Machine Learning in Mathematics

Projects in Machine Learning and Pure Mathematics:

Advances in machine learning and data analysis in the last decade have made it possible to develop more sophisticated artificial intelligence systems which are being used in a broad range of applications.

We focus on such application to pure mathematics and especially on algebra and number theory. All our projects are based on explicit computational results through implementation and use of ML packages and methods. Many of our projects will use Pytorch, Tensorflow, Keras in developing and training models. Both supervised and unsupervised learning techniques are being used.

For those interested to contribute to this volume please contact me at
http://www.risat.org/shaska.html
or fill the following form.

Some of the projects we are currently working on or are interested to get going are:

Machine Learning and automorphism groups of curves
Using ML for superelliptic families of curves of high genus
Arithmetic in the moduli space: an ML approach
Data analysis of Calabi-Yau hypersurfaces via weighted heights
Machine learning and isogenies of Abelian varieties of dimension 2 and 3
Machine learning and toric varieties
Machine learning and cryptography

These projects will be summarized in a book which will be published by Springer as part of the Springer series in Data Sciences.

https://www.springer.com/series/13852

The deadline for articles will be sometime in the Fall 2023.