12 citations · 18 across the 5 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
stat.ML2022
Bayesian Interpolation with Deep Linear Networks
Boris Hanin, Alexander Zlokapa
Characterizing how neural network depth, width, and dataset size jointly impact model quality is a central problem in deep learning theory. We give here a complete solution in the…
cs.LG2022★ 5 cited
Fault-Tolerant Neural Networks from Biological Error Correction Codes
Alexander Zlokapa, Andrew K. Tan, John M. Martyn +3
It has been an open question in deep learning if fault-tolerant computation is possible: can arbitrarily reliable computation be achieved using only unreliable neurons? In the grid…