Deep Learning Algorithms and Their Applications in the Perception Problem

Abstract

The objective of this paper is to summarize a comparative account of unsupervised and supervised deep learning models and their applications. The design of a model system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, selection of training and test samples and performance evaluation. Classification plays a vital role in deep learning algorithms and we found that, though the error backpropagation learning algorithm as provided by supervised learning model, is very efficient for a number of non-linear real-time problems, KSOM of unsupervised learning model, offers efficient solution and classification in the perception problem.