190   Artículos

 
en línea
Dmitry Namiot,Eugene Ilyushin     Pág. 60 - 69
Revista: International Journal of Open Information Technologies    Formato: Electrónico

 
en línea
Dmitry Yakupov,Dmitry Namiot     Pág. 128 - 155
Recommender systems were one of the first mass applications of data analysis in various fields. The reason is their final result (recommendations) that is transparent to end users and clear metrics for measuring the quality of their work. End-users can a... ver más
Revista: International Journal of Open Information Technologies    Formato: Electrónico

 
en línea
Dmitry Namiot,Eugene Ilyushin     Pág. 101 - 118
This article, written for the Robust Machine Learning Curriculum, discusses the so-called Generative Models in Machine Learning. Generative models learn the distribution of data from some sample data set and then can generate (create) new data instances.... ver más
Revista: International Journal of Open Information Technologies    Formato: Electrónico

 
en línea
Dmitry Namiot,Eugene Ilyushin,Oleg Pilipenko     Pág. 119 - 127
The development and use of artificial intelligence systems (machine learning) in critical areas (avionics, autonomous movement, etc.) inevitably raise the question of the reliability of the software used. Trusted computing systems have been around for a ... ver más
Revista: International Journal of Open Information Technologies    Formato: Electrónico

 
en línea
Artem Makhankin,Dmitry Namiot     Pág. 133 - 140
The purpose of this work is to create a clear visualization of passenger traffic for the Moscow metro system. The paper provides preliminary preparation of metadata from the entrance groups of turnstiles located at Moscow metro stations and visual analys... ver más
Revista: International Journal of Open Information Technologies    Formato: Electrónico

 
en línea
Huayu Li,Dmitry Namiot     Pág. 9 - 16
This article provides a detailed survey of the so-called adversarial attacks and defenses. These are special modifications to the input data of machine learning systems that are designed to cause machine learning systems to work incor... ver más
Revista: International Journal of Open Information Technologies    Formato: Electrónico

 
en línea
Dmitry Namiot,Eugene Ilyushin,Ivan Chizhov     Pág. 30 - 34
The paper deals with the issues of formal verification of machine learning systems. With the growth of the introduction of systems based on machine learning in the so-called critical systems (systems with a very high cost of erroneous decisions and actio... ver más
Revista: International Journal of Open Information Technologies    Formato: Electrónico

 
en línea
Dmitry Namiot,Vladimir Sukhomlin     Pág. 99 - 103
The paper describes the model of hyper-local Internet. This refers to a set of Internet resources that are, to one degree or another, relevant (useful) for users located in a certain limited area. At the same time, such a network is not visible outside t... ver más
Revista: International Journal of Open Information Technologies    Formato: Electrónico

 
en línea
Eugene Ilyushin,Dmitry Namiot,Ivan Chizhov     Pág. 17 - 22
The paper deals with the problem of adversarial attacks on machine learning systems. Such attacks are understood as special actions on the elements of the machine learning pipeline (training data, the model itself, test data) in order to either achieve t... ver más
Revista: International Journal of Open Information Technologies    Formato: Electrónico

 
en línea
Oleg Pokusaev,Dmitry Namiot,Alexander Chekmarev     Pág. 42 - 46
Digital methods of recording trips in transport today allow a quite accurate measurement of transport behavior. Digital payment tools and the development of telecommunications make it possible, in particular, to have complete information about passenger ... ver más
Revista: International Journal of Open Information Technologies    Formato: Electrónico

« Anterior     Página: 1 de 9     Siguiente »