Linear quantization of Hebbian-type associative memories in interconnection implementations

Pau Choo Chung, Ching Tsorng Tsai, Yung Nien Sun

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

The effects of linear quantized Hebbian-type associative memories (HAMs) on storage capacity and hardware implementations are explored in this paper. For the linear quantization, the interconnection weights are linearly quantized into a small number of levels. This consideration focuses mainly on the situation when only a limited accuracy range can be achieved on hardware implementations. Results of simulation and theory show that the number of quantization levels required is relatively small compared with the possible values of interconnections. Therefore, linear quantization in HAMs is worthwhile in hardware implementations.

Original languageEnglish
Pages1092-1096
Number of pages5
Publication statusPublished - 1994 Dec 1
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: 1994 Jun 271994 Jun 29

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period94-06-2794-06-29

Fingerprint

Computer hardware
Data storage equipment
Hardware

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Chung, P. C., Tsai, C. T., & Sun, Y. N. (1994). Linear quantization of Hebbian-type associative memories in interconnection implementations. 1092-1096. Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, .
Chung, Pau Choo ; Tsai, Ching Tsorng ; Sun, Yung Nien. / Linear quantization of Hebbian-type associative memories in interconnection implementations. Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, .5 p.
@conference{85a8e1b44e2e4f8ea0309747a0558302,
title = "Linear quantization of Hebbian-type associative memories in interconnection implementations",
abstract = "The effects of linear quantized Hebbian-type associative memories (HAMs) on storage capacity and hardware implementations are explored in this paper. For the linear quantization, the interconnection weights are linearly quantized into a small number of levels. This consideration focuses mainly on the situation when only a limited accuracy range can be achieved on hardware implementations. Results of simulation and theory show that the number of quantization levels required is relatively small compared with the possible values of interconnections. Therefore, linear quantization in HAMs is worthwhile in hardware implementations.",
author = "Chung, {Pau Choo} and Tsai, {Ching Tsorng} and Sun, {Yung Nien}",
year = "1994",
month = "12",
day = "1",
language = "English",
pages = "1092--1096",
note = "Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) ; Conference date: 27-06-1994 Through 29-06-1994",

}

Chung, PC, Tsai, CT & Sun, YN 1994, 'Linear quantization of Hebbian-type associative memories in interconnection implementations' Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, 94-06-27 - 94-06-29, pp. 1092-1096.

Linear quantization of Hebbian-type associative memories in interconnection implementations. / Chung, Pau Choo; Tsai, Ching Tsorng; Sun, Yung Nien.

1994. 1092-1096 Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Linear quantization of Hebbian-type associative memories in interconnection implementations

AU - Chung, Pau Choo

AU - Tsai, Ching Tsorng

AU - Sun, Yung Nien

PY - 1994/12/1

Y1 - 1994/12/1

N2 - The effects of linear quantized Hebbian-type associative memories (HAMs) on storage capacity and hardware implementations are explored in this paper. For the linear quantization, the interconnection weights are linearly quantized into a small number of levels. This consideration focuses mainly on the situation when only a limited accuracy range can be achieved on hardware implementations. Results of simulation and theory show that the number of quantization levels required is relatively small compared with the possible values of interconnections. Therefore, linear quantization in HAMs is worthwhile in hardware implementations.

AB - The effects of linear quantized Hebbian-type associative memories (HAMs) on storage capacity and hardware implementations are explored in this paper. For the linear quantization, the interconnection weights are linearly quantized into a small number of levels. This consideration focuses mainly on the situation when only a limited accuracy range can be achieved on hardware implementations. Results of simulation and theory show that the number of quantization levels required is relatively small compared with the possible values of interconnections. Therefore, linear quantization in HAMs is worthwhile in hardware implementations.

UR - http://www.scopus.com/inward/record.url?scp=0028744833&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028744833&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0028744833

SP - 1092

EP - 1096

ER -

Chung PC, Tsai CT, Sun YN. Linear quantization of Hebbian-type associative memories in interconnection implementations. 1994. Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, .