Automated Adjustment System of Restricted Boltzmann Machine

UDC 004.85(045) DOI:10.18372/1990-5548.60.13814
V. M. Sineglazov, O. R. Tofaniuk. Automated Adjustment System of Restricted Boltzmann Machine, N 2(60) – Kyiv: NAU, 2019. – pp. 43–52.
In this paper the problem of learning the deep believe neural network with help of a restricted Boltzmann machine and the choose of an optimal algorithm for its training is considered. Different algorithms of restricted Boltzmann machine training, which are used for the pre-training of deep believe neural network, are considered, in order to increase the efficiency of this network and further solve the problem of structural-parametric synthesis of deep believe neural network. This task represents the task of justifying the necessity of optimal choice of the restricted Boltzmann machine adjustment algorithm for improving the quality of training of the neural network. To solve this problem, it is suggested to create an automated adjustment system of restricted Boltzmann machine, which choose the optimal training algorithm for this neural network.
Index Terms—Deep Believe Network; Restricted Boltzmann Machine; Contrastive Divergence; Persistent Contrastive Divergence; Parallel Tempering.
References: 16 names.