Bidirectional associative memory with learning capability using simultaneous perturbation
Bidirectional associative memory with learning capability using simultaneous perturbation
复制标题
DOI：
10.1016/j.neucom.2005.02.021
复制
发表时间：
2005-12
期刊：
影响因子：
6
通讯作者：
Y. Maeda;M. Wakamura
中科院分区：
文献类型：
--
作者：
Y. Maeda;M. Wakamura
双向联想记忆（BAM）是一种典型的循环网络。它由两层组成，可以实现回忆模式与触发模式不同的异联想记忆。通常，BAM 中的权重是通过 Hebbian 学习或二元问题的相关学习来确定的。为了促进BAM更广泛的应用，发明新的学习方案至关重要，该方案不仅适用于二元问题，而且适用于模拟问题。此外，具有学习能力的 BAM 的硬件实现也很有趣。本文描述了一种使用同时扰动的 BAM 递归学习方案。此外，还说明了其使用FPGA的硬件实现。显示了一些结果和实现的细节。
Bidirectional associative memory (BAM) is a typical recurrent network. It consists of two layers and can realize the hetero-associative memory in which recalled patterns are different from triggering patterns. Ordinarily, weights in the BAM are determined by Hebbian learning or the correlation learning for binary problems. In order to promote wider range of applications of the BAMs, it is crucial to invent new learning scheme which is applicable not only to the binary problems but also to analog ones. Moreover, hardware implementation of the BAMs with learning capability is intriguing. In this paper, a recursive learning scheme for the BAMs using the simultaneous perturbation is described. Moreover, its hardware realization using the FPGA is explained. Some results and the details of the realization are shown.