FOLDS seminar: An Information Geometric Understanding of Deep Learning
/
Amy Gutmann Hall, Room 414
3333 Chestnut Street, Philadelphia, United States
Zoom link: https://upenn.zoom.us/j/98220304722 I will argue that properties of natural data are what predominantly make deep networks so effective. To that end, I will show that deep networks work well because of a characteristic structure in the space of learnable tasks. The input correlation matrix for typical tasks has a “sloppy” eigenspectrum where eigenvalues decay […]

