Quantization effects of Hebbian-Type associative memories

Pau Choo Chung, Yi Nung Chung, Ching Tsorng Tsai

研究成果: Conference contribution

摘要

Effects of quantization strategies in Hebbian-Type associative memories are exploded in this paper. The quantization strategies considered include two-level, three-level strategy with a cut-off threshold, and linear quantizations. The two-level strategy is to clip positive interconnections into +1 and negative interconnections into -1. The three-level quantization uses the same strategy in turning the interconnections into +1 or -1. except that it is applied only to those interconnections having their values larger than a cut-off threshold. Those interconnections within the cutoff threshold are then set to zero. Results indicate that three-level quantization with a properly selected cut-off threshold gives network higher performance than two-level quantization. The performance of a network with linear quantization is also compared with a network with three-level quantization. It is also found that the linear quantization, although it preserves more network interconnections, does not significantly enhance network performance compared with the three-level quantization. Hence, it is concluded that the three-level binary quantization with an optimal threshold is a better choice when network implementations are considered.

原文English
主出版物標題1993 IEEE International Conference on Neural Networks
發行者Publ by IEEE
頁面1366-1370
頁數5
ISBN(列印)0780312007
出版狀態Published - 1993 一月 1
事件1993 IEEE International Conference on Neural Networks - San Francisco, California, USA
持續時間: 1993 三月 281993 四月 1

出版系列

名字1993 IEEE International Conference on Neural Networks

Other

Other1993 IEEE International Conference on Neural Networks
城市San Francisco, California, USA
期間93-03-2893-04-01

    指紋

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Control and Systems Engineering
  • Software
  • Artificial Intelligence

引用此

Chung, P. C., Chung, Y. N., & Tsai, C. T. (1993). Quantization effects of Hebbian-Type associative memories. 於 1993 IEEE International Conference on Neural Networks (頁 1366-1370). (1993 IEEE International Conference on Neural Networks). Publ by IEEE.