Learning Compact Architectures for Deep Neural Networks

Learning Compact Architectures for Deep Neural Networks

Deep neural networks with millions of parameters are at the heart of many state of the art computer vision models. However, recent works have shown that models with much smaller number of parameters can often perform just as well. A smaller model has the advantage of being faster to evaluate and eas...

Full description

Bibliographic Details
Main Author: Srinivas, Suraj
Other Authors: Venkatesh Babu, R
Language:en_US
Published: 2018
Subjects:
Deep Neural Networks
Learning Compact Architectures
Machine Learning
Binary Neural Nets
Architecture Learning
Sparse Neural Networks
Bayesian Neural Networks
Neural Network Architectures
Computational and Data Sciences
Online Access:http://etd.iisc.ernet.in/2005/3581
http://etd.iisc.ernet.in/abstracts/4449/G28168-Abs.pdf

Internet

http://etd.iisc.ernet.in/2005/3581
http://etd.iisc.ernet.in/abstracts/4449/G28168-Abs.pdf

Similar Items