基于智能内存的人工神经网络  

Artificial Neural Networks Based on Intelligent Memory

作　　者：李峰[1] 张太镒[1] 崔涛 种稚萌[1] 

机构地区：[1]西安交通大学电子与信息工程学院,西安710049 [2]Department of Electrical and Computer Engineering University of Alberta

出　　处：《电子器件》2004年第3期515-517,384,共4页Chinese Journal of Electron Devices

摘　　要：人工神经网络 ( ANN)的性能 ,尤其当其被用于在线模式识别时 ,主要依赖于加权和计算的速度。一种新型结构使得其运算时间复杂度 ( O( m) )要比传统的串行冯·诺意曼机小得多。这种结构采用了一个附加电路 ,从而扩展了传统RAM的功能。Execution of artificial neural networks, especially for online pattern recognition, mainly depends on time-efficient execution of weighted sums. A new architecture achieves this goal, with a computation time(O(m)) superior to the time complexity of sequential von Neumann machines. This architecture uses additional logic to extend the functionality of conventional Ram. We discuss an implementation of this architecture that uses reconfigurable logic.

关 键 词：人工神经网络 智能内存 屏蔽解码器 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]