Graphs of Random Matrices in Deep Learning

Explore the intersection of random matrix theory and deep learning in this 25-minute lecture by Cristopher Salvi from Imperial College London. Delve into the fascinating world of graphs of random matrices and their applications in neural networks, gaining insights into how these mathematical structures influence the behavior and performance of deep learning models. Presented as part of the Fourth Symposium on Machine Learning and Dynamical Systems at the Fields Institute, this talk offers a unique perspective on the theoretical foundations underpinning modern machine learning algorithms.