16 citations · 18 across the 3 of their papers we have counts for
5 papers
Mode Combinability: Exploring Convex Combinations of Permutation Aligned Models
Adrián Csiszárik, Melinda F. Kiss, Péter Kőrösi-Szabó +3
We explore element-wise convex combinations of two permutation-aligned neural network parameter vectors and of size . We conduct extensive experiments by examining v…
Similarity and Matching of Neural Network Representations
Adrián Csiszárik, Péter Kőrösi-Szabó, Ákos K. Matszangosz +2
We employ a toolset -- dubbed Dr. Frankenstein -- to analyse the similarity of representations in deep neural networks. With this toolset, we aim to match the activations on given…
Negative Sampling in Variational Autoencoders
Adrián Csiszárik, Beatrix Benkő, Dániel Varga
Modern deep artificial neural networks have achieved great success in the domain of computer vision and beyond. However, their application to many real-world tasks is undermined by…
Towards Finding Longer Proofs
Zsolt Zombori, Adrián Csiszárik, Henryk Michalewski +2
We present a reinforcement learning (RL) based guidance system for automated theorem proving geared towards Finding Longer Proofs (FLoP). Unlike most learning based approaches, we…
Gradient Regularization Improves Accuracy of Discriminative Models
Dániel Varga, Adrián Csiszárik, Zsolt Zombori
Regularizing the gradient norm of the output of a neural network with respect to its inputs is a powerful technique, rediscovered several times. This paper presents evidence that g…