Conference on the Mathematical Theory of Deep Neural Networks

Conference on the Mathematical Theory of Deep Neural Networks aim is to give visibility to these results, and those that will follow in their wake, to shed light on the properties of large, adaptive, distributed learning architectures, and to revolutionize our understanding of these systems.​​​ These advances in practical results, however, have far outpaced a formal understanding of these networks and their training. The dearth of rigorous analysis for these techniques limits their usefulness in addressing scientific questions and, more broadly, hinders the systematic design of the next generation of networks.