KATAMIC sequential associative memory

Author

Nenov, Valeriy ; Read, Walter

Author_Institution

Dept. of Surgery/Neurosurgery, California Univ., Los Angeles, CA, USA

Volume

2

fYear

1993

fDate

25-29 Oct. 1993

Firstpage

1462

Abstract

We present a neural architecture for storing, retrieving and recognizing multiple sets of sequences of patterns. This architecture provides an integrated mechanism for storage and recall. It is based on a novel neuron-like computing element, the prediction, which learns to generate at each time step a prediction of its next input based on its long-term experience. The model was implemented on a CM-2 connection machine and simulations were run to test the model for memory capacity, speed of training and accuracy of retrieval and recognition.

Keywords

content-addressable storage; neural net architecture; CM-2; KATAMIC; connection machine; memory capacity; multiple pattern sequence sets; neural architecture; neuron-like computing element; pattern recognition accuracy; pattern retrieval accuracy; pattern storage; prediction; sequential associative memory; training speed; Associative memory; Computational modeling; Computer architecture; Computer science; Humans; Memory management; Neurosurgery; Predictive models; Surgery; Switches;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on

Print_ISBN

0-7803-1421-2

Type

conf

DOI

10.1109/IJCNN.1993.716821

Filename

716821