Power-law initialization algorithm for convolutional neural networks
- 10 August 2023
- journal article
- research article
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (30) , 22431-22447
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (41706198)
This publication has 13 references indexed in Scilit:
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Deep learningNature, 2015
- A new weight initialization method for sigmoidal feedforward artificial neural networks2014
- Statistical notes for clinical researchers: assessing normal distribution (2) using skewness and kurtosisRestorative Dentistry & Endodontics, 2013
- Jarque-Bera Test2011
- Scale-Free Brain Functional NetworksPhysical Review Letters, 2005
- Analyzing Weight Distribution of Feedforward Neural Networks and Efficient Weight Initialization2004
- Forward propagation universal learning network2002
- Feedforward networks training speed enhancement by optimal initialization of the synaptic coefficientsIEEE Transactions on Neural Networks, 2001
- Learning representations by back-propagating errorsNature, 1986