Nonlinear quantization on Hebbian-type associative memories |
| |
Authors: | Chishyan Liaw Ching-Tsorng Tsai Chao-Hui Ko |
| |
Affiliation: | 1.Department of Computer Science,Tunghai University,Taichung,Taiwan;2.Department of Information Management,Hsiuping Institute of Technology,Taichung,Taiwan |
| |
Abstract: | Hebbian-type associative memory is characterized by its simple architecture. However, the hardware implementation of Hebbian-type associative memories is normally complicated when there are a huge number of patterns stored. To simplify the interconnection values of a network, a nonlinear quantization strategy is presented. The strategy takes into account the property that the interconnection values are Gaussian distributed, and divides the interconnection weight values into a small number of unequal ranges accordingly. Interconnection weight values in each range contain information equally and each range is quantized to a value. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|