SRNET: A Shallow Skip Connection Based Convolutional Neural Network Design for Resolving Singularities
Author:
- 19 July 2019
- journal article
- research article
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 34 (4) , 924-938
Abstract
No abstract availableKeywords
This publication has 23 references indexed in Scilit:
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Going deeper with convolutions2015
- Deep learningNature, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Caffe2014
- Dynamics of Learning Near Singularities in Layered NetworksNeural Computation, 2008
- Singularities Affect Dynamics of Learning in NeuromanifoldsNeural Computation, 2006
- Learning long-term dependencies with gradient descent is difficultIEEE Transactions on Neural Networks, 1994
- Learning Complex, Extended Sequences Using the Principle of History CompressionNeural Computation, 1992
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989