NeuralNetworksandLearningMachines

This text is ideal for graduate-level neural network courses offered in the departments of Computer Engineering, Electrical Engineering, and Computer Science. Renowned for its thoroughness and readability, it is well-organized and completely up-to-date. This comprehensive treatment of neural networks from an engineering perspective recognizes the richness of the subject matter when studying the duality of neural networks and learning machines together.

In this revised and refocused edition, ideas from both neural networks and machine learning are hybridized to perform improved learning tasks beyond what either could do independently.

作者简介

SimonHaykin，于1953年获得英国伯明翰大学博士学位，目前为加拿大McMaster大学电子与计算机工程系教授、通信研究实验室主任。他是国际电子电气工程界的*名学者，曾获得IEEEMcNaughton金奖。他是加拿大皇家学会院士、IEEE会士，在神经网络、通信、自适应滤波器等领域成果颇丰，*有多部标准教材。