Jackel L D, Howard R E, Denker J S, Hubbard W, Solla S A
Appl Opt. 1987 Dec 1;26(23):5081-4. doi: 10.1364/AO.26.005081.
Electronic neural networks can perform the function of associative memory. Given an input pattern, the network searches through its stored memories to find which of them best matches the input. Thus the network does a combination of content-addressable search and error correction. The number of random memories that a network can store is limited to a fraction of the number of electronic neurons in the circuit. We propose a method for building a hierarchy of networks that allows the fast parallel search through a list of memories that is too large to store in a single network. We have demonstrated the principle of this approach by an example in image vector quantization.
电子神经网络可以执行关联记忆功能。给定一个输入模式，网络会在其存储的记忆中进行搜索，以找出最匹配该输入的记忆。因此，网络执行了内容可寻址搜索和纠错的组合。网络能够存储的随机记忆数量限于电路中电子神经元数量的一小部分。我们提出了一种构建网络层次结构的方法，该方法允许对一个太大而无法存储在单个网络中的记忆列表进行快速并行搜索。我们通过图像矢量量化中的一个示例证明了这种方法的原理。
