Abstract
Deep neural networks are typically represented by a much larger number of parameters than shallow models, making them prohibitive for small footprint devices. Recent research shows that there is considerable redundancy in the parameter space of deep neural networks. In this paper, we propose a method to compress deep neural networks by using the Fisher Information metric, which we estimate through a stochastic optimization method that keeps track of second-order information in the network. We first remove unimportant parameters and then use non-uniform fixed point quantization to assign more bits to parameters with higher Fisher Information estimates. We evaluate our method on a classification task with a convolutional neural network trained on the MNIST data set. Experimental results show that our method outperforms existing methods for both network pruning and quantization.
Original language | English (US) |
---|---|
Title of host publication | Proceedings - IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2016 |
Publisher | IEEE Computer Society |
Pages | 93-98 |
Number of pages | 6 |
Volume | 2016-September |
ISBN (Electronic) | 9781467390385 |
DOIs | |
State | Published - Sep 2 2016 |
Event | 15th IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2016 - Pittsburgh, United States Duration: Jul 11 2016 → Jul 13 2016 |
Other
Other | 15th IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2016 |
---|---|
Country | United States |
City | Pittsburgh |
Period | 7/11/16 → 7/13/16 |
Fingerprint
ASJC Scopus subject areas
- Hardware and Architecture
- Control and Systems Engineering
- Electrical and Electronic Engineering
Cite this
Reducing the model order of deep neural networks using information theory. / Tu, Ming; Berisha, Visar; Cao, Yu; Seo, Jae-sun.
Proceedings - IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2016. Vol. 2016-September IEEE Computer Society, 2016. p. 93-98 7560179.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Reducing the model order of deep neural networks using information theory
AU - Tu, Ming
AU - Berisha, Visar
AU - Cao, Yu
AU - Seo, Jae-sun
PY - 2016/9/2
Y1 - 2016/9/2
N2 - Deep neural networks are typically represented by a much larger number of parameters than shallow models, making them prohibitive for small footprint devices. Recent research shows that there is considerable redundancy in the parameter space of deep neural networks. In this paper, we propose a method to compress deep neural networks by using the Fisher Information metric, which we estimate through a stochastic optimization method that keeps track of second-order information in the network. We first remove unimportant parameters and then use non-uniform fixed point quantization to assign more bits to parameters with higher Fisher Information estimates. We evaluate our method on a classification task with a convolutional neural network trained on the MNIST data set. Experimental results show that our method outperforms existing methods for both network pruning and quantization.
AB - Deep neural networks are typically represented by a much larger number of parameters than shallow models, making them prohibitive for small footprint devices. Recent research shows that there is considerable redundancy in the parameter space of deep neural networks. In this paper, we propose a method to compress deep neural networks by using the Fisher Information metric, which we estimate through a stochastic optimization method that keeps track of second-order information in the network. We first remove unimportant parameters and then use non-uniform fixed point quantization to assign more bits to parameters with higher Fisher Information estimates. We evaluate our method on a classification task with a convolutional neural network trained on the MNIST data set. Experimental results show that our method outperforms existing methods for both network pruning and quantization.
UR - http://www.scopus.com/inward/record.url?scp=84988929256&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84988929256&partnerID=8YFLogxK
U2 - 10.1109/ISVLSI.2016.117
DO - 10.1109/ISVLSI.2016.117
M3 - Conference contribution
AN - SCOPUS:84988929256
VL - 2016-September
SP - 93
EP - 98
BT - Proceedings - IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2016
PB - IEEE Computer Society
ER -