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.

News
All news
Science
25 Nov
RUDN chemists have found an effective catalyst for the synthesis of raw materials of the chemical industry

RUDN chemists have proven the effectiveness of metal complexes for catalysis of cyanhydrin production — substances important for the chemical industry. Chemists managed to achieve 96.3% of the reaction efficiency.

Science
17 Nov
RUDN University Chemists Obtained an Unusual Planar Nickel complex exhibiting Magnetic Properties

RUDN University chemists obtained a metal-containing complex with an unusual planar architecture. The unexpected structure was formed due to the spontaneous fixation of carbon dioxide from the air during the reaction. This compound exhibits unusual magnetic properties (spin glass behaviour). This can be useful for creating memory storage devices.

Science
14 Nov
RUDN chemists have shown how a new antitumor drug interacts with blood proteins

RUDN chemists investigated in detail the molecular mechanism of interaction of the newly created antitumor drug with blood proteins. The results will not only allow us to judge the effectiveness of the drug, but also are of interest from the point of view of understanding the mechanisms of action of such drugs.