Deep Neural Networks: Selected Aspects of Learning and Application
Vladimir A. Golovko, Aliaksandr Kroshchanka, Egor Mikhno · Pattern Recognition and Image Analysis · 2021
Abstract Training methods for deep neural networks (DNNs) are analyzed. It is shown that maximizing the likelihood function of the distribution of the input data P(x) in the space of synaptic connections of a restricted Boltzmann machine (RBM) is equivalent to minimizing the cross-entropy (CE) of the network error function and minimizing the total mean squared error (MSE) of the network in the same space using linear neurons. The application of DNNs for the detection and recognition of productmarking is considered.