Tampere University of Technology

TUTCRIS Research Portal

Simultaneously Learning Architectures and Features of Deep Neural Networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning – ICANN 2019
Subtitle of host publicationDeep Learning - 28th International Conference on Artificial Neural Networks, Proceedings
EditorsIgor V. Tetko, Pavel Karpov, Fabian Theis, Vera Kurková
PublisherSpringer Verlag
Pages275-287
Number of pages13
ISBN (Print)9783030304836
DOIs
Publication statusPublished - 2019
Publication typeA4 Article in a conference publication
EventInternational Conference on Artificial Neural Networks - Munich, Germany
Duration: 17 Sep 201919 Sep 2019

Publication series

NameLecture Notes in Computer Science
Volume11728
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Conference on Artificial Neural Networks
CountryGermany
CityMunich
Period17/09/1919/09/19

Abstract

This paper presents a novel method which simultaneously learns the number of filters and network features repeatedly over multiple epochs. We propose a novel pruning loss to explicitly enforces the optimizer to focus on promising candidate filters while suppressing contributions of less relevant ones. In the meanwhile, we further propose to enforce the diversities between filters and this diversity-based regularization term improves the trade-off between model sizes and accuracies. It turns out the interplay between architecture and feature optimizations improves the final compressed models, and the proposed method is compared favorably to existing methods, in terms of both models sizes and accuracies for a wide range of applications including image classification, image compression and audio classification.

Publication forum classification

Field of science, Statistics Finland