • SOLAR is a regular array of identical processing cells, connected to programmable routing channels.

  • Each cell in the array has ability to self-organize by adapting its functionality in response to information contained in its input signals.

  • Cells choose their input signals from the adjacent routing channels and send their output signals to the routing channels.

  • Processing cells can be structured to implement minicolumns



Solar routing scheme
SOLAR environmentRouting Scheme


Pcb solar
PCB SOLAR environment

XILINX

VIRTEX XCV 1000


System SOLAR environment


Wiring in solar
Wiring in SOLAR environment

Initial wiring and final wiring selection for credit card

approval problem



Associative SOLAR environment



Defining simple brain

Sensors environment

Actuators

Defining Simple Brain

Reactive

Associations

Sensory

Inputs

Motor

Outputs


Simple brain properties
Simple Brain Properties environment

  • Interacts with environment through sensors and actuators

  • Uses distributed processing in sparsely connected neurons

  • Uses spatio-temporal associative learning

  • Uses feedback for input prediction and screening input information for novelty


Brain structure with value system

Sensors environment

Actuators

Brain Structure with Value System

Value System

Action

Planning

Reinforcement

Signal

Anticipated Response

Sensory

Inputs

Motor

Outputs


Brain structure with value system properties
Brain Structure with Value System Properties environment

  • Interacts with environment through sensors and actuators

  • Uses distributed processing in sparsely connected neurons

  • Uses spatio-temporal associative learning

  • Uses feedback for input prediction and screening input information for novelty

  • Develops an internal value system to evaluate its state in environment using reinforcement learning

  • Plans output actions for each input to maximize the internal state value in relation to environment

  • Uses redundant structures of sparsely connected processing elements


Value system in reinforcement learning control
Value System in Reinforcement Learning Control environment

States

Controller

Environment

Value System

Optimization

Reinforcement Signal


Artificial brain organization

Value System environment

Action

Planning

Sensors

Actuators

Artificial Brain Organization

Understanding

Decision making

Anticipated Response

Reinf.

Signal

Motor

Outputs

Sensory

Inputs


Artificial brain organization1
Artificial Brain Organization environment

  • Learning should be restricted to unexpected situation or reward

  • Anticipated response should have expected value

  • Novelty detection should also apply to the value system

  • Need mechanism to improve and compare the value


Artificial brain organization2

Value System environment

Action

Planning

Sensors

Actuators

Artificial Brain Organization

Understanding

Improvement

Detection

Expectation

Comparison

Inhibition

Novelty

Detection

Anticipated Response

Reinf.

Signal

Motor

Outputs

Sensory

Inputs


Artificial brain organization3
Artificial Brain Organization environment

  • Anticipated response block should learn the response that improves the value

  • A RL optimization mechanism may be used to learn the optimum response for a given value system and sensory input

  • Random perturbation should be applied to the optimum response to explore possible states and learn their the value

  • New situation will result in new value and WTA will chose the winner


Artificial brain organization4
Artificial Brain Organization environment

Positive

Reinforcement

Negative

Reinforcement

Sensory

Inputs

Motor

Outputs


Artificial brain selective processing
Artificial Brain Selective Processing environment

  • Sensory inputs are represented by more and more abstract features in the sensory inputs hierarchy

  • Possible implementation is to use winner takes all or Hebbian circuits to select the best match

  • Random wiring may be used to preselect sensory features

  • Uses feedback for input prediction and screening input information for novelty

  • Uses redundant structures of sparsely connected processing elements


Microcolumn organization
Microcolumn Organization environment

superneuron

WTA

Positive

Reinforcement

Negative

Reinforcement

WTA

WTA

Sensory

Inputs

Motor

Outputs


Superneuron Organization environment

  • Each microcolumn contains a number of superneurons

  • Within each microcolumn, superneurons compete on different levels of signal propagation

  • Superneuron contains a predetermined configuration of

    • Sensory (blue)

    • Motor and (yellow)

    • Reinforcement neurons (positive green and negative red)

  • Superneurons internally organize to perform operations of

    • Input selection and recognition

    • Association of sensory inputs

    • Feedback based anticipation

    • Learning inhibition

    • Associative value learning, and

    • Value based motor activation


Superneuron Organization environment

  • Sensory neurons are primarily responsible for providing information about environment

    • They receive inputs from sensors or other sensory neurons on lower level

    • They interact with motor neurons to represent action and state of environment

    • They provide an input to reinforcement neurons

    • They help to activate motor neurons

  • Motor neurons are primarily responsible for activation of motor functions

    • They are activated by reinforcement neurons with the help from sensory neurons

    • They activate actuators or provide an input to lower level motor neurons

    • They provide an input to sensory neurons

  • Reinforcement neurons are primarily responsible for building the internal value system

    • They receive inputs from reinforcement learning sensors or other reinforcement neurons on lower level

    • They receive inputs from sensory neurons

    • They provide an input to motor neurons

    • They help to activate sensory neurons


S1h environment

S2h

WTA

S2

S3

WTA

WTA

S1

Sensory Neurons Interactions


WTA environment

WTA

WTA

Sensory Neurons Functions

  • Sensory neurons are responsible for

    • Representation of inputs from environment

    • Interactions with motor functions

    • Anticipation of inputs and screening for novelty

    • Selection of useful information

    • Identifying invariances

    • Making spatio-temporal associations


Sensory Neurons Functions environment

Sensory neurons

  • Represent inputs from environment by

    • Responding to activation from lower level (summation)

    • Selecting most likely scenario (WTA)

  • Interact with motor functions by

    • Responding to activation from motor outputs (summation)

  • Anticipate inputs and screen for novelty by

    • Correlation to sensory inputs from higher level

    • Inhibition of outputs to higher level

  • Select useful information by

    • Correlating its outputs with reinforcement neurons

  • Identify invariances by

    • Making spatio-temporal associations betweenneighbor sensory neurons


From apparent mess
From Apparent Mess environment


To clear mind organization
To Clear Mind Organization environment

WTA

WTA

WTA

WTA


ad