- Title
- A convolutional recursive modified Self Organizing Map for handwritten digits recognition
- Creator
- Mohebi, Ehsan; Bagirov, Adil
- Date
- 2014
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/70124
- Identifier
- vital:6492
- Identifier
-
https://doi.org/10.1016/j.neunet.2014.08.001
- Identifier
- ISSN:0893-6080
- Abstract
- It is well known that the handwritten digits recognition is a challenging problem. Different classification algorithms have been applied to solve it. Among them, the Self Organizing Maps (SOM) produced promising results. In this paper, first we introduce a Modified SOM for the vector quantization problem with improved initialization process and topology preservation. Then we develop a Convolutional Recursive Modified SOM and apply it to the problem of handwritten digits recognition. The computational results obtained using the well known MNIST dataset demonstrate the superiority of the proposed algorithm over the existing SOM-based algorithms.
- Publisher
- Elsevier Ltd
- Relation
- Neural Networks Vol. 60, no. (2014), p. 104-118; http://purl.org/au-research/grants/arc/DP140103213
- Rights
- © 2014 Elsevier Ltd.
- Rights
- This metadata is freely available under a CCO license
- Subject
- MD Multidisciplinary; Convolutional neural network; Recursive neural network; Self Organizing Maps; SOM initialization; SOM topology; Vector quantization; Algorithms; Convolution; Topology; Classification algorithm; Computational results; Handwritten digits recognition; Recursive neural networks; Topology preservation; Self organizing maps
- Reviewed
- Hits: 3275
- Visitors: 3109
- Downloads: 3
| Thumbnail | File | Description | Size | Format |
|---|