The minimal width of neural networks and immersions of real projective space
The minimal width of deep neural networks that can approximate all continuous functions from $\mathbb{R}^n$ to $\mathbb{R}^m$ in the topology of uniform convergence on compact subsets is investigated, suggesting an intriguing connection between the approximation theory of neural networks and differential topology.
Bao-Zhi Chu, Ben Weinkove
· 0 citations