CS 182 Sections 103 - 104AnnouncementsScheduleQuizSlide 5KARMADBNsDynamic Bayes NetsMetaphor MapsWhere does the domain knowledge come from?DBN for the target domainLet’s try a different domainSlide 13Slide 14How do the source domain f-structs get parameterized?Slide 16SHRUTISlide 18focal clusterSlide 20dynamic binding exampleActive Schemas in SHRUTISlide 23Review: ProbabilityPriors/Unconditional ProbabilityConditional ProbabilityInferenceIndependenceBayes NetsSlide 31Markov BlanketReference: JointsReference: Joint, cont.Slide 35Reference: InferenceSlide 37Slide 38Reference: Inference, cont.Approximation MethodsStochastic SimulationCS 182Sections 103 - 104slides created by Eva Mok ([email protected])modified by jgmApril 13, 2005Announcements•a8 out, due Monday April 19th, 11:59pm•BBS articles are assigned for the final paper:–Arbib, Michael A. (2002). The mirror system, imitation, and the evolution of language. –Hurford, James R. (2003). The neural basis of predicate-argument structure.–Grush, Rick (2004). The emulation theory of representation: motor control, imagery, and perception. •Skim through them and let us know, as part of a8, which article you plan to use.Schedule•Last Week–Inference in Bayes Net–Metaphor understanding using KARMA•This Week–Formal Grammar and Parsing–Construction Grammar, ECG•Next Week–Psychological model of sentence processing–Grammar LearningQuiz1. How are the source and target domains represented in KARMA?2. How does the source domain information enter KARMA? How should it?3. What does SHRUTI buy us?4. How are bindings propagated in a structured connectionist framework?Quiz1. How are the source and target domains represented in KARMA?2. How does the source domain information enter KARMA? How should it?3. What does SHRUTI buy us?4. How are bindings propagated in a structured connectionist framework?KARMA•DBN to represent target domain knowledge•Metaphor maps link target and source domain •X-schema to represent source domain knowledgeDBNs•Explicit causal relations + full joint table  Bayes Nets•Sequence of full joint states over time  HMM•HMM + BN  DBNs•DBNs are a generalization of HMMs which capture sparse causal relationships of full jointDynamic Bayes NetsMetaphor Maps1. map entities and objects between embodied and abstract domains2. invariantly map the aspect of the embodied domain event onto the target domain by setting the evidence for the status variable based on controller state (event structure metaphor)3. project x-schema parameters onto the target domainWhere does the domain knowledge come from?•Both domains are structured by frames•Frames have:–List of roles (participants, frame elements)–Relations between roles–Scenario structureDBN for the target domainT0 T1Economic StateGoalPolicy OutcomeDifficulty[Liberalization, Protectionism] [free trade, protection ][success, failure][present, absent][recession,nogrowth,lowgrowth,higrowth]Let’s try a different domain•I didn’t quite catch what he was saying•His slides are packed with information•He sent the audience a clear message9/11 Commission Public Hearing, Monday, March 31, 2003 When we can get a good flow of information from the streets of our cities across to, whether it is an investigating magistrate in France or an intelligence operative in the Middle East, and begin to assemble that kind of information and analyze it and repackage it and send it back out to users, whether it's a policeman on the beat or a judge in Italy or a Special Forces Team in Afghanistan, then we will be getting close to the kind of capability we need to deal with this kind of problem. That's going to take a couple, a few years.Target domain belief net (T-1)Metaphor Map (conduit metaphor)Ideas are objectsWords are containersSendersare speakersReceiversare addresseessendistalkreceiveishearTarget domain belief net (T) (communication frame)speaker addressee action outcomedegree of understandingSource domain f-structs (transfer)X-Schema representationsender receiver means force ratetransfersend receivepackQuiz1. How are the source and target domains represented in KARMA?2. How does the source domain information enter KARMA? How should it?3. What does SHRUTI buy us?4. How are bindings propagated in a structured connectionist framework?How do the source domain f-structs get parameterized?•In the KARMA system, they are hand-coded.•In general, you need analysis of sentences:–syntax–semanticsSyntax captures:•constraints on word order•constituency (units of words)•grammatical relations (e.g. subject, object)•subcategorization & dependency (e.g. transitive, intransitive, subject-verb agreement)Quiz1. How are the source and target domains represented in KARMA?2. How does the source domain information enter KARMA? How should it?3. What does SHRUTI buy us?4. How are bindings propagated in a structured connectionist framework?SHRUTI•A connectionist model of reflexive processingReflexive reasoningautomatic, extremely fast (~300ms), ubiquitous• computation of coherent explanations and predictions• gradual learning of causal structure• episodic memory• understanding languageReflective reasoningconscious deliberation, slowovert consideration of alternativesexternal props (pencil + paper)• solving logic puzzles• doing cryptarithmetic• planning a vacationSHRUTI•synchronous activity without using global clock•An episode of reflexive processing is a transient propagation of rhythmic activity•An “entity” is a phase in the above rhythmic activity.•Bindings are synchronous firings of role and entity cells•Rules are interconnection patterns mediated by coincidence detector circuits that allow selective propagation of activity•Long-term memories are coincidence and coincidence-failure detector circuits•An affirmative answer / explanation corresponds to reverberatory activity around closed loopsfocal cluster•provides locus of coordination, control and decision making•enforce sequencing and concurrency•initiate information seeking actions•initiate evaluation of conditions•initiate conditional actions•link to other schemas, knowledge structuresQuiz1. How are the source and target domains represented in KARMA?2. How does the source domain information enter KARMA? How should it?3. What does SHRUTI buy us?4. How are bindings propagated in a structured connectionist framework?dynamic binding