On-line backpropagation in two-layered neural networks

On-line backpropagation in two-layered neural networks
复制标题

两层神经网络中的在线反向传播

DOI:
10.1088/0305-4470/28/20/002
复制
发表时间:
1995
期刊:
Journal of Physics A
影响因子:
--
通讯作者:
Michael Biehl
Michael Biehl
中科院分区:
--
文献类型:
--
作者:
P. Riegler;Michael Biehl

文献摘要

被引文献

相似文献

我们提出了一个精确的分析学习规则的在线梯度下降在一个两层的神经网络可调隐藏到输出的权重(误差的反向传播)。结果进行了比较,具有相同的架构,但固定的权重在第二层的网络的训练。
We present an exact analysis of learning a rule by on-line gradient descent in a two-layered neural network with adjustable hidden-to-output weights (backpropagation of error). Results are compared with the training of networks having the same architecture but fixed weights in the second layer.