3
Mathematicians from RUDN University and the Free University of Berlin proposed a new way of using neural networks for working with noisy high-dimensional data

Mathematicians from RUDN University and the Free University of Berlin proposed a new way of using neural networks for working with noisy high-dimensional data

Mathematicians from RUDN University and the Free University of Berlin have proposed a new approach to studying the probability distributions of observed data using artificial neural networks. The new approach works better with so-called outliers, i.e. input data objects that deviate significantly from the overall sample.

The restoration of the probability distribution of observed data by artificial neural networks is the most important part of machine learning. The probability distribution not only allows us to predict the behaviour of the system under study, but also to quantify the uncertainty with which forecasts are made. The main difficulty is that, as a rule, only the data are observed, but their exact probability distributions are not available. To solve this problem, Bayesian and other similar approximate methods are used. But their use increases the complexity of a neural network and therefore makes its training more complicated.

RUDN University and the Free University of Berlin mathematicians used deterministic weights in neural networks, which would help overcome the limitations of Bayesian methods. They developed a formula that allows one to correctly estimate the variance of the distribution of observed data. The proposed model was tested on different data: synthetic and real; on data containing outliers and on data from which the outliers were removed. The new method allows restoration of probability distributions with accuracy previously unachievable.

The mathematicians of RUDN University and the Free University of Berlin used deterministic weights for neural networks and used the networks outputs to encode the distribution of latent variables for the desired marginal distribution. An analysis of the training dynamics of such networks allowed them to obtain a formula that correctly estimates the variance of observed data, despite the presence of outliers in the data. The proposed model was tested on different data: synthetic and real. The new method allows restoring probability distributions with higher accuracy compared with other modern methods. Accuracy was assessed using the AUC method (area under the curve is the area under the graph that allows making assessment of the mean square error of the predictions depending on the sample size estimated by the network as “reliable”; the higher the AUC score, the better the predictions).

The article was published in the journal Artificial Intelligence.

30 Jan 2018
The conference on international arbitration, where law students from European universities simulate court proceedings and alternately defend the interests of the respondent and the orator.
912
Student's Scientific Initiatives View all
03 Nov 2017
June 22 - 26, 2017 in Barnaul, Altai State University, took place the Summer Academy of the BRICS Youth Assembly, an international event that brought together representatives of different countries
1226
Similar newsletter View all
21 Oct
RUDN University mathematician determined the conditions for the coexistence of three species in the wild

RUDN University mathematician together with colleagues from India and France for the first time studied in detail the system of coexistence of three species of living creatures in the wild. The results help to understand what parameters determine the extinction andли survivalof species, and how the number of species changes in space and time.

24
21 Oct
RUDN University Chemist Created Coordination Polymers Films with up to 99.99% antibacterial efficiency

RUDN University chemist with his colleagues from Portugal has developed two types of coating based on new coordination polymers with silver. Both compounds were successfully tested against four common pathogens.

21
21 Oct
RUDN scientists have improved titanium dental implants with graphene nanosloyers

RUDN researchers have created and tested a method for processing titanium dental implants. It turned out that theanoslos of graphene on the surface of titanium improve its interaction with stem cells,which are placed on the implant so that it better "takes root".Thanks to this method ofprocessing, stem cells are better kept on the surface, multiply and turn into the desired cells.

23
Similar newsletter View all