Convolutional Gaussian Processes
We present a practical way of introducing convolutional structure into Gaussian processes, making them more suited to high-dimensional inputs like images. The main contribution of our work is the construction of an inter-domain inducing point approximation that is well-tailored to the convolutional kernel. This allows us to gain the generalisation benefit of a convolutional kernel, together with fast but accurate posterior inference. We investigate several variations of the convolutional kernel, and apply it to MNIST and CIFAR-10, which have both been known to be challenging for Gaussian processes. We also show how the marginal likelihood can be used to find an optimal weighting between convolutional and RBF kernels to further improve performance. We hope that this illustration of the usefulness of a marginal likelihood will help automate discovering architectures in larger models.
Code (4)
Tasks
Gaussian ProcessesSimilar Papers 제목 키워드 기반
Deep convolutional Gaussian processes
We propose deep convolutional Gaussian processes, a deep Gaussian process architecture with convolutional structure. The model is a principled Bayesian framework for detecting hierarchical combinations of local features …
ClassificationGaussian ProcessesGeneral Classificationimage-classification+1Graph Convolutional Gaussian Processes
We propose a novel Bayesian nonparametric method to learn translation-invariant relationships on non-Euclidean domains. The resulting graph convolutional Gaussian processes can be applied to problems in machine learning …
BIG-bench Machine LearningGaussian ProcessesSuperpixel Image ClassificationTranslationInterrelation of equivariant Gaussian processes and convolutional neural networks
Currently there exists rather promising new trend in machine leaning (ML) based on the relationship between neural networks (NN) and Gaussian processes (GP), including many related subtopics, e.g., signal propagation in …
Gaussian ProcessesSparse Orthogonal Variational Inference for Gaussian Processes
We introduce a new interpretation of sparse variational approximations for Gaussian processes using inducing points, which can lead to more scalable algorithms than previous methods. It is based on decomposing a Gaussian…
Gaussian ProcessesMulti-class ClassificationregressionVariational InferenceA Gaussian Process perspective on Convolutional Neural Networks
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 understan…
Gaussian Processes