Logo image
Back
Lossless Compression of Deep Neural Networks
Conference proceeding   Peer reviewed

Lossless Compression of Deep Neural Networks

Thiago Serra, Abhinav Kumar and Srikumar Ramalingam
INTEGRATION OF CONSTRAINT PROGRAMMING, ARTIFICIAL INTELLIGENCE, AND OPERATIONS RESEARCH, CPAIOR 2020, Vol.12296, pp.417-430
Lecture Notes in Computer Science
01/01/2020
DOI: 10.1007/978-3-030-58942-4_27
url
https://arxiv.org/pdf/2001.00218View
Open Access

Abstract

Deep neural networks have been successful in many predictive modeling tasks, such as image and language recognition, where large neural networks are often used to obtain good accuracy. Consequently, it is challenging to deploy these networks under limited computational resources, such as in mobile devices. In this work, we introduce an algorithm that removes units and layers of a neural network while not changing the output that is produced, which thus implies a lossless compression. This algorithm, which we denote as LEO (Lossless Expressiveness Optimization), relies on Mixed-Integer Linear Programming (MILP) to identify Rectified Linear Units (ReLUs) with linear behavior over the input domain. By using l(1) regularization to induce such behavior, we can benefit from training over a larger architecture than we would later use in the environment where the trained neural network is deployed.
 Computer Science Computer Science, Artificial Intelligence Computer Science, Software Engineering Operations Research & Management Science Science & Technology Technology

Details

Metrics

12 Record Views
34 Times Cited - Web of Science
Logo image