Open AccessDEPENDENCE OF THE INITIAL DISTRIBUTION OF WEIGHTS ON THE TRAINING EFFICIENCY OF DEEP NEURAL NETWORKS
Author(s) -
I. P. Kolganov
Publication year - 2020
Publication title -
prikladnaâ matematika i fundamentalʹnaâ informatika
Language(s) - English
Resource type - Journals
ISSN - 2311-4908
DOI - 10.25206/2311-4908-2020-7-4-24-33
Subject(s) - training (meteorology) , artificial neural network , computation , computer science , training set , set (abstract data type) , data set , mean squared error , regression , distribution (mathematics) , deep neural networks , artificial intelligence , algorithm , mathematics , machine learning , statistics , physics , meteorology , programming language , mathematical analysis
The article is devoted to the influence of the initial weights, during training. Data set is generated by computation methods based on the Lennard-Jones equation. The trained regression model predicts interaction energy between two particles. The sum square error is chosen as the criterion for evaluating of the efficiency. The article presents graphs of the efficiency indicator from the number of training steps, for different regimes. The data obtained in this article will allow to analyze the possibility of fast method designing for complex models.