The paper investigates the complexity of training two-layer neural networks with different activation functions. It provides answers to several open questions and establishes the computational hardness of these problems for certain dimensions and activation functions.

https://arxiv.org/abs//2303.17045

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers