Title:
DEEP RECEPTIVE FIELD NETWORKS
Document Type and Number:
WIPO Patent Application WO/2016/195496
Kind Code:
A3
Abstract:
The invention provides a method for recognition of information in digital image data, said method comprising a learning phase on a data set of example digital images having known information, and characteristics of categories are computed automatically from each example digital image and compared to its known category, said method comprises training a convolutional neural network comprising network parameters using said data set, in which via deep learning each layer of said convolutional neural network is represented by a linear decomposition of all filters as learned in each layer into basis functions.
Inventors:
JACOBSEN JÖRN-HENRIK (NL)
VAN GEMERT JOHANNES CHRISTIANUS (NL)
VAN DEN BOOMGAARD REINIER (NL)
LOU ZHONGYU (NL)
SMEULDERS ARNOLDUS WILHELMUS MARIA (NL)
VAN GEMERT JOHANNES CHRISTIANUS (NL)
VAN DEN BOOMGAARD REINIER (NL)
LOU ZHONGYU (NL)
SMEULDERS ARNOLDUS WILHELMUS MARIA (NL)
Application Number:
PCT/NL2016/050399
Publication Date:
January 12, 2017
Filing Date:
June 03, 2016
Export Citation:
Assignee:
UNIV AMSTERDAM (NL)
International Classes:
G06N99/00; G06V10/764
Foreign References:
| US20140355861A1 | 2014-12-04 | |||
| CN103996056A | 2014-08-20 |
Other References:
HONGLAK LEE ET AL: "Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations", PROCEEDINGS OF THE 26TH ANNUAL INTERNATIONAL CONFERENCE ON MACHINE LEARNING, ICML '09, 1 January 2009 (2009-01-01), New York, New York, USA, pages 1 - 8, XP055252280, ISBN: 978-1-60558-516-1, DOI: 10.1145/1553374.1553453
JOAN BRUNA ET AL: "Classification with Invariant Scattering Representations", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 6 December 2011 (2011-12-06), XP080555322
MARC'AURELIO RANZATO ET AL: "Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition", CVPR '07. IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION; 18-23 JUNE 2007; MINNEAPOLIS, MN, USA, IEEE, PISCATAWAY, NJ, USA, 1 June 2007 (2007-06-01), pages 1 - 8, XP031114414, ISBN: 978-1-4244-1179-5
SEBASTIAN BACH ET AL: "On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation", PLOS ONE, vol. 10, no. 7, 10 July 2015 (2015-07-10), US, pages 1 - 46, XP055228791, ISSN: 1932-6203, DOI: 10.1371/journal.pone.0130140
QUOC V LE ET AL: "Tiled convolutional neural networks", ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 23, 31 December 2010 (2010-12-31), pages 1279 - 1287, XP055168826, Retrieved from the Internet [retrieved on 20150210]
YUJIA LI ET AL: "Generative Moment Matching Networks", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 10 February 2015 (2015-02-10), XP080677536
KAREN SIMONYAN ET AL: "Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps", 20 December 2013 (2013-12-20), XP055226059, Retrieved from the Internet [retrieved on 20151105]
CHA ZHANG AND ZHENGYOU ZHANG ED - CHA ZHANG AND ZHENGYOU ZHANG: "Boosting-Based Face Detection and Adaptation", 1 September 2010, BOOSTING-BASED FACE DETECTION AND ADAPTATION (BOOK SERIES: SYNTHESIS LECTURES ON COMPUTER VISION), MORGAN & CLAYPOOL PUBLISHERS SERIES, PAGE(S) 140PP, ISBN: 978-1-60845-133-3, XP008130361
JOAN BRUNA ET AL: "Classification with Invariant Scattering Representations", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 6 December 2011 (2011-12-06), XP080555322
MARC'AURELIO RANZATO ET AL: "Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition", CVPR '07. IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION; 18-23 JUNE 2007; MINNEAPOLIS, MN, USA, IEEE, PISCATAWAY, NJ, USA, 1 June 2007 (2007-06-01), pages 1 - 8, XP031114414, ISBN: 978-1-4244-1179-5
SEBASTIAN BACH ET AL: "On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation", PLOS ONE, vol. 10, no. 7, 10 July 2015 (2015-07-10), US, pages 1 - 46, XP055228791, ISSN: 1932-6203, DOI: 10.1371/journal.pone.0130140
QUOC V LE ET AL: "Tiled convolutional neural networks", ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 23, 31 December 2010 (2010-12-31), pages 1279 - 1287, XP055168826, Retrieved from the Internet
YUJIA LI ET AL: "Generative Moment Matching Networks", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 10 February 2015 (2015-02-10), XP080677536
KAREN SIMONYAN ET AL: "Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps", 20 December 2013 (2013-12-20), XP055226059, Retrieved from the Internet
CHA ZHANG AND ZHENGYOU ZHANG ED - CHA ZHANG AND ZHENGYOU ZHANG: "Boosting-Based Face Detection and Adaptation", 1 September 2010, BOOSTING-BASED FACE DETECTION AND ADAPTATION (BOOK SERIES: SYNTHESIS LECTURES ON COMPUTER VISION), MORGAN & CLAYPOOL PUBLISHERS SERIES, PAGE(S) 140PP, ISBN: 978-1-60845-133-3, XP008130361
Attorney, Agent or Firm:
VAN ESSEN, Peter Augustinus (NL)
Download PDF:
Previous Patent: POLYKETIDES, METHODS OF USE AND PREPARATION
Next Patent: CHAIN CONVEYOR WITH FREE-ROTATING ROLLERS AND RETRACTABLE FLIGHTS
Next Patent: CHAIN CONVEYOR WITH FREE-ROTATING ROLLERS AND RETRACTABLE FLIGHTS