Projection based weight normalization: Efficient method for optimization on oblique manifold in DNNs
Authors:
- Lei HuangLHLei Huang
- Xianglong LiuXLXianglong Liu
- Jie QinJQJie Qin
- Fan ZhuFZFan Zhu
- Li LiuLLLi Liu
- Ling ShaoLSLing Shao
- 1 September 2020
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 105
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61872021, 61690202)
This publication has 11 references indexed in Scilit:
- Learning binary code for fast nearest subspace searchPattern Recognition, 2020
- Spatio-temporal deformable 3D ConvNets with attention for action recognitionPattern Recognition, 2020
- Hierarchical LSTMs with Adaptive Attention for Visual CaptioningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Multiple Marginal Fisher AnalysisIEEE Transactions on Industrial Electronics, 2018
- From Deterministic to Generative: Multimodal Stochastic RNNs for Video CaptioningIEEE Transactions on Neural Networks and Learning Systems, 2018
- Active multi-kernel domain adaptation for hyperspectral image classificationPattern Recognition, 2018
- Connections Between Nuclear-Norm and Frobenius-Norm-Based RepresentationsIEEE Transactions on Neural Networks and Learning Systems, 2016
- Efficient BackProp2012
- Riemannian Geometry of Grassmann Manifolds with a View on Algorithmic ComputationActa Applicandae Mathematicae, 2004
- On the Geometry of Feedforward Neural Network Error SurfacesNeural Computation, 1993