Рет қаралды 778
The classical universal approximation theorem (dating back to ~1999) is a foundational result, giving (part of) an answer to the question "why do neural networks work?" This is a brief introduction to our recent paper which proves some natural "dual" theorems on universal approximation, and in particular highlights a difference between deep and shallow neural networks.
Paper: arxiv.org/abs/...
Long version of this video: • [13 minutes] Universal...
This presentation was prepared as part of the acceptance of our paper to the Conference on Learning Theory 2020.