VLSI implementation of a neural network memory with several hundreds of neurons
VLSI implementation of a neural network memory with several hundreds of neurons
复制标题
具有数百个神经元的神经网络存储器的 VLSI 实现
DOI：
10.1063/1.36253
复制
发表时间：
1987
期刊：
影响因子：
3.5
通讯作者：
D. B. Schwartz
中科院分区：
文献类型：
--
作者：
H. Graf;L. Jackel;R. Howard;B. Straughn;J. Denker;W. Hubbard;D. Tennant;D. B. Schwartz
我们使用模拟和数字VLSI技术以及定制的微制造工艺，设计了一种在单个芯片上具有256个神经元的电子神经网络(ENN)存储器。具有反相和同相输出的放大器用于神经元进行抑制性和兴奋性连接。各个神经元之间的连接是由非晶硅电阻提供的，这些电阻在最后的制造步骤中被放置在芯片上。这项技术允许神经元非常密集地堆积在一起。电子束直写被用来对电阻进行图案化，从而很容易将存储在网络中的信息从一个芯片改变到另一个芯片。
We designed an Electronic Neural Network (ENN) memory with 256 neurons on a single chip using a combination of analog and digital VLSI technology plus a custom microfabrication process. Amplifiers with inverting and noninverting outputs are used for the neurons to make inhibitory and excitatory connections. The connections between the individual neurons are provided by amorphous‐silicon resistors which are placed on the CMOS chip in the last fabrication step. This technique allows a very dense packing of the neurons. Electron‐beam direct‐writing is used to pattern the resistors making it easy to change the information stored in the network from one chip to the next.