Informational Neurobayesian Approach to Neural Networks Training. Opportunities and Prospects
Machine Learning
2017-12-05 v3
Abstract
A study of the classification problem in context of information theory is presented in the paper. Current research in that field is focused on optimisation and bayesian approach. Although that gives satisfying results, they require a vast amount of data and computations to train on. Authors propose a new concept named Informational Neurobayesian Approach (INA), which allows to solve the same problems, but requires significantly less training data as well as computational power. Experiments were conducted to compare its performance with the traditional one and the results showed that capacity of the INA is quite promising.
Keywords
Cite
@article{arxiv.1710.07264,
title = {Informational Neurobayesian Approach to Neural Networks Training. Opportunities and Prospects},
author = {Artem Artemov and Eugeny Lutsenko and Edward Ayunts and Ivan Bolokhov},
journal= {arXiv preprint arXiv:1710.07264},
year = {2017}
}
Comments
9 pages, 5 figures, 2 tables; corrected typos, mistake in a formula