.png){kind=icon}
返回
A novel weight initialization method for the random neural network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2009.02.023.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 paper, we propose a novel weight initialization method for the random neural network. The method relies on approximating the signal-flow equations of the network to obtain a linear system of equations with nonnegativity constraints. For the solution of the formulated linear nonnegative least squares problem we have developed a projected gradient algorithm. It is shown that supervised learning with the developed initialization method has better performance in terms of both solution quality and execution time than learning with random initialization when applied to a combinatorial optimization emergency response problem. (C) 2009 Elsevier B.V. All rights reserved.
Keyword:
Random neural network (RNN)
Weight initialization
Nonnegative least squares (NNLS)
Projected gradient method
Combinatorial optimization
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
暂无机构信息
引用论文
G-networks:: A versatile approach for work removal in queueing networksG-networks:: 一种在排队网络中删除工作的通用方法
PREAI
分享收藏
分享收藏
分享收藏A new method in determining initial weights of feedforward neural networks for training enhancement确定用于训练增强的前馈神经网络初始权重的新方法.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏分享收藏Magnetic resonance imaging of resting OEF and CMRO2 using a generalized calibration model for hypercapnia and hyperoxiaNeuroImage
NeuroImageIF0
PREAI
分享收藏
查看更多内容