Learning the Architecture of Deep Neural Networks
Year: 2015
Type: preprint
Abstract: Deep neural networks with millions of parameters are at the heart of many state of the art machine learning models today. However, recent works have shown that models with much smaller number of parameters can also perform just as well. In this work, we introduce the problem of architecture-learning, i.e; learning the architecture of a neural network along with weights. We introduce a new trainable parameter called tri-state ReLU, which helps in eliminating unnecessary neurons. We also propose a smooth regularizer which encourages the total number of neurons after elimination to be small. The resulting objective is differentiable and simple to optimize. We experimentally validate our method on both small and large networks, and show that it can learn models with a considerably small number of parameters without affecting prediction accuracy.
Source: arXiv (Cornell University)
Authors: Suraj Srinivas, R. Venkatesh Babu
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2181028625
