A Gaussian Process perspective on Convolutional Neural Networks

2018/10/25 by Anastasia Borovykh, Borovykh, Anastasia · 2 citations
Computer Science · Physics and Astronomy · #Gaussian Processes and Bayesian Inference #Neural Networks and Applications #Statistical Mechanics and Entropy

paper · pdf · doi:10.48550/arxiv.1810.10798

Abstract

In this paper we cast the well-known convolutional neural network in a Gaussian process perspective. In this way we hope to gain additional insights into the performance of convolutional networks, in particular understand under what circumstances they tend to perform well and what assumptions are implicitly made in the network. While for fully-connected networks the properties of convergence to Gaussian processes have been studied extensively, little is known about situations in which the output from a convolutional network approaches a multivariate normal distribution.

Citations

• Additive Gaussian Processes
• ImageNet classification with deep convolutional neural networks

Cited by

• A review of uncertainty quantification in deep learning: Techniques, applications and challenges
• Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation
• Deep Convolutional Networks as shallow Gaussian Processes

Related

• Gaussian Process Behaviour in Wide Deep Neural Networks
• Deep Convolutional Networks as shallow Gaussian Processes
• A brief note on understanding neural networks as Gaussian processes
• GP-ConvCNP: Better Generalization for Convolutional Conditional Neural\n Processes on Time Series Data
• Understanding Convolutional Neural Networks