A New Framework to Train Autoencoders Through Non-Smooth Regularization

Deep structures consisting of many layers of nonlinearities have a high potential of expressing complex relations if properly initialized. Autoencoders play a complementary role in training a deep structure by initializing each layer in a greedy unsupervised manner. Due to the high capacity presente...

Full description

Bibliographic Details

Published in:	IEEE transactions on signal processing Vol. 67; no. 7; pp. 1860 - 1874
Main Authors:	Amini, Sajjad, Ghaemmaghami, Shahrokh
Format:	Journal Article
Language:	English
Published:	IEEE 01.04.2019
Subjects:	Autoencoder Convergence Decoding Encoding Feature extraction gradient descent Neural networks proximal operator regularizer Signal processing algorithms Training
ISSN:	1053-587X, 1941-0476
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!