Conference proceeding
Self-Managing Associative Memory for Dynamic Acquisition of Expertise in High-Level Domains
21ST INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-09), PROCEEDINGS, pp.998-1003
01/01/2009
Abstract
Self-organizing maps can be used to implement an associative memory for an intelligent system that dynamically learns about new high-level domains over time. SOMs are an attractive option for implementing associative memory: they are fast, easily parallelized, and digest a stream of incoming data into a topographically organized collection of models where more frequent classes of data are represented by higher-resolution collections of models. Typically, the distribution of models in an SOM, once developed, remains fairly stable, but developing expertise in a new high-level domain requires altering the allocation of models. We use a mixture of analysis and empirical studies to characterize the behavior of SOMs for high-level associative memory, finding that new high-resolution collections of models develop quickly. High-resolution areas of the SOM decay rapidly unless actively refreshed, but in a large SOM, the ratio between growth rate and decay rate may be high enough to support both fast learning and long-term memory.
Details
- Title: Subtitle
- Self-Managing Associative Memory for Dynamic Acquisition of Expertise in High-Level Domains
- Creators
- Jacob Beal
- Contributors
- C Boutilier (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- 21ST INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-09), PROCEEDINGS, pp.998-1003
- Publisher
- International Joint Conferences on Artificial Intelligence; Menlo Park, Calif
- Number of pages
- 6
- Language
- English
- Date published
- 01/01/2009
- Academic Unit
- Electrical and Computer Engineering
- Record Identifier
- 9984627322502771
Metrics
1 Record Views