no code implementations • 18 Jun 2022 • Yuval Sieradzki, Nitzan Hodos, Gal Yehuda, Assaf Schuster
We show that a CFNN can approximate the indicator of a $d$-dimensional ball to arbitrary accuracy with only 2 layers and $\mathcal{O}(1)$ neurons, where a 2-layer deterministic network was shown to require $\Omega(e^d)$ neurons, an exponential improvement (arXiv:1610. 09887).
no code implementations • 10 Feb 2021 • Gal Yehuda, Amir Yehudayoff
We prove that at least $\Omega(n^{0. 51})$ hyperplanes are needed to slice all edges of the $n$-dimensional hypercube.
no code implementations • ICML 2020 • Gal Yehuda, Moshe Gabel, Assaf Schuster
Can deep neural networks learn to solve any task, and in particular problems of high complexity?