inria-00104833, version 1
A Fast Learning Strategy Using Pattern Selection for Feedforward Neural Networks
Tenth International Workshop on Frontiers in Handwriting Recognition 2006 - IWFHR'10 (2006) 6
- 1:
-
INRIA – CNRS : UMR7503 – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL) France
Bibliographic reference
- Type of document: Peer-reviewed conferences/proceedings
- Domain:
Computer Science/Computer Vision and Pattern Recognition Computer Science/Document and Text Processing - Title: A Fast Learning Strategy Using Pattern Selection for Feedforward Neural Networks
- Abstract: Intelligent pattern selection is an active learning strategy where the classifiers select during training the most informative patterns. This paper investigates such a strategy where the informativeness of a pattern is measured as the approximation error produced by the classifier. The algorithm builds the training corpus starting from a small randomly chosen initial dataset and new patterns are added to the learning corpus based on their error sensitivity. The training dataset expansion is based on the selection of the most erroneous patterns. Our experimental results on MNIST 1 separated digit dataset show that only 3.26%of training data are sufficient for training purpose without decreasing the performance (98.36%) of the resulting neural classifier.
- ACM Classification:
I.: Computing Methodologies/I.5: PATTERN RECOGNITION I.: Computing Methodologies/I.7: DOCUMENT AND TEXT PROCESSING - Full text language: English
- Publication date: 2006-10-23
- Audience: international
- Conference title: Tenth International Workshop on Frontiers in Handwriting Recognition 2006 - IWFHR'10
- Conference city: La Baule
- Country: France
- Conference date: 2006-10-23
- Conference date (end): 2006-10-26
- Organizer: Université de Rennes 1
- Scientific editor(s): Guy Lorette
- Commercial editor: Suvisoft
- Pagination: 6
- Keywords: Pattern selection – incremental learning – handwritten digit recognition – neural networks – support vector machines
- Comment: http://www.suvisoft.com
- Contract, financing: Université de Rennes 1
Attached file list to this document:
![]() |
![]() |
cr1109240398082.pdf |
- inria-00104833, version 1
- http://hal.inria.fr/inria-00104833
- oai:hal.inria.fr:inria-00104833
- From:
- Submitted on: Monday, 9 October 2006 14:59:40
- Updated on: Wednesday, 8 December 2010 17:24:19




Associated documents
Export