Zhang W, Itoh K, Tanida J, Ichioka Y
Appl Opt. 1990 Nov 10;29(32):4790-7. doi: 10.1364/AO.29.004790.
This paper proposes a parallel distributed processing model with local space-invariant interconnections, which is more readily implemented by optics and is able to classify patterns correctly, even if they have been shifted or distorted. Error backpropagation is used as a training algorithm. Computer simulation results presented indicate that the processing is effective and the network can deal with the shifted or distorted patterns. Moreover, the optical implementation architecture using matched filters for the model is discussed.
本文提出了一种具有局部空间不变互连的并行分布式处理模型，该模型更易于通过光学方法实现，并且即使模式发生了平移或失真，也能够正确地对其进行分类。误差反向传播被用作训练算法。给出的计算机模拟结果表明，该处理是有效的，并且网络能够处理平移或失真的模式。此外，还讨论了针对该模型使用匹配滤波器的光学实现架构。
