eprintid: 3594
rev_number: 6
eprint_status: archive
userid: 69
dir: disk0/00/00/35/94
datestamp: 2016-11-14 11:18:52
lastmod: 2016-11-14 11:18:52
status_changed: 2016-11-14 11:18:52
type: book_section
metadata_visibility: show
creators_name: Giuffrida, Mario Valerio
creators_name: Tsaftaris, Sotirios A.
creators_id: valerio.giuffrida@imtlucca.it
creators_id: 
title: Rotation-Invariant Restricted Boltzmann Machine Using Shared Gradient Filters
ispublished: pub
subjects: QA76
subjects: T1
divisions: CSA
full_text_status: none
abstract: Finding suitable features has been an essential problem in computer vision. We focus on Restricted Boltzmann Machines (RBMs), which, despite their versatility, cannot accommodate transformations that may occur in the scene. As a result, several approaches have been proposed that consider a set of transformations, which are used to either augment the training set or transform the actual learned filters. In this paper, we propose the Explicit Rotation-Invariant Restricted Boltzmann Machine, which exploits prior information coming from the dominant orientation of images. Our model extends the standard RBM, by adding a suitable number of weight matrices, associated with each dominant gradient. We show that our approach is able to learn rotation-invariant features, comparing it with the classic formulation of RBM on the MNIST benchmark dataset. Overall, requiring less hidden units, our method learns compact features, which are robust to rotations.
date: 2016
date_type: published
series: Lecture Notes in Computer Science
number: 9887
publisher: Springer International Publishing
pagerange: 480-488
pages: 9
id_number: 10.1007/978-3-319-44781-0_57
refereed: TRUE
isbn: 978-3-319-44780-3
book_title: Artificial Neural Networks and Machine Learning – ICANN 2016 25th. International Conference on Artificial Neural Networks, Barcelona, Spain, September 6-9, 2016, Proceedings, Part II
official_url: http://dx.doi.org/10.1007/978-3-319-44781-0_57
citation:   Giuffrida, Mario Valerio and Tsaftaris, Sotirios A.  Rotation-Invariant Restricted Boltzmann Machine Using Shared Gradient Filters.   In:  Artificial Neural Networks and Machine Learning – ICANN 2016 25th. International Conference on Artificial Neural Networks, Barcelona, Spain, September 6-9, 2016, Proceedings, Part II.   Lecture Notes in Computer Science  (9887).  Springer International Publishing, pp. 480-488.  ISBN 978-3-319-44780-3      (2016)