4 citations · 4 across the 3 of their papers we have counts for
3 papers
cs.AI2022
Adversarial Learning to Reason in an Arbitrary Logic
Stanisław J. Purgał, Cezary Kaliszyk
Existing approaches to learning to prove theorems focus on particular logics and datasets. In this work, we propose Monte-Carlo simulations guided by reinforcement learning that ca…
cs.LG2021★ 4 cited
A Study of Continuous Vector Representationsfor Theorem Proving
Stanisław Purgał, Julian Parsert, Cezary Kaliszyk
Applying machine learning to mathematical terms and formulas requires a suitable representation of formulas that is adequate for AI methods. In this paper, we develop an encoding t…
cs.LG2020
Improving Expressivity of Graph Neural Networks
Stanisław Purgał
We propose a Graph Neural Network with greater expressive power than commonly used GNNs - not constrained to only differentiate between graphs that Weisfeiler-Lehman test recognize…