Barge M, Heggarty K, Idan Y, Chevallier R
Appl Opt. 1996 Aug 10;35(23):4655-65. doi: 10.1364/AO.35.004655.
We present an optical implementation of an improved version of the Kohonen map neural network applied to the recognition of handwritten digits taken from a postal code database. Improvements result from the introduction of supervision during the learning stage, a technique that also simplifies the map layer labeling. The experimental implementation is based on a frequency-multiplexed raster computer-generated hologram used to realize the required N(4) interconnection. The setup is shown to be equivalent to a 64-channel correlator. Computer simulations are used to study various detection and classification procedures. The results of the optical experiments, obtained with binary phase computer-generated holograms, are presented and shown to be in excellent agreement with the simulations.
我们展示了一种改进版科霍宁映射神经网络的光学实现，该网络应用于从邮政编码数据库中提取的手写数字识别。改进源于在学习阶段引入监督，这一技术还简化了映射层标记。实验实现基于一个频率复用光栅计算机生成全息图，用于实现所需的N(4)互连。该装置被证明等效于一个64通道相关器。使用计算机模拟来研究各种检测和分类程序。展示了用二元相位计算机生成全息图获得的光学实验结果，结果表明与模拟结果非常吻合。
