papers AI Learner
The Github is limit! Click to go to the new site.

Deep Asymmetric Networks with a Set of Node-wise Variant Activation Functions

2019-05-17
Jinhyeok Jang, Hyunjoong Cho, Jaehong Kim, Jaeyeon Lee, Seungjoon Yang

Abstract

This work presents deep asymmetric networks with a set of node-wise variant activation functions. The nodes’ sensitivities are affected by activation function selections such that the nodes with smaller indices become increasingly more sensitive. As a result, features learned by the nodes are sorted by the node indices in the order of their importance. Asymmetric networks not only learn input features but also the importance of those features. Nodes of lesser importance in asymmetric networks can be pruned to reduce the complexity of the networks, and the pruned networks can be retrained without incurring performance losses. We validate the feature-sorting property using both shallow and deep asymmetric networks as well as deep asymmetric networks transferred from famous networks.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1809.03721

PDF

http://arxiv.org/pdf/1809.03721


Similar Posts

Comments