Mathematicians propose new way of using neural networks to work with noisy, high-dimensional data
(PHYSorg.com Mathematics)

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 article was published in the journal Artificial Intelligence.