Improved Learning of One-hidden-layer Convolutional Neural Networks with Overlaps
Machine Learning
2018-06-05 v2 Artificial Intelligence
Computer Vision and Pattern Recognition
Data Structures and Algorithms
Machine Learning
Abstract
We propose a new algorithm to learn a one-hidden-layer convolutional neural network where both the convolutional weights and the outputs weights are parameters to be learned. Our algorithm works for a general class of (potentially overlapping) patches, including commonly used structures for computer vision tasks. Our algorithm draws ideas from (1) isotonic regression for learning neural networks and (2) landscape analysis of non-convex matrix factorization problems. We believe these findings may inspire further development in designing provable algorithms for learning neural networks and other complex models.
Cite
@article{arxiv.1805.07798,
title = {Improved Learning of One-hidden-layer Convolutional Neural Networks with Overlaps},
author = {Simon S. Du and Surbhi Goel},
journal= {arXiv preprint arXiv:1805.07798},
year = {2018}
}