Michael R. Douglas (Harvard CMSA)

New Technologies in Mathematics Seminar Speaker: Riccardo Zecchina (Bocconi University) Title: Local learning needs dendrites Abstract: I will present a learning scheme for recurrent networks in which nonlinear dendrites enable learning by generating and stabilizing task-relevant attractors within a representation manifold. The scheme is local in space and time and matches the performance of backpropagation […]

New Technologies in Mathematics Seminar Speaker: Xinjie He, UCLA Title: The IEANTN Project: Automation and Mathematical Understanding Abstract: Explicit analytic number theory combines conceptual arguments with extensive bookkeeping and numerical computation, often drawing on long chains of results across many papers. The Integrated Explicit Analytic Number Theory Network (IEANTN) aims to organize this literature into […]