Techniques for high-performance analog neural networks

摘要

Abstract: We consider analog neural network implementations (using VLSI or optical technologies) with limited accuracy and various noise and nonlinearity error sources. Algorithms and techniques to achieve high performance (good recognition P$+$PRM$/$-c$/% and large storage capacity) on such systems are considered. The adaptive clustering neural net (ACNN) and robust Ho-Kashyap (HK-2) associative processor (AP) are the neural networks considered in detail.!2