期刊
NEURAL NETWORKS
卷 16, 期 5-6, 页码 683-689出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/S0893-6080(03)00127-8
关键词
recurrent neural network; input-output; adaptive behavior
We illustrate the ability of a fixed-weight neural network, trained with Kalman filter methods, to perform tasks that are usually entrusted to an explicitly adaptive system. Following a simple example, we demonstrate that such a network can be trained to exhibit input-output behavior that depends on which of two conditioning tasks was performed a substantial number of time steps in the past. This behavior can also be made to survive an intervening interference task. (C) 2003 Published by Elsevier Science Ltd.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据