Deep Convolutional Transform Learning -- Extended version

This work introduces a new unsupervised representation learning technique called Deep Convolutional Transform Learning (DCTL). By stacking convolutional transforms, our approach is able to learn a set of independent kernels at different layers. The features extracted in an unsupervised manner can th...

Full description

Saved in:
Bibliographic Details
Main Authors Maggu, Jyoti, Majumdar, Angshul, Chouzenoux, Emilie, Chierchia, Giovanni
Format Journal Article
LanguageEnglish
Published 02.10.2020
Subjects
Computer Science - Learning
Statistics - Machine Learning
Online AccessGet full text
DOI10.48550/arxiv.2010.01011

Cover

More Information
Summary:This work introduces a new unsupervised representation learning technique called Deep Convolutional Transform Learning (DCTL). By stacking convolutional transforms, our approach is able to learn a set of independent kernels at different layers. The features extracted in an unsupervised manner can then be used to perform machine learning tasks, such as classification and clustering. The learning technique relies on a well-sounded alternating proximal minimization scheme with established convergence guarantees. Our experimental results show that the proposed DCTL technique outperforms its shallow version CTL, on several benchmark datasets.
DOI:10.48550/arxiv.2010.01011