Comparative study of self-organizing map and deep self-organizing map using MATLAB
- 24 November 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1020-1023
Abstract
We are interested in testing the efficiency of different algorithm which are traditional SOM (self-organizing map) and new DSOM (deep self-organizing map) for image cataloging. DSOM consist of SOM and the sampling operator are arranged in the way to get the better result than the SOM which also include generating another 2D map, then it is fed into the next self-organizing layer this manner confined in order is gained, is made better in the higher layers. The making of DSOM is unique and we will test the accuracy and other parameters which are shown in this document. Experiment were carried out to see how DSOM influence the presentation.Keywords
This publication has 9 references indexed in Scilit:
- PHY-layer key exchange for wireless communication2015
- Chaotic neural network based pseudo-random sequence generator for cryptographic applications2015
- Identification of Visual Attention Regions in Machine Vision using Saliency Map2015
- Supervised Kohonen networks for classification problemsChemometrics and Intelligent Laboratory Systems, 2006
- A Self-Organizing Learning Array System for Power Quality Classification Based on Wavelet TransformIEEE Transactions on Power Delivery, 2005
- Host-based intrusion detection using self-organizing maps2003
- Handwritten digits recognition by a supervised Kohonen-like learning algorithm1991
- The self-organizing mapProceedings of the IEEE, 1990
- Neocognitron: A neural network model for a mechanism of visual pattern recognitionIEEE Transactions on Systems, Man, and Cybernetics, 1983