paper-with-me

Papers

Deep Gaussian Processes with Convolutional Kernels

2018-06-05 · Vinayak Kumar, Vaibhav Singh, P. K. Srijith, Andreas Damianou

Deep Gaussian processes (DGPs) provide a Bayesian non-parametric alternative to standard parametric deep learning models. A DGP is formed by stacking multiple GPs resulting in a well-regularized composition of functions. The Bayesian framework that equips the model with attractive properties, such as implicit capacity control and predictive uncertainty, makes it at the same time challenging to combine with a convolutional structure. This has hindered the application of DGPs in computer vision tasks, an area where deep parametric models (i.e. CNNs) have made breakthroughs. Standard kernels used in DGPs such as radial basis functions (RBFs) are insufficient for handling pixel variability in raw images. In this paper, we build on the recent convolutional GP to develop Convolutional DGP (CDGP) models which effectively capture image level features through the use of convolution kernels, therefore opening up the way for applying DGPs to computer vision tasks. Our model learns local spatial influence and outperforms strong GP based baselines on multi-class image classification. We also consider various constructions of convolution kernel over the image patches, analyze the computational trade-offs and provide an efficient framework for convolutional DGP models. The experimental results on image data such as MNIST, rectangles-image, CIFAR10 and Caltech101 demonstrate the effectiveness of the proposed approaches.

📄 PDF Abstract BibTeX arXiv:1806.01655

Code (0)

등록된 구현이 없습니다.

Tasks

Gaussian Processesimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Convolutional Gaussian Processes

2017-09-06 · NeurIPS 2017 12 · Mark van der Wilk, Carl Edward Rasmussen, James Hensman

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…

Gaussian Processes

Sentiment analysis with genetically evolved Gaussian kernels

2019-04-01 · Ibai Roman, Alexander Mendiburu, Roberto Santana, Jose A. Lozano

Sentiment analysis consists of evaluating opinions or statements from the analysis of text. Among the methods used to estimate the degree in which a text expresses a given sentiment, are those based on Gaussian Processes…

Gaussian ProcessesSentiment Analysis

Kriging via variably scaled kernels

2026-03-16 · Gianluca Audone, Francesco Marchetti, Emma Perracchione, Milvia Rossini arxiv

Classical Gaussian processes and Kriging models are commonly based on stationary kernels, whereby correlations between observations depend exclusively on the relative distance between scattered data. While this assumptio…

Gaussian Processes

Gaussian Process Kernels for Pattern Discovery and Extrapolation

2013-02-18 · Andrew Gordon Wilson, Ryan Prescott Adams

Gaussian processes are rich distributions over functions, which provide a Bayesian nonparametric approach to smoothing and interpolation. We introduce simple closed form kernels that can be used with Gaussian processes t…

Gaussian Processes

On power sum kernels on symmetric groups

2022-11-10 · Iskander Azangulov, Viacheslav Borovitskiy, Andrei Smolensky

In this note, we introduce a family of "power sum" kernels and the corresponding Gaussian processes on symmetric groups $\mathrm{S}_n$. Such processes are bi-invariant: the action of $\mathrm{S}_n$ on itself from both si…

Gaussian Processes