.png){kind=icon}
返回
An adaptive nonmonotone active set - weight constrained - neural network training algorithm
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2019.06.033.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this work, a new direction for improving the classification accuracy of artificial neural networks is proposed by bounding the weights of the network, during the training process. Furthermore, a new adaptive nonmonotone active set - weight constrained - neural network training algorithm is proposed in order to demonstrate the efficacy and efficiency of our approach. The proposed training algorithm consists of two phases: a gradient projection phase which utilizes an adaptive nonmonotone line search and an unconstrained optimization phase which exploits the box structure of the bounds. Also, a set of switching criteria is defined for efficiently switching between the two phases. Our preliminary numerical experiments illustrate that the classification efficiency of the proposed algorithm outperforms classical neural network training algorithms, providing empirical evidence that it provides more stable, efficient and reliable learning. (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Artificial neural networks
Constrained optimization
Weight bounds
ASA method
Conjugate gradient algorithm
Accuracy
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:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Origin of Structural Change Driven by A-Site Lanthanide Doping in ABO3-Type Perovskite Ferroelectrics.png)
Crystals
OAAI
CrystalsIF0
OAAI分享收藏A new efficient training strategy for deep neural networks by hybridization of artificial bee colony and limited-memory BFGS optimization algorithms基于人工蜂群和有限内存BFGS优化算法的深度神经网络高效训练策略NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏分享收藏
查看更多内容