Video From 24w5297: Mathematics of Deep Learning
Salma Tarmoun, University of Pennsylvania
Tuesday, June 11, 2024 16:30 - 17:03
Gradient Descent and Attention Models: Challenges Posed by the Softmax Function
![](http://www.birs.ca/files/images/poster.png)
©2024 Banff International Research Station for Mathematical Innovation and Discovery. All Rights Reserved.