5 citations · 7 across the 7 of their papers we have counts for
8 papers
Evaluating SageMath-Augmented LLM Agents for Computational and Experimental Mathematics
Pavel Snopov, German Magai
Recent advances in AI for Mathematics have focused largely on autoformalization and theorem proving, leaving the role of Computer Algebra Systems (CAS) in agentic LLM workflows und…
Sheaf theory: from deep geometry to deep learning
Anton Ayzenberg, Thomas Gebhart, German Magai +1
This paper provides an overview of the applications of sheaf theory in deep learning, data science, and computer science in general. The primary text of this work serves as a frien…
ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain
Guillermo Bernárdez, Lev Telyatnikov, Marco Montagna +70
This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learnin…
Coverings by open and closed hemispheres
Anton Ayzenberg, Maxim Beketov, German Magai
In this paper we study the nerves of two types of coverings of a sphere : (1) coverings by open hemispheres; (2) antipodal coverings by closed hemispheres. In the first ca…
ICML 2023 Topological Deep Learning Challenge : Design and Results
Mathilde Papillon, Mustafa Hajij, Helen Jenne +53
This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning. The competi…
Global cognitive graph properties dynamics of hippocampal formation
Konstantin Sorokin, Andrey Zaitsew, Aleksandr Levin +3
In the present study we have used a set of methods and metrics to build a graph of relative neural connections in a hippocampus of a rodent. A set of graphs was built on top of tim…
Deep neural networks architectures from the perspective of manifold learning
German Magai
Despite significant advances in the field of deep learning in ap-plications to various areas, an explanation of the learning pro-cess of neural network models remains an important…
Topology and geometry of data manifold in deep learning
German Magai, Anton Ayzenberg
Despite significant advances in the field of deep learning in applications to various fields, explaining the inner processes of deep learning models remains an important and open q…