Modified backpropagation algorithm for fast learning in neural networks
Electronics Letters (1990)
摘要
A fast learning rule for artificial neural systems which is based on modifications to a backpropagation algorithm is described. The rule minimises the error function along the direction of the gradient and backpropagates the error pattern according to a constant error energy approach.
更多查看译文
关键词
adaptive systems,neural nets,virtual machines,artificial neural systems,backpropagation algorithm,constant error energy approach,fast learning rule
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要