A Gaussian Process perspective on Convolutional Neural Networks
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.
References in corpus (9)
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
- Deep Neural Networks as Gaussian Processes
- Conditional Time Series Forecasting with Convolutional Neural Networks
- Gaussian Process Kernels for Pattern Discovery and Extrapolation
- Additive Gaussian Processes
- Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
- Stochastic Gradient Descent as Approximate Bayesian Inference
- Stochastic Variational Deep Kernel Learning
- Steps Toward Deep Kernel Methods from Infinite Neural Networks
Cited by in corpus (8)
- 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
- Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
- Finite Versus Infinite Neural Networks: an Empirical Study
- A Fine-Grained Spectral Perspective on Neural Networks
- Towards NNGP-guided Neural Architecture Search
- A Bayesian Perspective on the Deep Image Prior