A “Consciousness” Based Architecture for a Functioning Mind

1. A “Consciousness” Based Architecture for a Functioning Mind Stan Franklin and the Conscious Software Research Group Institute for Intelligent Systems University of Memphis

2. 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 The Conscious Software Research Group

3. 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.

4. Examples

5. 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

6. Contexts at work

7. 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.

8. I A D Internet IDA: an Intelligent Distribution Agent Read personnel data Check job requisition list Adhere to Navy policies Choose jobs to offer members Negotiate with members Write orders Telephone Detailer

9. 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

10. IDA’s Architecture Metacognition Database Perception Linear Functional Deliberation Negotiation Write Orders Behavior Net Conceptual & Behavioral Learning “Consciousness” Perception Associative Memory Episodic Memory Emotions

11. Levels of abstraction • High level • behaviors • message type nodes • emotions • metacognitive actions • etc. • Low level • codelets

12. 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

13. Perception via a Slipnet Norfolk nor NRFK norfolk Norfolk . . . San Diego Jacksonville Miami location information request preference acceptance

14. Sparse Distribute Memory — Boolean Space — dim = N (enough to code features) bit vector Job List Outgoing Message Focus Working memory Perception Behavior Net Emotion Deliberation Associative Memory

15. Coalitions and Consciousness • Coalition manager • Spotlight manager • Broadcast mechanism

16. Broadcast Behavior net templates Behavior Net in Action Behavior net Work Space Stands Side lines Playing field

17. Drive to Acknowledge A Behavior Stream Activation from drive Send an acknowledgement Compose an acknowledgment Find an email address Find and move a template From the Sidelines Activation from the environment, external or internal

18. 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

19. 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

20. Associative Memory Working memory Job List Outgoing Message Playing Field Stands “Consciousness” in Action Focus

21. 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

22. 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

23. Modeling Cognition • Situated (embodied) cognition—Varela, Thompson & Roach • Perceptual symbol systems—Barsalou • Memory via actions—Glenberg • Global workspace theory—Baars • Cognitive architecture—Sloman

24. Sloman’s Architecture

25. Web and Email Addresses • Stan Franklin stan.franklin@memphis.edu—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