Presentation is loading. Please wait.

Presentation is loading. Please wait.

Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California

Similar presentations


Presentation on theme: "Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California"— Presentation transcript:

1 Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California http://cll.stanford.edu/ Architectures for Adaptive Interpretation

2 As typically defined and utilized, a cognitive architecture: aims to demonstrate generality and flexibility, rather than success on a single application domain; aims to demonstrate generality and flexibility, rather than success on a single application domain; specifies the infrastructure that holds constant over domains; specifies the infrastructure that holds constant over domains; focuses on functional structures and processes, rather than on the knowledge or implementation levels; focuses on functional structures and processes, rather than on the knowledge or implementation levels; commits to representations and organizations of knowledge; commits to representations and organizations of knowledge; comes with a programming language for encoding knowledge and constructing intelligent systems. comes with a programming language for encoding knowledge and constructing intelligent systems. Characteristics of Cognitive Architectures These design principles apply not only to architectures focused on action, but also to ones focused on explanation and understanding.

3 Most previous architectures, like Soar, ACT-R, Prodigy, and 3T were designed for action. As a result: Short-term beliefs focus on goals and plans; Short-term beliefs focus on goals and plans; Long-term knowledge focuses on skills and procedures; Long-term knowledge focuses on skills and procedures; Inference is implemented with one-way production rules. Inference is implemented with one-way production rules. To support flexible understanding and explanation, we need an alternative class of architectures in which: Beliefs focus on inferences made from knowledge and facts; Beliefs focus on inferences made from knowledge and facts; An episodic belief memory replaces short-term memory; An episodic belief memory replaces short-term memory; Knowledge exists to generate accurate and useful inferences; Knowledge exists to generate accurate and useful inferences; Inference involves flexible abduction rather than deduction. Inference involves flexible abduction rather than deduction. Architectures for Action and Interpretation We need architectures of this sort for robust learning by reading.

4 Interpretive Architecture: Structures and Processes Old General Knowledge Learning and Revision FixedParser Inference and Interpretation New General Knowledge New Specific Beliefs Old Specific Beliefs Statements and Questions FixedGenerator Answers and Summaries

5 For each input I, 1. Use the fixed parser to generate new beliefs. 2. Update the old beliefs by incorporating the new beliefs. 3. Use the interpreter to infer additional new beliefs. 4. If not yet done, go to step 3; else go to step 5. 5. Use the learner to add or revise knowledge structures. 6. If not yet done, do to step 5; else go to step 7. 7. Use the fixed generator to produce output. Basic Interpretive Cycle Inference is driven by new facts or questions, but guided by old beliefs and knowledge; learning is driven by new beliefs but biased by old knowledge and beliefs. This leaves open key questions about the eagerness/laziness of inference, the size of input/output units, and the degree to which learning and inference are interleaved.


Download ppt "Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California"

Similar presentations


Ads by Google