This survey is devoted to one of the central problems of Information Theory — the problem of determination of interdependence between coding rate and error probability exponent for different information transmission systems. The overview deals with memoryless systems of finite alphabet setting. It presents material complementary to the contents of the series of the most remarkable in Informatio...

We address the problem of training the free parameters of a statistical machine translation system. We show significant improvements over a state-of-the-art minimum error rate training baseline on a large ChineseEnglish translation task. We present novel training criteria based on maximum likelihood estimation and expected loss computation. Additionally, we compare the maximum a-posteriori deci...

A general criterion for the design of adaptive systems in digital communications called the statistical reference criterion is proposed. The criterion is based on imposition of the probability density function of the signal of interest at the output of the adaptive system, with its application to the scenario of highly powerful interferers being the main focus of this paper. The knowledge of th...

In this paper we propose ways to incorporate Machine Learning training outputs into a study of statistical significance. We describe these methods in supervised classification tasks using CNN and DNN output, unsupervised learning based on VAE. As use cases, consider two physical situations where are often used: high- p_T ...