ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Some experiments on human memory and a new neural model

Biswas, NN and Bhattacharyya, Swapan K (1993) Some experiments on human memory and a new neural model. In: International Journal of Systems Science, 24 (11). pp. 1987-1995.

Full text not available from this repository. (Request a copy)
Official URL: http://www.informaworld.com/smpp/content~db=all~co...

Abstract

An associative memory with parallel architecture is presented. The neurons are modelled by perceptrons having only binary, rather than continuous valued input. To store m elements each having n features, m neurons each with n connections are needed. The n features are coded as an n-bit binary vector. The weights of the n connections that store the n features of an element has only two values -1 and 1 corresponding to the absence or presence of a feature. This makes the learning very simple and straightforward. For an input corrupted by binary noise, the associative memory indicates the element that is closest (in terms of Hamming distance) to the noisy input. In the case where the noisy input is equidistant from two or more stored vectors, the associative memory indicates two or more elements simultaneously. From some simple experiments performed on the human memory and also on the associative memory, it can be concluded that the associative memory presented in this paper is in some respect more akin to a human memory than a Hopfield model.

Item Type: Journal Article
Publication: International Journal of Systems Science
Publisher: Taylor and Francis Group
Additional Information: Copyright of this article belongs to Taylor and Francis Group.
Department/Centre: Division of Electrical Sciences > Electrical Communication Engineering
Division of Interdisciplinary Sciences > Supercomputer Education & Research Centre
Date Deposited: 02 Mar 2011 06:25
Last Modified: 27 Feb 2019 08:58
URI: http://eprints.iisc.ac.in/id/eprint/35748

Actions (login required)

View Item View Item