Pattern recognition is the science which helps in getting inferences from input data, usage of tools from machine learning and other algorithm designing. Neural networks techniques are popular in the field of pattern recognition. The importance of Neural Network is that it provides very powerful framework for representing mappings from several input variables to output variables. Self Organizing Map(SOM) technique has been applied in this work where implementation of one-D, two-D SOM has been done and modified algorithm of SOM has been proposed. In SOM unsupervised learning is employed where targets are not specified. Implementation of this has been done in C++. As a result of this modified algorithm of SOM performs better than using architecture of one-D map and two-D map networks for some sets of patterns.

1. Anil K. Jain , Robert P. W. Duin, Jianchang Mao, January 2000 ,"Statistical Pattern Recognition : a Review", IEEE Transactions on pattern analysis and machine intelligence, vol. 22, no. 1.
2. Teuvo Kohonen," march 1990 The Self Organizing Map", IEEE .
3. Chung-Chian Hsu, Shu-Han Lin, January 2012" Visualized analysis of mixed Numeric and Categorical data via Extended Self-Organizing Map", IEEE transactions on neural networks and learning systems, vol. 23, no. 1.
4. Valluru Rao, Hayagriva Rao, "C++ NEURAL NETWORKS AND FUZZY LOGIC",M&T Publishing, Edition 2nd.
5. Kelvin L. Preedy, Paul E. Keller, "ARTIFICIAL NEURAL NETWORKS AN INTRODUCTION" ,SPIE press edition 2005.
6. Indira Hirway,2003," Identification of BPL Households for Poverty Alleviation Programmes" Economic and Political Weekly, vol 38,no 45,pp 4803-4808.
7. Guoqiang Peter Zhang ,2000 "Neural Networks for Classification: A Survey" IEEE transactions on systems, man, and cybernetics—part c: applications and reviews, vol. 30, no. 4,.
8. R. Zurita-Milla, J. A. E. van Gijsel, N. A. S. Hamm, P. W. M. Augustijn, and A. Vrieling,, August 26, 2012, "Exploring Spatiotemporal Phenological Patterns and Trajectories Using Self-Organizing Maps", IEEE transactions on geoscience and remote sensing, accepted,.
9. Jayanta Kumar Basu, Debnath Bhattacharyya, Tai- Hoon Kim, April 2010," Use of Artificial Neural Network in Pattern Recognition", International Journal of Software Engineering and Its Applications, Vol. 4, No. 2.
10. Abhinandan De, Nirmalendu Chatterjee, April 2002," Recognition of Impulse Fault patterns in transformers using Kohonen's Self-Organizing Feature Map", IEEE transactions on power delivery, vol. 17, no. 2.

Som unsupervised Learning Machine Learning.