BACK-PROPAGATION LEARNING AND NONIDEALITIES IN ANALOG NEURAL NETWORK HARDWARE
BACK-PROPAGATION LEARNING AND NONIDEALITIES IN ANALOG NEURAL NETWORK HARDWARE
复制标题
DOI：
10.1109/72.80296
复制
发表时间：
1991-01-01
影响因子：
--
通讯作者：
WONG, CC
中科院分区：
文献类型：
--
作者：
FRYE, RC;RIETMAN, EA;WONG, CC
我们目前的实验结果，使用光学控制的神经网络的自适应学习。 我们已经使用了非线性系统识别和信号预测的例子问题，潜在的神经网络应用的两个共同领域，研究模拟神经硬件的能力。 这些实验研究了模拟硬件系统中典型的各种非理想性的影响。 他们表明，使用大型非均匀组件阵列的网络可以执行模拟计算，其准确度比预期的要高得多，因为网络元素的变化程度。 我们还研究了其他常见的非理想性，如噪声，权重量化和动态范围限制的影响。
We present experimental results of adaptive learning using an optically controlled neural network. We have used example problems in nonlinear system identification and signal prediction, two common areas of potential neural network application, to study the capabilities of analog neural hardware. These experiments investigate the effects of a variety of nonidealities typical of analog hardware systems. They show that networks using large arrays of nonuniform components can perform analog computations with a much higher degree of accuracy than might be expected, given the degree of variation in the network's elements. We have also investigated effects of other common nonidealities, such as noise, weight quantization, and dynamic range limitations.