Stereotyping users and tasks with associative memories

Qiyang Chen, A. F. Norcio

Research output: Contribution to conferencePaperpeer-review

4 Scopus citations

Abstract

This paper presents a user modeling mechanism which is based on associative memory. In the context of associative user modeling, all task-related attributes or assumptions, termed as concepts, are organized into associative memory which is considered as a universal stereotype toward all potential users. The modeling process extracts the concepts and their weighted connections from the associative memory to form a unique profile that fits a particular user or task. This process is conducted by propagating the activation level throughout the network. We suggest that this approach can be expected to overcome some inherent problems of the conventional stereotyping approaches in terms of providing noise tolerance, pattern completion and learning capabilities. It can also avoid the complexity of truth maintenance in default reasoning which exists in previously known stereotyping systems.

Original languageEnglish
Pages1169-1174
Number of pages6
StatePublished - 1 Dec 1994
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: 27 Jun 199429 Jun 1994

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period27/06/9429/06/94

Fingerprint Dive into the research topics of 'Stereotyping users and tasks with associative memories'. Together they form a unique fingerprint.

Cite this