CS 182Sections 103 - 104slides derived from those ofEva Mok and Joe MakinMarch 21, 2007The Last StretchCognition and LanguageComputationS tructured ConnectionismComputational NeurobiologyBiologyMidtermQuizFinalsNeural DevelopmentTriangle NodesNeural Net & LearningSpatial RelationMotor ControlMetaphorSHRUTIGrammarabstractionRegier ModelBailey ModelNarayanan ModelChang ModelVisual SystemPsycholinguistics ExperimentsQuestions●What is Constrained Best Fit?●How does Bailey use multiple levels of representation to learn different senses of verbs?●What is Minimum Description Length?●How do we use Minimum Description Length to merge a grammar?●What does the prefix affix tree look like for the following sentences:●eat them here or there●eat them anywhere●What does the affix tree look like after the best prefix merge?Questions●What is Constrained Best Fit?●How does Bailey use multiple levels of representation to learn different senses of verbs?●What is Minimum Description Length?●How do we use Minimum Description Length to merge a grammar?●What does the prefix affix tree look like for the following sentences:●eat them here or there●eat them anywhere●What does the affix tree look like after the best prefix merge?Constrained Best Fit•Physical example?•Chemical example?• Biological example?Questions●What is Constrained Best Fit?●How does Bailey use multiple levels of representation to learn different senses of verbs?●What is Minimum Description Length?●How do we use Minimum Description Length to merge a grammar?●What does the prefix affix tree look like for the following sentences:●eat them here or there●eat them anywhere●What does the affix tree look like after the best prefix merge?Bailey’s VerbLearn Model• 3 Levels of representation1. cognitive: words, concepts2. computational: f-structs, x-schemas3. connectionist: structured models, learning rules• Input: labeled hand motions (f-structs)• learning: 1. the correct number of senses for each verb2. the relevant features in each sense, and3. the probability distributions on each included feature•execution: perform a hand motion based on a label6palmextendslideaccelpostureelbow jntschema8palmextendslideaccelpostureelbow jntschema[6]palm 0.9extend 0.9slide 0.9accelpostureelbow jntschemadata #1data #2data #3data #4[2]index 0.9fixed 0.9depress 0.9accelpostureelbow jntschema[6 - 8]palm 0.9extend 0.9slide 0.9accelpostureelbow jntschemapalm 0.7grasp 0.3extend 0.9slide 0.9postureelbow jntschema2indexfixeddepressaccelpostureelbow jntschema2graspextendslideaccelpostureelbow jntschemaLimitations of Bailey’s modelan instance of recruitment learning (1-shot)embodied (motor control schemas)learns words and carries out actionthe label contains just the verbassumes that the labels are mostly correctno grammarQuestions●What is Constrained Best Fit?●How does Bailey use multiple levels of representation to learn different senses of verbs?●What is Minimum Description Length?●How do we use Minimum Description Length to merge a grammar?●What does the prefix affix tree look like for the following sentences:●eat them here or there●eat them anywhere●What does the affix tree look like after the best prefix merge?Minimum Description Length•Occam's Razor•Constrain set of hypotheses– Like “prior distribution” over hypotheses– from Tom Griffiths's lecture– prior distribution is more flexibleQuestions●What is Constrained Best Fit?●How does Bailey use multiple levels of representation to learn different senses of verbs?●What is Minimum Description Length?●How do we use Minimum Description Length to merge a grammar?●What does the prefix affix tree look like for the following sentences:●eat them here or there●eat them anywhere●What does the affix tree look like after the best prefix merge?Grammar merging•How can we measure description length?– complicated rules are bad– lots of rules are bad• measure “derivation length”– alpha * size(rules) + derivationCost(rules, sentences)•How can we merge rules?– extract common prefix–extract common suffixQuestions●What is Constrained Best Fit?●How does Bailey use multiple levels of representation to learn different senses of verbs?●What is Minimum Description Length?●How do we use Minimum Description Length to merge a grammar?●What does the prefix affix tree look like for the following sentences:●eat them here or there●eat them anywhere●What does the affix tree look like after the best prefix merge?Affix Trees•Data structures that help you figure out what merges are possible• Each node in the tree represents a symbol, either terminal or non-terminal (we call that the “affix” in the code)• Prefix Tree•Suffix TreePrefix Treer1: S → eat them here or therer2: S → eat them anywhereeatthemhereortherer1r1r1r1r1r2anywherer2r2Sr1 r2Prefix Merger3: S → eat them X1r4: X1 → here or therer5: X1 → anywhereeatthemr3r3Sr3hereortherer4r4r4anywherer5X1X1r3r4 r5Have a good Spring
View Full Document