This volume contains the proceedings of the 2024 Spring Central Sectional Meeting, held at the University of Wisconsin-Milwaukee, Milwaukee, WI, on April 20-21, 2024. Our motivation for this volume is to fill the void of mathematical literature in the current developments of artificial intelligence, machine learning, deep learning, geometric deep learning, geometric information theory, etc. While there are some excellent mathematical ideas in such developments, the literature is flooded by papers and books written by computer scientists and engineers that lightly touch upon these subjects, thereby missing deep mathematical understanding. This makes it difficult for anyone who wants to enter such areas of research. What is missing in the literature is exactly the theoretical mathematical background in artificial intelligence and machine learning.
Mee Seong Im, John Hopkins University, Baltimore, MD, and Tony Shaska, Oakland University, Rochester, MI
ArticlesTony Shaska, Artificial neural networks on graded vector spacesMee Seong Im and Venkat R. Dasari, Computational complexity reduction of deep neural networksCarl Henrik Ek, Oisin Kim and Challenger Mishra, Calabi-Yau metrics through Grassmannian learning and Donaldson's algorithmJose Luis Crespo, Jaime Gutierrez and Angel Valle, Neural network design options for RNG's verificationMee Seong Im, Clement Kam and Caden Pici, Diagrammatics of informationIlias Kotsireas and Tony Shaska, A neurosymbolic framework for geometric reduction of binary formsYuta Kambe, Yota Maeda and Tristan Vaccon, Geometric generality of Transformer-based Grobner basis computationMee Seong Im, Semi-invariants of filtered quiver representations with at most two pathwaysElira Curri and Tony Shaska, Polynomials, Galois groups, and database-driven arithmetic