Deep Convolutional Neural Networks with Zero-Padding: Feature Extraction and Learning
Abstract
This paper studies the performance of deep convolutional neural networks (DCNNs) with zero-padding in feature extraction and learning. After verifying the roles of zero-padding in enabling translation-equivalence, and pooling in its translation-invariance driven nature, we show that with similar number of free parameters, any deep fully connected networks (DFCNs) can be represented by DCNNs with zero-padding. This demonstrates that DCNNs with zero-padding is essentially better than DFCNs in feature extraction. Consequently, we derive universal consistency of DCNNs with zero-padding and show its translation-invariance in the learning process. All our theoretical results are verified by numerical experiments including both toy simulations and real-data running.
Cite
@article{arxiv.2307.16203,
title = {Deep Convolutional Neural Networks with Zero-Padding: Feature Extraction and Learning},
author = {Zhi Han and Baichen Liu and Shao-Bo Lin and Ding-Xuan Zhou},
journal= {arXiv preprint arXiv:2307.16203},
year = {2023}
}
Comments
18