1 / 29

Copycat Architecture & IDA’s Perception

Copycat Architecture & IDA’s Perception. By Uma Ramamurthy Cognitive Science Seminar January 29, 2003. Introduction. Analogy-making is a process of high-level perception.

Download Presentation

Copycat Architecture & IDA’s Perception

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. Copycat Architecture & IDA’s Perception By Uma Ramamurthy Cognitive Science Seminar January 29, 2003

  2. Introduction • Analogy-making is a process of high-level perception. • Copycat models analogy-making where conceptual fluidity emerges from complex, subconscious interaction between perception and concepts • Distilling the essence of one situation • Adapting that to fit another situation

  3. Copycat in detail… Makes analogies between situations in an idealized microworld of letter-string analogy problems abc abd ijk ? xyz ?

  4. Copycat’s Task • Use concepts it possesses to build perceptual structures – • Description of objects • Bonds between objects of the same string • Groups of objects in a string • Correspondences between objects in different strings • Represent its understanding of the problem • Formulate a solution to the given problem

  5. Copycat’s task Given: abc abd Solve: ijk ? OR: xyz ?

  6. Copycat’s Architecture • Four main elements: • Slipnet • Workspace • Coderack (with codelets) • Temperature

  7. Copycat’s Architecture (contd.) Slipnet: A B X Y Z Links rightmost successor opposite predecessor leftmost last first Label nodes

  8. Copycat’s Architecture (contd.) Slipnet: • Concepts residing in a network of nodes and links • A concept’s central region is a node • A concept’s associative halo may include any of the nodes linked to the central node • A node is activated when instances of it are perceived by codelets • Activation spreads from a node to nearby nodes as a function of their conceptual proximity

  9. Copycat’s Architecture (contd.) Slipnet: • Rate of activation decay is a function of the node’s conceptual depth • Conceptual depth – a static, pre-assigned number – captures the generality and abstractness of the concept • “opposite” is deeper than “successor” • Length of a link between nodes indicates degree of association  conceptual proximity • shorter the link, greater the degree of association

  10. Copycat’s Architecture (contd.) Slipnet: • Link lengths vary in response to the system’s perception • Label node active  all links labeled by the node shrink, indicating close relationships, hence more slippable • Slippage from one node to to a neighbor is probabilistically made  function of the conceptual proximity between the two nodes

  11. Copycat’s Architecture (contd.) Workspace: • Place where perceptual structures are build heirarchically on top of the given input (3 strings of letters) • Six types of structures - • Descriptions of objects • Bonds between objects in the same string • Groups of objects in the same string • Correspondences between objects in different strings • Rule describing the change from initial to modified string • Translated Rule - how the target string should be modified to get the answer string • Structures have time-varying strength value - a function of several factors including conceptual depth and activation

  12. Copycat’s Architecture (contd.) Coderack: • “A codelet is a piece of code that carries out some small, local task that is part of the process of building a structure” • Any run of the system starts with a standard, initial population of codelets • Codelets wait on the rack to be chosen  the choice is probabilistic • Codelets that build perceptual structures send activation to Slipnet nodes, representing the concepts associated with that structure

  13. Copycat’s Architecture (contd.) Types of Codelets: • Scouting Codelets for all structures • Strength (of a structure) Evaluating Codelets • Building Codelets • Breaking Structure Codelets • Translate Rule Codelets

  14. Copycat’s Architecture (contd.) Temperature: • Measures degree of perceptual organization in the system • Controls degree of randomness used in making decisions • Higher temperature  little information to base decisions (more random) • Lower temperature  greater certainty about basis of decisions • Stopping  more likely at lower temperature • Final temperature  indicator of program’s satisfaction with the answer it created

  15. Copycat System Program run: Until a rule has been built and translated, do: Choose a codelet and remove it from the Coderack; Run the chosen codelet; If N codelets have run, then: Update the Slipnet; Update the Coderack with relevant codelets; Build the answer according to the translated rule

  16. Example Run a b c a b d i j k

  17. Perceptual Structures A B C A B D a b c a b d I J K i j k 100 rightmostletter middleletter rightmostletter leftmostletter middleletter leftmostletter leftmostletter middleletter rightmostletter

  18. Perceptual Structures (contd.) A B C A B D a b c a b d I J K i j k 81 rightmostletter middleletter rightmostletter leftmostletter middleletter leftmostletter leftmostletter middleletter rightmostletter Lmost  Lmost Mid  Mid Rmost  Rmost

  19. Perceptual Structures (contd.) Replace letter-category of rmost letter by successor A B C A B D a b c a b d I J K i j k 48 rightmostletter middleletter rightmostletter leftmostletter middleletter leftmostletter leftmostletter middleletter rightmostletter Lmost  Lmost Mid  Mid Rmost  Rmost

  20. Perceptual Structures (contd.) Replace letter-category of rmost letter by successor A B C A B D a b c a b d I J K i j k 31 rightmostletter middleletter rightmostletter leftmostletter middleletter leftmostletter leftmostletter middleletter rightmostletter Lmost  Lmost Mid  Mid Rmost  Rmost

  21. Perceptual Structures (contd.) Replace letter-category of rmost letter by successor A B C A B D a b c a b d I J K i j k 15 rightmostletter middleletter rightmostletter leftmostletter middleletter leftmostletter leftmostletter middleletter rightmostletter Lmost  Lmost Mid  Mid Rmost  Rmost

  22. Perceptual Structures (contd.) Replace letter-category of rmost letter by successor A B C A B D a b c a b d I J K i j k i j l 12 rightmostletter middleletter rightmostletter leftmostletter middleletter leftmostletter leftmostletter middleletter rightmostletter Lmost  Lmost Mid  Mid Rmost  Rmost Replace letter-category of rmost letter by successor

  23. Copycat’s Shortcomings • No Learning • No new Slipnet nodes can be created • No new Codelets can be generated • Works only in a fixed, predefined domain

  24. IDA’s Perception Module • Slipnet representing concepts such as location, job-types, message-types • Workspace to process incoming email message – feature extraction from the message by Perceptual Codelets to activate Slipnet nodes • Filling up a template in the Workspace with mandatory fields of a message-type • No Temperature

  25. IDA’s Slipnet • Nodes • Links • Features • Message types

  26. Piece of IDA’s Slipnet NRFK norfolk nor Norfolk . . . Jacksonville Norfolk San Diego Miami location information request preference acceptance

  27. IDA’s Perception Module • Output from the Perception Module goes to the Attention Registers of the Focus/Working Memory • “Internal” perception via access to Navy databases and other information stores • Input/Output piece handles incoming and outgoing email messages of IDA

  28. In the computational model… • Fixed, pre-defined set of message-types are “perceived” • Everything “perceived” goes to long-term associative memory • No learning in the current version of IDA

  29. In the Conceptual Model… • Everything perceived will not go to long-term memory • Perceptual Learning occurs through “curiosity” and “fringe consciousness” • A conscious interaction with declarative memory (IDA’s long-term/autobiographical memory) may result in generation of • New Slipnet nodes • Possibly new Perceptual Codelets • Slipnet nodes may decay and “disappear” from the system over time if they remain unused for LONG times • … and much more

More Related