Chao T H, Stoner W W
Appl Opt. 1993 Mar 10;32(8):1359-69. doi: 10.1364/AO.32.001359.
An optical neural network based on the neocognitron paradigm [IEEE Trans. Syst. Man Cybern. SMC-13, 826-834 (1983)] is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by feeding back the output of the feature correlator iteratively to the input spatial light modulator and by updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space-object discrimination is also presented.
介绍了一种基于新认知机范式的光学神经网络[《IEEE系统、人与控制论汇刊》SMC - 13，826 - 834（1983年）]。该架构设计的一个新颖之处在于每个处理层内的平移不变多通道傅里叶光学相关。通过将特征相关器的输出迭代反馈到输入空间光调制器并更新傅里叶滤波器来实现多层处理。通过用从目标图像中提取的特征对神经网络进行训练，实现了具有类内容错和类间区分的成功模式识别。提供了详细的系统描述。还给出了用于空间目标识别的两层神经网络的实验演示。
