1 / 18

"Conscious" Software Agents” Can they be (or are they) Sentient?

"Conscious" Software Agents” Can they be (or are they) Sentient?. Stan Franklin and the “Conscious” Software Research Group. Global Workspace Theory. The nervous system is a distributed parallel system with many different specialized processors

byron-gay
Download Presentation

"Conscious" Software Agents” Can they be (or are they) Sentient?

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. "Conscious" Software Agents”Can they be (or are they) Sentient? Stan Franklin and the “Conscious” Software Research Group

  2. Global Workspace Theory • 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 relevant processors needed to cope with novel or problematic situation

  3. Implements Baars’ Global Workspace Theory of Consciousness ‘Conscious’ Agent Multiple drives Conceptualization Memory—beliefs Learning Emotions—attitudes, moods Action selection—intention Cognitive Agent Autonomous Agent Senses — Acts — has own Agenda Structurally Coupled to Environment “Conscious” Software Agent

  4. Why a ‘Conscious’ Agent? • Flesh out global workspace theory with detailed architecture and mechanisms • Hypotheses for cognitive scientists and neuroscientists • Produce flexible, adaptive, more human-like software • Want smart agents? Model them after humans. • Produce a sentient software agent, an “ultimate artifact”?

  5. I A D Internet IDA: an Intelligent Distribution Agent Dialogue with members Read personnel data Check requisition lists Conform to Navy policies Choose options to offer members Write orders Telephone Detailer

  6. 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

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

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

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

  10. IDA’s Temporal Deliberation • Create scenes organized around events • Build scenarios as sequences of scenes • Choose between scenarios, discarding some

  11. Associative Memory Working memory Detach Date Job List Leave Time Playing Field Detach Date Leave Time Stands Leave Time Detach Date “Conscious” Deliberation Focus

  12. Ideomotor Theory William James (circa 1890) ----- Bernard Baars (1988) Voluntary action—”conscious” selection 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 • Timekeeper—operates the clock

  13. 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

  14. Indefinite Oscillation? • Timekeeper’s patience decays—quicker decisions • Proposer’s (objector’s, supporter’s) activation decays— harder to get to “consciousness” • Metacognition may intervene

  15. Adding Self to IDA • Baars’ self • Observing self as overarching context • Self systems as competing context hierarchies • IDA has • Competing goal context hierarchies (not deep) • Competing perceptual contexts • Damasio’s selves • Proto-self—can do • Core self—? • Autobiographical self—will do

  16. Adding Self Consciousness to IDA • Evidence of Self Consciousness • Knowledge of individual history—will do • Self reporting—plan to do • Self concept—Blackmore’s self • memeplex—missing in IDA

  17. 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

More Related