NestedNet: Learning Nested Sparse Structures in Deep Neural Networks

Recently, there have been increasing demands to construct compact deep architectures to remove unnecessary redundancy and to improve the inference speed. While many recent works focus on reducing the redundancy by eliminating unneeded weight parameters, it is not possible to apply a single deep netw...

Full description

Bibliographic Details

Published in:	2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 8669 - 8678
Main Authors:	Kim, Eunwoo, Ahn, Chanho, Oh, Songhwai
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.06.2018
Subjects:	Computer architecture Knowledge engineering Neural networks Optimization Redundancy Task analysis
ISSN:	1063-6919
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!