no code implementations • 2 Jul 2023 • Zsolt Zombori, Agapi Rissaki, Kristóf Szabó, Wolfgang Gatterbauer, Michael Benedikt
We consider learning a probabilistic classifier from partially-labelled supervision (inputs denoted with multiple possibilities) using standard neural architectures with a softmax as the final layer.
1 code implementation • 10 Mar 2023 • Michael Rawson, Christoph Wernhard, Zsolt Zombori, Wolfgang Bibel
Noting that lemmas are a key feature of mathematics, we engage in an investigation of the role of lemmas in automated theorem proving.
no code implementations • 27 Feb 2023 • András Kornai, Michael Bukatin, Zsolt Zombori
Currently, the dominant paradigm in AI safety is alignment with human values.
no code implementations • 5 Jul 2021 • Domonkos Czifra, Endre Csóka, Zsolt Zombori, Géza Makay
Our paper explores the game theoretic value of the 7-in-a-row game.
no code implementations • 31 May 2021 • Zsolt Zombori, Josef Urban, Miroslav Olšák
This leads us to explore how the entropy of the inference selection implemented via the neural network influences the proof search.
no code implementations • 25 Jun 2020 • Dániel Lévai, Zsolt Zombori
The Lottery Ticket Hypothesis postulates that a freshly initialized neural network contains a small subnetwork that can be trained in isolation to achieve similar performance as the full network.
1 code implementation • 15 Apr 2020 • Zsolt Zombori, Josef Urban, Chad E. Brown
We present a reinforcement learning toolkit for experiments with guiding automated theorem proving in the connection calculus.
1 code implementation • 30 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).
no code implementations • 28 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.