Using Kerr-Type Nonlinear Optical Materials for Artificial Neural Network Implimentations

使用克尔型非线性光学材料实现人工神经网络

• 批准号: 9312345
• 负责人: Steven Skinner
• 金额: $ 13.64万
• 依托单位: Wichita State University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1993
• 资助国家: 美国
• 起止时间: 1993-10-01 至 1996-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9312345&HistoricalAwards=false
• 关键词: Using; Kerr; Type; Nonlinear; Optical

9312345 Skinner The objective of this project is to investigate the usefulness of Kerr- Type nonlinear optical materials for all-optical implementations of feed forward artificial neural networks with optical error back- propagation training. These types of materials have pico-second response times and allow both weighted connections and nonlinear neuron processing to be implemented using thin materials layers separated by free space. This gives such networks and advantage over other optical implementations which require complicated hardware devices to implement the weighted connections and separate hardware for neuron processing. In addition, a layered network of Kerr-Type material can process both forward calculation signals and backward error propagation simultaneously. The nonlinear layers serve as processing layers and the linear layers (fee space) serve as connection layers. Each nonlinear layer can be thought of as a plane continuum of neurons connected with the layers before and after it by a continuum of optical paths. The number of available neurons and connections are limited only by the available resolution of the system optics. The inputs and weights are a distribution of irradiance in 2D space and the weights vary the refractive index profile of the nonlinear medium. The nonlinear forcing and processing functions necessary for neural computing are given by the self-action effects of the propagating wave coupled with the optical with signals applied to the nonlinear layers. Such a network has been numerically simulated in two dimensions and trained to perform logic functions and a simple optical demonstration of this network is constructed. Further simulation and training of the network to preform more complicated tasks as well as implementation of these networks in two dimensions is proposed, followed by an extension of the simulation and implementation to three dimensions. This well involve both theoretical and experimental investigations in parallel with computer simulation to determine the optimal network geometry (number and type of layers, size and required resolution of with and signal fields) as well as better techniques for controlling the application of the weight light fields. ***

9312345斯金纳本项目的目的是研究克尔型非线性光学材料的有用性，用于全光学实现的前馈人工神经网络与光学误差反向传播训练。 这些类型的材料具有皮秒响应时间，并且允许使用由自由空间分隔的薄材料层来实现加权连接和非线性神经元处理。 这给出了这样的网络和优于其他光学实现的优点，其他光学实现需要复杂的硬件设备来实现加权连接和用于神经元处理的单独硬件。此外，克尔型材料的分层网络可以同时处理前向计算信号和后向误差传播。 非线性层用作处理层，线性层（fee空间）用作连接层。 每个非线性层可以被认为是一个平面连续的神经元与它之前和之后的层通过连续的光路连接。 可用神经元和连接的数量仅受系统光学器件的可用分辨率的限制。 输入和权重是2D空间中的辐照度分布，并且权重改变非线性介质的折射率分布。 神经计算所需的非线性强迫和处理函数由传播波与施加到非线性层的信号的光耦合的自作用效应给出。 这样的网络已在二维数值模拟和训练，以执行逻辑功能，并构造了一个简单的光学演示这个网络。 进一步模拟和训练的网络，以执行更复杂的任务，以及这些网络在两个维度的实施，提出了扩展的模拟和实施到三维。 这将涉及理论和 实验研究与计算机模拟并行，以确定最佳网络几何形状（层数和类型，尺寸和所需的分辨率与信号字段）以及更好的技术，用于控制权重轻字段的应用。 ***