Transcript Artificial Brain Organization

Motor cortex
Somatosensory cortex
Sensory associative
cortex
Pars
opercularis
Visual associative
cortex
Broca’s
area
Visual
cortex
Primary
Auditory cortex
Wernicke’s
area
Artificial Brain Organization
1
EE141
Janusz Starzyk, Ohio University
Elements of Intelligence










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
2
EE141
Problems of Classical AI
 Lack
of robustness and generalization
 No real-time processing
 Central processing of information by a
single processor
 No natural interface to environment
3
EE141
Intelligent Behavior
Emergent from interaction with environment
 Based on large number of sparsely connected
neurons
 Asynchronous
 Interact with environment through sensorymotor system
 Value driven
 Adaptive

4
EE141
Simple Brain Organization
Reactive
Associations
Sensory
Inputs
Sensors
Motor
Outputs
Actuators
5
EE141
Simple Brain Properties
 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
6
EE141
Brain Structure with Value System
Value System
Reinforcement
Signal
Action
Planning
Anticipated Response
Sensory
Inputs
Sensors
Motor
Outputs
Actuators
7
EE141
Brain Structure with Value System Properties







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
8
EE141
Value System in Reinforcement
Learning Control
States
Environment
Controller
Value System
Optimization
Reinforcement Signal
9
EE141
Artificial Brain Organization
Value System
Understanding
Decision making
Action
Planning
Anticipated Response
Reinf.
Signal
Sensors
EE141
Sensory
Inputs
Motor
Outputs
Actuators
10
Artificial Brain Organization
 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
11
EE141
Artificial Brain Organization
Value System
Understanding
Action
Planning
Expectation
Improvement
Detection
Comparison
Inhibition
Novelty
Detection
Anticipated Response
Reinf.
Signal
Sensors
EE141
Sensory
Inputs
Motor
Outputs
Actuators
12
Artificial Brain Organization





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 of the optimum should be used
to the optimum response in case the value system
changed
New situation will result in new value and WTA will
chose the winner
Problem is how to do
13
EE141
Artificial Brain Organization
14
EE141
Artificial Brain Organization
Positive
Reinforcement
Sensory
Inputs
EE141
Negative
Reinforcement
Motor
Outputs
15
Artificial Brain Selective Processing
Sensory inputs is 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

16
EE141
Artificial Brain Organization
WTA
WTA
WTA
WTA
17
EE141
Microcolumn Organization
V. Mountcastle argues that all regions of the
brain perform the same algorithm
 SOLAR combines many groups of neurons
(microcolumns) in a pseudorandom way
 Each microcolumn has the same structure
 Thus it performs the same computational
algorithm satisfying Mountcastle’s principle


Mindful Brain Cortical Organization and the Group-Selective
Theory of Higher Brain Function G. M. Edelman and V. B.
Mountcastle MIT Press, March 1982
18
EE141
Microcolumn Organization
superneuron
WTA
Positive
Reinforcement
Negative
Reinforcement
WTA
Sensory
Inputs
WTA
Motor
Outputs
19
EE141
Superneuron Organization



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
20
EE141
Superneuron Organization

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
21
EE141
Sensory Neurons Interactions
WTA
WTA
WTA
22
EE141
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
WTA
WTA
EE141
23
WTA
Sensory Neurons Functions
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 between neighbor
sensory neurons
24
EE141
25
EE141