53 citations · 53 across the 3 of their papers we have counts for
1 paper
Surbhi Goel, Varun Kanade, Adam Klivans +1
We give the first dimension-efficient algorithms for learning Rectified Linear Units (ReLUs), which are functions of the form $\mathbf{x} \mapsto \max(0, \mathbf{w} \cdot \mathbf{x…