41 citations
Showing 2018Show all
3 papers · 1 filter
cs.LG2018
MBS: Macroblock Scaling for CNN Model Reduction
Yu-Hsun Lin, Chun-Nan Chou, Edward Y. Chang
In this paper we propose the macroblock scaling (MBS) algorithm, which can be applied to various CNN architectures to reduce their model size. MBS adaptively reduces each CNN macro…
cs.LG2018
BRIEF: Backward Reduction of CNNs with Information Flow Analysis
Yu-Hsun Lin, Chun-Nan Chou, Edward Y. Chang
This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective. This algorithm can remove substantial non-z…
cs.LG2018
EA-CG: An Approximate Second-Order Method for Training Fully-Connected Neural Networks
Sheng-Wei Chen, Chun-Nan Chou, Edward Y. Chang
For training fully-connected neural networks (FCNNs), we propose a practical approximate second-order method including: 1) an approximation of the Hessian matrix and 2) a conjugate…