Free energy of Bayesian Convolutional Neural Network with Skip Connection

2023/07/04 by Shuya Nagayasu, Sumio Watanabe, Nagayasu, Shuya +1 · 1 citation
Computer Science · #Neural Networks and Applications #Advanced Neural Network Applications #Face and Expression Recognition

paper · pdf · doi:10.48550/arxiv.2307.01417

Abstract

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.

Cited by

• ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Space

Related

• Bayesian Free Energy of Deep ReLU Neural Network in Overparametrized Cases
• A Kernel Perspective of Skip Connections in Convolutional Networks
• Algebraic Representations for Faster Predictions in Convolutional Neural Networks
• ResNet: Enabling Deep Convolutional Neural Networks through Residual Learning
• Bayesian Deep Convolutional Networks with Many Channels are Gaussian\n Processes