复合对向－反向传播人工神经网络模型及其应用

A New Artificial Neural Network Model:Combined Counter-Back Propagation and its Application

摘要: 组合Ｋｏｈｏｎｅｎ竞争学习和反向传播学习的优点，本文首次提出了复合对向－反向传播人工神经网络模型，该模型较好地体现了生物神经网络系统信息处理时的自适应、自组织、分布式存贮及并行处理等特点。它保留了反向传播网络的优点，同时较后者更易收敛，计算时间缩短，网络参数设置也更为自由。通过在临床精液检查结果分析中的成功应用，证明了该系统的有效性和可靠性。

Abstract: A new artificial neural network model,combined counter-back propagation (CCBP),was developed by combining all virtues of competitive learning and back propagation learning.The characteristics of CCBP model were studied throughly, and it was showed that CC