Error estimate for a universal function approximator of ReLU network with a local connection
Machine Learning
2020-09-04 v1 Information Theory
math.IT
Machine Learning
Abstract
Neural networks have shown high successful performance in a wide range of tasks, but further studies are needed to improve its performance. We analyze the approximation error of the specific neural network architecture with a local connection and higher application than one with the full connection because the local-connected network can be used to explain diverse neural networks such as CNNs. Our error estimate depends on two parameters: one controlling the depth of the hidden layer, and the other, the width of the hidden layers.
Cite
@article{arxiv.2009.01461,
title = {Error estimate for a universal function approximator of ReLU network with a local connection},
author = {Jae-Mo Kang and Sunghwan Moon},
journal= {arXiv preprint arXiv:2009.01461},
year = {2020}
}