Sanjeev Arora | Opening the black box: Toward mathematical understanding of deep learning

On August 24-25, 2020 the CMSA hosted our sixth annual Conference on Big Data. The Conference featured many speakers from the Harvard community as well as scholars from across the globe, with talks focusing on computer science, statistics, math and physics, and economics.

Speaker: Sanjeev Arora

Title: Opening the black box: Toward mathematical understanding of deep learning

Abstract: Deep learning has led to significant progress on old problems of AI and machine learning. But mathematical understanding of this technique is still lacking. The talk will survey the main mathematical questions and the hurdles the confront researchers trying to answer them. It will also highlight the inadequacies of traditional optimization-based language for thinking about deep learning.

[cosmonicefellow]

About vignette 4, does it mean for any data that can be represented as vectors or matrices of the same dimensions, you can mix them to train a neural network?