Search Results for author: Adrián Csiszárik

Found 6 papers, 2 papers with code

Mode Combinability: Exploring Convex Combinations of Permutation Aligned Models

no code implementations22 Aug 2023 Adrián Csiszárik, Melinda F. Kiss, Péter Kőrösi-Szabó, Márton Muntag, Gergely Papp, Dániel Varga

We explore element-wise convex combinations of two permutation-aligned neural network parameter vectors $\Theta_A$ and $\Theta_B$ of size $d$.

Linear Mode Connectivity Re-basin

Similarity and Matching of Neural Network Representations

1 code implementation NeurIPS 2021 Adrián Csiszárik, Péter Kőrösi-Szabó, Ákos K. Matszangosz, Gergely Papp, Dániel Varga

With this toolset, we aim to match the activations on given layers of two trained neural networks by joining them with a stitching layer.

Visualizing Transfer Learning

no code implementations15 Jul 2020 Róbert Szabó, Dániel Katona, Márton Csillag, Adrián Csiszárik, Dániel Varga

We provide visualizations of individual neurons of a deep image recognition network during the temporal process of transfer learning.

Transfer Learning

Negative Sampling in Variational Autoencoders

no code implementations7 Oct 2019 Adrián Csiszárik, Beatrix Benkő, Dániel Varga

Modern deep artificial neural networks have achieved great success in the domain of computer vision and beyond.

Density Estimation Out-of-Distribution Generalization +1

Towards Finding Longer Proofs

1 code implementation30 May 2019 Zsolt Zombori, Adrián Csiszárik, Henryk Michalewski, Cezary Kaliszyk, Josef Urban

We present a reinforcement learning (RL) based guidance system for automated theorem proving geared towards Finding Longer Proofs (FLoP).

Automated Theorem Proving reinforcement-learning +1

Gradient Regularization Improves Accuracy of Discriminative Models

no code implementations28 Dec 2017 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.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.