LEARNING REPRESENTATIONS BY BACK-PROPAGATING ERRORS
LEARNING REPRESENTATIONS BY BACK-PROPAGATING ERRORS
复制标题
DOI：
10.1038/323533a0
复制
发表时间：
1986-10-09
期刊：
影响因子：
64.8
通讯作者：
WILLIAMS, RJ
中科院分区：
文献类型：
--
作者：
RUMELHART, DE;HINTON, GE;WILLIAMS, RJ
我们描述了一个新的学习过程，反向传播，神经元样的单位网络。该过程重复地调整网络中的连接的权重，以便最小化网络的实际输出向量与期望输出向量之间的差的测量。作为权重调整的结果，不属于输入或输出的内部“隐藏”单元开始表示任务域的重要特征，并且任务中的隐藏由这些单元的交互捕获。创建有用的新特征的能力将反向传播与早期更简单的方法（如感知器收敛过程1）区分开来。
We describe a new learning procedure, back-propagation, for networks of neurone-like units. The procedure repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector. As a result of the weight adjustments, internal ‘hidden’ units which are not part of the input or output come to represent important features of the task domain, and the regularities in the task are captured by the interactions of these units. The ability to create useful new features distinguishes back-propagation from earlier, simpler methods such as the perceptron-convergence procedure1.