Application of deep belief networks in image semantic analysis and lossy compression for transmission

This paper presents a method of modern deep machine learning and its application in dimension reduction and lossy compression. Deep belief networks (or DBN´s), first proposed by Yoshua Bengio, are hierarchic, stochastic, neural networks with appropriate architecture and dedicated training algorithms. They are composed of layers, each one of which is a restricted Boltzmann machine (or RBM). There exists a consistent and well formulated mathematical model describing how DBN´s work. Such adaptive systems are used to learn presented training sets with or without a supervisor. In this paper, the knowledge acquired in this manner is used to classify handwritten digits, stored in a database; then compress and shape the explored, abstract information for the transmission purposes. The experiments performed show, that recognition error of order of less than 5% can be achieved by iterative training.