Multi-dimensional data classification is an important and challenging problem in many astro-particle experiments. Neural networks have proved to be versatile and robust in multi-dimensional data classification. In this article we shall study the classification of gamma from the hadrons for the MAGIC Experiment. Two neural networks have been used for the classification task. One is Multi-Layer Perceptron based on supervised learning and other is Self-Organising Map (SOM), which is based on unsupervised learning technique. The results have been shown and the possible ways of combining these networks have been proposed to yield better and faster classification results.
Physics analysis in astroparticle experiments requires the capability of recognizing new phenomena; in order to establish what is new, it is important to develop tools for automatic classification, able to compare the final result with data from different detectors. A typical example is the problem of Gamma Ray Burst detection, classification, and possible association to known sources: for this task physicists will need in the next years tools to associate data from optical databases, from satellite experiments (EGRET, GLAST), and from Cherenkov telescopes (MAGIC, HESS, CANGAROO, VERITAS).
Self-Organising Maps (SOMs) are effective tools in classification problems, and in recent years the even more powerful Dynamic Growing Neural Networks, a variant of SOMs, have been developed. Automatic Classification (also called clustering) is an important and difficult problem in many Astrophysical experiments, for instance, Gamma Ray Burst classification, or gamma-hadron separation. After a brief introduction to classification problem, we discuss Self-Organising Maps in section 2. Section 3 discusses with various models of growing neural networks and finally in section 4 we discuss the research perspectives in growing neural networks for efficient classification in astrophysical problems.