LGMLJul 4, 2023

Free energy of Bayesian Convolutional Neural Network with Skip Connection

arXiv:2307.01417v13 citationsh-index: 28
Originality Incremental advance
AI Analysis

This provides theoretical insights into the generalization properties of skip connections in Bayesian CNNs, which is incremental to existing ensemble-based explanations.

The paper tackles the problem of understanding how skip connections affect generalization in Bayesian Convolutional Neural Networks, showing that the upper bound of free energy and generalization error do not depend on overparametrization.

Since the success of Residual Network(ResNet), many of architectures of Convolutional Neural Networks(CNNs) have adopted skip connection. While the generalization performance of CNN with skip connection has been explained within the framework of Ensemble Learning, the dependency on the number of parameters have not been revealed. In this paper, we show that Bayesian free energy of Convolutional Neural Network both with and without skip connection in Bayesian learning. The upper bound of free energy of Bayesian CNN with skip connection does not depend on the oveparametrization and, the generalization error of Bayesian CNN has similar property.

Foundations

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

Your Notes