1 / 23

Background to the IDA Model

Learn about the IDA model developed by Stan Franklin and the 'Conscious' Software Research Group. This intelligent agent helps sailors with tasks such as personnel data checks, job requisitions, policy enforcement, job offering, negotiation, and more.

lamberton
Download Presentation

Background to the IDA Model

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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Background to the IDA Model Stan Franklin and the ‘Conscious’ Software Research Group Machine Consciousness Workshop, Torino, Fall 2003

  2. I A D Internet IDA: an Intelligent Distribution Agent Dialogue with sailors Read personnel data Check job requisition lists Enforce Navy policies Choose jobs to offer members Negotiate with them about jobs Telephone Detailer Stan Franklin—Machine Consciousness—Torino

  3. Autonomous Agent GW Theory Conceptual Model Computational Model IDA: a ‘conscious’ software agent IDA Stan Franklin—Machine Consciousness—Torino

  4. 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 Stan Franklin—Machine Consciousness—Torino

  5. Contexts at work Stan Franklin—Machine Consciousness—Torino

  6. 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. Stan Franklin—Machine Consciousness—Torino

  7. Modules and Mechanisms • Perception—Copycat Architecture—Hofstadter • Action Selection—Behavior Net—Maes • Episodic Memory—Sparse Distributed Memory—Kanerva • Emotions—Pandemonium Theory—Jackson • Metacognition—Fuzzy Classifier Systems—Holland • Learning—Copycat Architecture, Reinforcement • Constraint Satisfaction—Linear Functional • Language Generation—Pandemonium Theory • Deliberation—Pandemonium Theory • ‘Consciousness’ —Pandemonium Theory Stan Franklin—Machine Consciousness—Torino

  8. IDA’s Architecture Metacognition Database Perception Constraint Satisfaction Deliberation Negotiation Problem Solving Behavior Net Expectation & Automization ‘Consciousness’ Perception Working Memory Episodic Memory Emotions Stan Franklin—Machine Consciousness—Torino

  9. A continuing iteration of a cognitive cycle of activities involving: Perception Working memory Transient episodic memory Long-term declarative memory ‘Consciousness’ Action selection Motor activity Processing in IDA Stan Franklin—Machine Consciousness—Torino

  10. Cognitive Cycle Processing • Hypothesis— Like IDA’s, human cognitive processing is via a continuing sequence of Cognitive Cycles • Duration— Each cognitive cycle takes roughly 200 ms with steps 1 through 5 occupying about 80 ms • Overlapping— Several cycles may have parts running simultaneously in parallel • Seriality— Consciousness maintains serial order and the illusion of continuity • Start— Cycle may start with action selection instead of perception Stan Franklin—Machine Consciousness—Torino

  11. Levels of abstraction • High level • behaviors • message type nodes • emotions • metacognitive actions • etc. • Low level • codelets Stan Franklin—Machine Consciousness—Torino

  12. Codelets • Small pieces of code each performing a simple, specialized task • Many acts as demons, 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 Stan Franklin—Machine Consciousness—Torino

  13. Norfolk nor NRFK norfolk Norfolk . . . San Diego Jacksonville Miami location information request preference acceptance Perception via a Slipnet Stan Franklin—Machine Consciousness—Torino

  14. Coalitions and Consciousness • Coalition manager • Spotlight manager • Broadcast mechanism Stan Franklin—Machine Consciousness—Torino

  15. 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 Stan Franklin—Machine Consciousness—Torino

  16. Broadcast Behavior net templates Behavior Net in Action Behavior net Working Memory Stands Side lines Playing field Stan Franklin—Machine Consciousness—Torino

  17. Associative Memory Working memory Job List Outgoing Message Playing Field Stands ‘Consciousness’ in Action Focus Stan Franklin—Machine Consciousness—Torino

  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 Stan Franklin—Machine Consciousness—Torino

  19. Associative Memory Working memory Detach Date Job List Leave Time Playing Field Detach Date Leave Time Stands Leave Time Detach Date Deliberation in Action Focus Stan Franklin—Machine Consciousness—Torino

  20. Ideomotor Theory William James (circa 1890) ----- Bernard Baars (1988) Voluntary vs non-voluntary action Theory of voluntary action • Proposers—propose a course of action • Objectors—raise objections to such a course of action • Supporters—lend support to such a course of action • Auctioneer—wields the gavel Stan Franklin—Machine Consciousness—Torino

  21. Ideomotor Theory in Action Idea pops to mind (proposer)—no objection (objector)—do it Objection (objector)—don’t do it Objection then support (supporter)—do it Different proposal—no objection—do it Different proposal—original proposal— no objection—do it Last unopposed proposal is acted upon Stan Franklin—Machine Consciousness—Torino

  22. Web and Email Addresses • Stan Franklin • franklin@memphis.edu • www.cs.memphis.edu/~franklin • ‘Conscious’ Software Research Group • www.cs.memphis.edu/~csrg Stan Franklin—Machine Consciousness—Torino

More Related