Slide 1OutlineSlide 3Machine ConsciousnessMachine ConsciousnessMachine ConsciousnessSlide 7Global Workspace TheoryGlobal Workspace TheoryGlobal Workspace TheorySlide 11IDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureSlide 26IDA: A Cognitive Agent ArchitectureLisa SorosOutlineMachine ConsciousnessGlobal Workspace TheoryIDA: A Cognitive Agent ArchitectureMachine ConsciousnessMachine ConsciousnessMay 2001: Swartz Foundation sponsors a workshop at the Banbury Center in Long Island called 'Can A Machine Be Conscious?'Attended by 20 psychologists, computer scientists, philosophers, physicists, neuroscientists, engineers, and indutrialists. After the workshop, all but one attendee agreed that a machine could be conscious.Machine ConsciousnessAssuming a machine could be conscious, how could we make it so?First, we need a model of consciousness in general.Machine Consciousness3 major theories of consciousness:1. Dennett's Multiple Drafts Theory2. Shanon's Theory3. Baar's Global Workspace Theory While each model has its idiosyncrasies, all assume that consciousness is not unitary in nature.Global Workspace TheoryGlobal Workspace TheoryTheorized by Bernard Baars, a former Senior Fellow in Theoretical Neurobiology at The Neurosciences Institute (La Jolla, CA) in 1988Emerged from the cognitive architecture tradition pioneered by Alan Newell and Herbert Simon (who won the Turing Award in 1975 for their contributions to AI and the psychology of human cognition)Newell et al showed the utility of a global workspace in managing complex knowledge sourcesGlobal Workspace TheoryAccording to GWT, The function of consciousness is to broadcast information to separate functional modules throughout the brainThe global workspace is a central processor which contains the contents of consciousnessThe global workspace functions as a sort of cognitive blackboardGlobal Workspace TheoryBaars explains his theory using the metaphor of a theatre of consciousness:Working memory provides the ”stage” of consciousnessExecutive guidance directs the ”spotlight” of attention on the stageThe rest of the theater (small, special purpose, independent processes) is dark and unconsciousIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureDeveloped by Stan Franklin and the 'Conscious' Software Research Group at the University of MemphisFranklin's work on 'conscious' software agents has produced ~60 academic publicationsAfter receiving his Ph.D. from UCLA, he has been on the faculty at UF, the Indian Institute of Technology at Kanpur, Carnegie Mellon, and the University of MemphisIDA: A Cognitive Agent ArchitectureIDA: Intelligent Distribution AgentDesigned to serve as a detailer for the U.S. NavyCommunicates with sailors via natural language e-mails to negotiate new assignments after their tours of dutyMust also adhere to ~90 Navy policies, fulfill job requirements, keep moving costs down, and respond to the wishes of the sailorsIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitectureCodelet – a special purpose, relatvely independent mini-agent typically implemented as a small piece of code running as a separate thread (Hofstadter)Perceptual codelets, attention codelets, information codelets, behavior codelets, language generation codelets...Codelets in IDA correspond with processors in GWTIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent ArchitecturePerceptionConsists mostly of input from e-mailsUses only surface-level NLP (no parsing)Uses a Copycat-like architecture (Hofstadter & Mitchell) with perceptual codelets triggered by both e-mail content and internal knowledgeThis allows IDA to recognize, categorize, and understandIDA: A Cognitive Agent Architecture”A secretary sending out an email announcement of an upcoming seminar on Compact Operators on Banach Spaces can be said to have understood the organizer’s request that she do so even though she has no idea of what a Banach pace is much less what compact operators on them are. In most cases it would likely require person years of diligent effort to impart such knowledge. Nonetheless, the secretary understands the request at a level sufficient for her to get out the announcement. In the same way IDA understands incoming email messages well enough to do all the things she needs to with them.” - FranklinIDA: A Cognitive Agent ArchitectureWorkspaceCorresponds to the Working Memory (or STM) in humansConsists of registers set aside for particular categories of informationPerceptual & internal codelets write to the workspace, while many other codelets are watching the workspace in case they need to react to itInterfaces with LTM; some, but not all, workspace contents are written to associative memoryIDA: A Cognitive Agent ArchitectureAssociative MemorySDM – Sparse Distributed Memory, a content-addressable memoryWriting to the workspace cues activation and retrieval in the associative memoryIDA: A Cognitive Agent ArchitectureIDA: A Cognitive Agent Architecture'Consciousness' mechanismA coalition manager, a broadcast manager, a spotlight controller, and attention codelets (which bring appropriate contents to 'consciousness')Attention codelets watch out for items that might require 'conscious' attentionWhen attention-worthy items are found, the information codelets that describe the item are gathered into a coalition to handle the situationThe coalition then competes for the spotlight of 'consciousness'IDA: A Cognitive Agent ArchitectureExample:An attention codelet recognizes the please-find-job message typeIt gathers information codelets carrying the sailor's name and SSN in addition to the message typeThe attention and information codelets form a coalition and compete for 'consciousness'If successful, the coalition's contents are broadcast to the rest of the systemIDA: A Cognitive Agent ArchitectureBehavior Selection
View Full Document