.png){kind=icon}
返回
Back-propagation is not efficient
.png){kind=icon}
PRE
AI
DOI：10.1016/0893-6080(95)00135-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The back-propagation learning algorithm for multi-layered neural networks, which is often successfully used in practice, appears very time consuming even for small network architectures or training tasks. However, no results are yet known concerning the complexity of this algorithm. Blum and Rivest proved that training even a three-node network is NP-complete for the case when a neuron computes the discrete linear threshold function. We generalize the technique from their NP-hardness proof for a continuous sigmoidal function used in back-propagation. We show that training a three-node sigmoid network with an additional constraint on the output neuron function (e.g., zero threshold) is NP-hard. As a consequence of this, we find training sigmoid feedforward networks, with a single hidden layer and with zero threshold of output neuron, to be intractable. This implies that back-propagation is generally not an efficient algorithm, unless at least P = NP. We rake advantage of these results by showing the NP-hardness of a special nonlinear programming problem. Copyright (C) 1996 Elsevier Science Ltd.
Keyword:
learning theory
loading problem
NP-hardness
standard sigmoid function
back-propagation
nonlinear programming
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.3K
被引数:
3.0W
机构
暂无机构信息
引用论文
.png){kind=icon}
Two-dimensional bricklayer arrangements of tolans using halogen bonding interactions使用卤素键相互作用的tolans的二维瓦工层布置
PREAI
分享收藏分享收藏
分享收藏分享收藏
查看更多内容