Deep Learning using Restricted Boltzmann Machines

Restricted Boltzmann machines (RBM) are probabilistic graphical models which are represented as stochastic neural networks. Increase in computational capacity and development of faster learning algorithms, led RBMs to become more useful for many machine learning problems. RBMs are the building blocks of many deep multilayer architectures like Deep Belief networks (DBN) and Deep Boltzmann Machines (DBM). Many machine learning algorithms like neural networks with a few hidden layers, Support Vector Machines (SVM), k-Nearest Neighbors (kNN), etc., are shallow architectures but DBNs and DBMs are deep architectures with many hidden layers. In this paper we have compared two different inference models with four different architectures. Experimental comparisons demonstrate that both the inference vary according to the number of hidden layers and number of neurons in it.