We investigate the mathematical capabilities of two iterations of ChatGPT (released 9-
January-2023 and 30-January-2023) and of GPT-4 by testing them on publicly available …

Proving mathematical theorems at the olympiad level represents a notable milestone in
human-level automated reasoning,,–, owing to their reputed difficulty among the world's best …

It is widely known that neural networks (NNs) are universal approximators of continuous
functions. However, a less known but powerful result is that a NN with a single hidden layer …

Symbolic regression, the task of predicting the mathematical expression of a function from
the observation of its values, is a difficult task which usually involves a two-step procedure …

We propose an online training procedure for a transformer-based automated theorem
prover. Our approach leverages a new search algorithm, HyperTree Proof Search (HTPS) …

Neuro-Symbolic Artificial Intelligence–the combination of symbolic methods with methods
that are based on artificial neural networks–has a long-standing history. In this article, we …

Machine learning (ML) has emerged as an indispensable methodology to describe,
discover, and predict complex physical phenomena that efficiently help us learn underlying …

Recently, many datasets have been proposed to test the systematic generalization ability of
neural networks. The companion baseline Transformers, typically trained with default hyper …

Currently deployed public-key cryptosystems will be vulnerable to attacks by full-scale
quantum computers. Consequently," quantum resistant" cryptosystems are in high demand …

Labeled data for imitation learning of theorem proving in large libraries of formalized
mathematics is scarce as such libraries require years of concentrated effort by human …