Math of Deep Learning Seminar: Michael Eickenberg


Title: A greedy and local perspective on neural network training and parallelization

Abstract: In this talk, Michael will show that meaningful object recognition accuracy can be achieved without end-to-end backpropagation, using only progressive linearization of object category as training objective. The approach used - greedy and local optimization - leads to an immediate application in parallelizing the training of deep networks.

Will present both of these ideas, based on the papers as well as other recent developments in local parallel training.


If you would like to attend, please email for the Zoom link.

The agenda of this meeting is empty