Functioning Mind
Stan Franklin
A “Consciousness” Based Architecture for a Functioning Mind
Stan Franklinand the
Conscious Software Research GroupInstitute for Intelligent Systems
University of Memphis
Functioning Mind
Stan Franklin
The Conscious Software Research The Conscious Software Research GroupGroup
• Stan Franklin• Art Graesser• Sri Satish Ambati• Ashraf Anwar• Myles Bogner* • Arpad Kelemen• Ravikumar Kondadadi• Lee McCauley• Irina Makkaveeva
• Aregahegn Negatu• Uma Ramamurthy• Alexei Stoliartchouk• Zhouhua Zhang• Scott Dodson* • Gurumoorthy Nagasubramanian*• Brent Olde* • Hongjun Song* • Yun Wan*
* former member off to better things
Functioning Mind
Stan Franklin
Autonomous Agent
An autonomous agent is a system
• situated within and a part of an environment
• that senses that environment
• and acts on it,
• over time,
• in pursuit of its own agenda
• so as to effect what it senses in the future.
Functioning Mind
Stan Franklin
Examples
Functioning Mind
Stan Franklin
Global Workspace Theory
• A psychological theory of consciousness
• The nervous system is a distributed parallel system with many different specialized processors
• Global workspace contains a coalition of processors
• Broadcasts globally to all other processors
• Recruit other processors needed for any degree of novel or problematic situation
• Explains limited capacity and seriality
Functioning Mind
Stan Franklin
Contexts at work
Functioning Mind
Stan Franklin
Why a ‘Conscious’ Agent?
• Flesh out the theory with detailed architecture and mechanisms
• Hypotheses for cognitive scientists and neuroscientists
• Produce flexible, adaptive, human-like software
• Want smart agents? Model them after humans.
Functioning Mind
Stan Franklin
IDA: an Intelligent Distribution Agent
Detailer
Telephone
Read personnel dataCheck job requisition listAdhere to Navy policiesChoose jobs to offer membersNegotiate with members Write orders Internet
IDA
Functioning Mind
Stan Franklin
Modules and Mechanisms• Perception—Copycat Architecture—Hofstadter• Action Selection—Behavior Net—Maes• Associative Memory—Sparse Distributed Memory—Kanerva• Episodic Memory—Case-based Memory• Emotions—Pandemonium Theory—Jackson• Metacognition—Fuzzy Classifier Systems—Holland, Zadeh• Learning—Copycat Architecture, Case-based Reasoning• Constraint Satisfaction—Linear Functional• Language Generation—Pandemonium Theory• Deliberation—Pandemonium Theory• “Consciousness” —Pandemonium Theory
Functioning Mind
Stan Franklin
IDA’s Architecture
“Consciousness”Perception
Metacognition
AssociativeMemory
EpisodicMemory
Behavior Net
Emotions
DatabasePerception
LinearFunctional Deliberation Negotiation Write
Orders
Conceptual& Behavioral
Learning
Functioning Mind
Stan Franklin
Levels of abstraction
• High level– behaviors– message type nodes– emotions– metacognitive actions– etc.
• Low level– codelets
Functioning Mind
Stan Franklin
Codelets
• Small pieces of code each performing a simple, specialized task• Acts as a demon, always watching for a chance to act• Most subserve some high level entity, e.g.
– behavior– slipnet node– metacognitive action
• Some codelets work on their own, e.g.– watching for incoming mail– checking for time and place conflicts
• Codelets do almost all the work• IDA is a multi-agent system
Functioning Mind
Stan Franklin
Perception via a Slipnet
preference acceptance information request
location
San Diego Miami Norfolk Jacksonville. . .
Norfolk norfolk nor NRFK
Functioning Mind
Stan Franklin
Associative Memory
Working memory
Focus
Sparse Distribute Memory — Boolean Space — dim = N (enough to code features) bit vector
Perception Behavior Net Emotion Deliberation
JobList
OutgoingMessage
Functioning Mind
Stan Franklin
Coalitions and Consciousness
• Coalition manager
• Spotlight manager
• Broadcast mechanism
Functioning Mind
Stan Franklin
Behavior Net in Action
Behavior net templates
Behavior net
Side lines
Playing field
Stands
WorkSpace
Broadcast
Functioning Mind
Stan Franklin
A Behavior Stream
Find and movea template
Compose an acknowledgment
Find an emailaddress
Drive to Acknowledge
From the Sidelines
Activation from drive
Activation from the environment, external or internal
Send an acknowledgement
Functioning Mind
Stan Franklin
Deliberation
• Faced with a goal or problem • Imagine possible plans or solutions
– Scenarios– Routes – Internal virtual reality—Dawkins
• Evaluate them– Using reason– Using emotions
• Choose among them
Functioning Mind
Stan Franklin
IDA’s Deliberation
• Create scenes– May require objects, actors, concepts, relations, frames– Organized around events
• Build scenarios as sequences of scenes
• Choose between scenarios, discarding some
Using Barsalou’s perceptual symbol systems as a guide
Functioning Mind
Stan Franklin
“Consciousness” in Action
Associative Memory
Working memoryFocus
PlayingField
Stands
OutgoingMessage
JobList
Functioning Mind
Stan Franklin
Metacognition
• Thinking about thinking
• What Sloman calls meta-management
• Influences action selection strategies
– More or less opportunistic, thoughtful or goal-oriented
• Influences resource allocation
• Fuzzy classifier system
Functioning Mind
Stan Franklin
Learning
• Associative learning via pandemonium theory
• Associative learning via sparse distributed memory
• Perceptual learning via case-based reasoning
• Behavioral learning via case-based reasoning
• Metacognitive learning via classifiers
Functioning Mind
Stan Franklin
Modeling Cognition
• Situated (embodied) cognition—Varela, Thompson & Roach
• Perceptual symbol systems—Barsalou
• Memory via actions—Glenberg
• Global workspace theory—Baars
• Cognitive architecture—Sloman
Functioning Mind
Stan Franklin
Sloman’s Architecture
Functioning Mind
Stan Franklin
Web and Email Addresses
• Stan Franklin [email protected]—www.msci.memphis.edu/~franklin
• “Conscious” Software Research Group www.msci.memphis.edu/~csrg
• CMattie Project—www.msci.memphis.edu/~cmattie
• IDA Project—www.msci.memphis.edu/~ida
Top Related