LGNAMLJun 12, 2019

On regularization for a convolutional kernel in neural networks

arXiv:1906.04866v22 citations
Originality Incremental advance
AI Analysis

This work addresses a known bottleneck in deep learning for improving stability and generalization in CNNs, but it is incremental as it builds on existing regularization techniques.

The authors tackled the problem of exploding/vanishing gradients and poor generalization in convolutional neural networks by proposing a penalty function to constrain the singular values of convolutional kernels around 1, demonstrating effectiveness through numerical examples.

Convolutional neural network is an important model in deep learning. To avoid exploding/vanishing gradient problems and to improve the generalizability of a neural network, it is desirable to have a convolution operation that nearly preserves the norm, or to have the singular values of the transformation matrix corresponding to a convolutional kernel bounded around $1$. We propose a penalty function that can be used in the optimization of a convolutional neural network to constrain the singular values of the transformation matrix around $1$. We derive an algorithm to carry out the gradient descent minimization of this penalty function in terms of convolution kernels. Numerical examples are presented to demonstrate the effectiveness of the method.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes