Login / Signup
Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks.
Mohammed Nowaz Rabbani Chowdhury
Shuai Zhang
Meng Wang
Sijia Liu
Pin-Yu Chen
Published in:
CoRR (2023)
Keyphrases
</>
convolutional neural networks
levels of abstraction
image patches
real time
bayesian networks
dynamic programming
response time
computationally efficient
routing protocol
computationally expensive
convolutional network