Holomorphic feedforward networks
Michael R. Douglas (Simons Center for Geometry and Physics)
Abstract: A very popular model in machine learning is the feedforward neural network (FFN). After a brief introduction to machine learning, we describe FFNs which represent sections of holomorphic line bundles on complex manifolds, and software which uses them to get numerical approximations to Ricci flat Kähler metrics.
algebraic geometrydifferential geometrysymplectic geometry
Audience: researchers in the topic
Series comments: To receive the series announcements, which include the
Zoom access password*, please register in
math.tecnico.ulisboa.pt/seminars/geolis/index.php?action=subscribe#subscribe
*the last announcement for a seminar is sent 2 hours before the seminar.
Geometria em Lisboa video channel: educast.fccn.pt/vod/channels/bu46oyq74
Organizers: | Jose Mourao*, Rosa Sena Dias, Sílvia Anjos* |
*contact for this listing |