A novel associative memory for high level control functions

Author

Tsai, Wei K. ; Parlos, Alexander ; Fernandez, Benito

Author_Institution

Dept. of Electr. & Comput. Eng., California Univ., Irvine, CA, USA

fYear

1990

fDate

5-7 Dec 1990

Firstpage

2374

Abstract

A novel associative memory (AM) knowledge base for real-time diagnostics and high-level control functions for complex large-scale dynamic systems is presented. The proposed AM architecture is called ASDM as it is an adaptive architecture based on the sparse distributed memory (SDM) first introduced by Kanerva (1988). ASDM is proposed to overcome many limitations of SDM, while keeping most of the advantages of the original SDM. The new model is adaptive since the memory cells are renamed according to a learning/storing process. The analysis of the best match problem can be carried out in a deterministic setting. Also introduced is the concept of time-varying intensity of memory, and generalized metrics are used for determining distance between two data objects. One major application of this ASDM is that of a neural expert system. With the ASDM, the machine can `learn´ rules on top of the knowledge acquired from human experts

Keywords

computerised control; content-addressable storage; knowledge based systems; large-scale systems; learning systems; neural nets; adaptive architecture; associative memory; knowledge base; large-scale dynamic systems; learning systems; learning/storing process; neural expert system; neural nets; sparse distributed memory; Artificial neural networks; Associative memory; Computer architecture; Control systems; Humans; Large-scale systems; Level control; Power engineering and energy; Real time systems; Variable speed drives;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 1990., Proceedings of the 29th IEEE Conference on

Conference_Location

Honolulu, HI

Type

conf

DOI

10.1109/CDC.1990.204052

Filename

204052