Principle and Present Status of Pattern Recognition System with Optical Neural Network 光学神经网络模式识别系统原理及其现状
Shift, rotation and scale invariant optical neural network recognition system 平移、旋转及尺度不变光学神经网络识别系统
Three-layer optical neural network for pattern recognition with rotation invariance 具有转动不变性模式识别能力的三层光学神经网络模型
Semiconductor optoelectronic devices in the optical neural network 光神经网络中的半导体光电器件
A programmable optical neural network using a phase array beam splitter as the interconnection device 使用相位型阵列分束器作为互连元件的可编程光学神经网络
Multivalue Models For Optical Neural Network and Its Experimental Investigation 光学神经网络多值模型及实验研究
To deal with the defects of BP neural network and genetic algorithm, this paper presents a new optical model of BP neural Network, which can optimize the structure, weights and biases of neural network simultaneously. 针对BP网络和遗传算法的缺陷,提出了一种新的遗传神经网络优化模型,可以用来同时优化BP神经网络的网络结构和权值阈值,叙述了该算法的设计过程。
Structure-light-induced waveguide devices in PR crystals can be used for the current optical communication systems, and may be used for optical dynamic interconnection and optical neural network systems. 因此光折变晶体中结构光写入的波导器件可以被用于现有的光通信系统,并且有望被用于动态光互连以及光学神经网络系统。
Simulation and Design of Optical Fiber Direction Coupler Using Neural Network 光纤方向耦合器的神经网络仿真与设计
The identification of the chaotic optical system with BP feedforward neural network supported by a modified BP algorithm is suggested. 研究了利用前向神经网络对混沌光学系统进行混沌加速系统辨识的可能性。
Theoretical Analysis and Single Channel Optical Implementation of the Hopfield Neural Network Model and Its Improved Model Hopfield神经网络模型和改进模型的理论分析及单通道光学实现
Using Self imaging Functions for the Optical Interconnection of Neural Network 比例自变换实现神经网络光学互连
In this paper, two multivalue models for optical neural network are studied and optically simulated with a optical system including a SLM PROM. 本文对两种光学神经网络多值模型进行了探讨,并设计了以空间光调制器PROM为主体的光学系统对这两种模型进行了光学模似。
Assessment of signal-to-noise ratio of space optical remote sensor using artificial neural network 航天光学遥感器信噪比的人工神经网络评价
In this paper, we briefly introduce basic structure and principle of optical neural devices for the purpose of optical neural network. 简要介绍了用于光神经网络的光神经器件的基本结构与工作原理。
The errors induced by diffraction in these networks are emphasized and analyzed with computer simulation using the experimental parameters and input data, where diffraction, optical information processing and neural network theories are applied. 根据衍射、光学信息处理和神经网络理论,采用实验中的参量和输入数据,对衍射造成的输出误差做了仿真分析。
A model of three-layer optical neural network is proposed for pattern recognition with rotation invariance. 本文提出一种适于光学实现的三层神经网络模型,该模型具有对多目标转动不变的模式识别能力。
Architecture design of an optical neural network with lenslet array 二维光学神经网络自由空间互连结构设计
Optical neural network with a third-order interconnection 二阶互连光学神经网络
Three-phase optical current transducer based on neural network inverse modeling 基于神经网络逆建模的三相光学电流互感器
Evaluation of Positive-Complemental optical neural network model 正补态光学神经网络模型性能评估
Real time recognition of the correlation peaks of multi channel optical correlator using neural network 基于人工神经网络的多路光学相关器相关峰的实时识别
Optical Implementation of Neural Network 神经元网络的光学实现
Analysis on the storage capacity of IPA model and the construction of a two layer hetero Association optical neural network model 图样间联想光学神经网络模型存贮分析及两层异联想识别模型的构造
Optical Neural Network and Optical Neurochips 光神经网络与光神经芯片
Influence of Hardware Error on Optical Neural Network 光学神经网络中硬件误差对性能影响的分析
Optical Implementation of WTA Neural Network with Bipolar Neuron States 全双极WTA神经网络模型的光学实现
Micro lenses and lens arrays are significant devices of micro optics and have been widely applied on fiber coupling, beam shaping, integral imaging and optical neural network, et al. 微透镜及微透镜阵列作为微光学领域的重要器件之一,在光纤耦合、光束整形、集成成像、光学神经网络等场合有广泛的应用。
It can modulate space lights at real-time, changing optical signal to electroic signal. It is the key device which constitute the real-time optical information processing, optical caculate and optical neural network. It can achieve high speed and complex operations such as matrix multiplication and division. 可实时地在空间上调制光束,进行对光电信号转换,是构成实时光学信息处理、光计算和光学神经网络等系统的关键器件,能够快速完成矩阵乘除等复杂运算。