Characteristics of Hebbian-Type Associative Memories with Quantized Interconnections

Pau Choo Chung; Ching Tsorng Tsai; Yung Nien Sun

doi:10.1109/81.269054

Characteristics of Hebbian-Type Associative Memories with Quantized Interconnections

Pau Choo Chung, Ching Tsorng Tsai, Yung Nien Sun

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

The effects of quantized Hebbian-type associative memories (HAM's) on storage capacity and hardware implementations are explored in this paper. The quantizations include a two-level strategy and a three-level strategy using a cutoff threshold in which the interconnection weights of both strategies are restricted to binary memory points on each synapse. The restricted interconnection weights enable a digital or an analog HAM to be implemented more space efficiently. The three-level quantized network with sparse connectivity among neurons has further simplified analog circuits in the dedicated hardwares. Results of simulation and theory show that the three-level quantized network with a properly selected cutoff threshold possesses higher storage capacity than the two-level quantized network.

Original language	English
Pages (from-to)	168-171
Number of pages	4
Journal	IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications
Volume	41
Issue number	2
DOIs	https://doi.org/10.1109/81.269054
Publication status	Published - 1994 Feb

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering

Access to Document

10.1109/81.269054

Cite this

@article{9e9597c44bb94ce2acb350740da60a33,

title = "Characteristics of Hebbian-Type Associative Memories with Quantized Interconnections",

abstract = "The effects of quantized Hebbian-type associative memories (HAM's) on storage capacity and hardware implementations are explored in this paper. The quantizations include a two-level strategy and a three-level strategy using a cutoff threshold in which the interconnection weights of both strategies are restricted to binary memory points on each synapse. The restricted interconnection weights enable a digital or an analog HAM to be implemented more space efficiently. The three-level quantized network with sparse connectivity among neurons has further simplified analog circuits in the dedicated hardwares. Results of simulation and theory show that the three-level quantized network with a properly selected cutoff threshold possesses higher storage capacity than the two-level quantized network.",

author = "Chung, {Pau Choo} and Tsai, {Ching Tsorng} and Sun, {Yung Nien}",

note = "Funding Information: Manuscript received January 4, 1993; revised July 20, 1993. This work was supported by the National Science Council, R.O.C., under Grant NSC 83448-E006-004. This paper was recommended by Associate Editor Isao Shirakawa. The authors are with the Department of Electrical Engineering, National Cheng-Kung University, Tainan, Taiwan 70101, ROC. IEEE Log Number 9215705D.",

year = "1994",

month = feb,

doi = "10.1109/81.269054",

language = "English",

volume = "41",

pages = "168--171",

journal = "IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications",

issn = "1057-7122",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - Characteristics of Hebbian-Type Associative Memories with Quantized Interconnections

AU - Chung, Pau Choo

AU - Tsai, Ching Tsorng

AU - Sun, Yung Nien

N1 - Funding Information: Manuscript received January 4, 1993; revised July 20, 1993. This work was supported by the National Science Council, R.O.C., under Grant NSC 83448-E006-004. This paper was recommended by Associate Editor Isao Shirakawa. The authors are with the Department of Electrical Engineering, National Cheng-Kung University, Tainan, Taiwan 70101, ROC. IEEE Log Number 9215705D.

PY - 1994/2

Y1 - 1994/2

N2 - The effects of quantized Hebbian-type associative memories (HAM's) on storage capacity and hardware implementations are explored in this paper. The quantizations include a two-level strategy and a three-level strategy using a cutoff threshold in which the interconnection weights of both strategies are restricted to binary memory points on each synapse. The restricted interconnection weights enable a digital or an analog HAM to be implemented more space efficiently. The three-level quantized network with sparse connectivity among neurons has further simplified analog circuits in the dedicated hardwares. Results of simulation and theory show that the three-level quantized network with a properly selected cutoff threshold possesses higher storage capacity than the two-level quantized network.

AB - The effects of quantized Hebbian-type associative memories (HAM's) on storage capacity and hardware implementations are explored in this paper. The quantizations include a two-level strategy and a three-level strategy using a cutoff threshold in which the interconnection weights of both strategies are restricted to binary memory points on each synapse. The restricted interconnection weights enable a digital or an analog HAM to be implemented more space efficiently. The three-level quantized network with sparse connectivity among neurons has further simplified analog circuits in the dedicated hardwares. Results of simulation and theory show that the three-level quantized network with a properly selected cutoff threshold possesses higher storage capacity than the two-level quantized network.

UR - http://www.scopus.com/inward/record.url?scp=0028377949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028377949&partnerID=8YFLogxK

U2 - 10.1109/81.269054

DO - 10.1109/81.269054

M3 - Article

AN - SCOPUS:0028377949

SN - 1057-7122

VL - 41

SP - 168

EP - 171

JO - IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications

JF - IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications

IS - 2

ER -

Characteristics of Hebbian-Type Associative Memories with Quantized Interconnections

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this