Publikációk

The efficient and accurate characterization of the robustness of neural networks to input perturbation is an important open problem. Many approaches exist including heuristic and exact (or complete) methods. Complete methods are expensive but their mathem

Zsolt János Viharos

Fooling a Complete Neural Network Verifier

Dániel Zombori

Balázs Bánhelyi

István Megyeri

Comprehensive analysis of the predictive validity of the university entrance score in Hungary

Roland Molontay

Traits versus Grades : The predictive power of psychological factors and pre-enrollment achievement measures on academic performance.

Séllei Beatrix

Stumphauser Nóra

Roland Molontay

The effect of central bank communication on sovereign bond yields: The case of Hungary

Barczikay Tamás

Comparing the effectiveness of two remedial mathematics courses using modern regression discontinuity techniques

Roland Molontay

Ensemble Bag-of-Audio-Words Representation Improves Paralinguistic Classification Accuracy

Gábor Gosztolya

Busa-Fekete Róbert

Deep Learning-Based Masonry Wall Image Analysis

HierarchyNet: Hierarchical CNN-Based Urban Building Classification