Deep Gaussian Processes with Convolutional Kernels

Abstract

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.

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Deep Gaussian Processes for Regression using Approximate Expectation Propagation
• Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
• Random Feature Expansions for Deep Gaussian Processes
• Convolutional Gaussian Processes
• Nested Variational Compression in Deep Gaussian Processes
• Calibrating Deep Convolutional Gaussian Processes

Cited by in corpus (8)

• On Exact Computation with an Infinitely Wide Neural Net
• Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation
• When Gaussian Process Meets Big Data: A Review of Scalable GPs
• Deep Convolutional Networks as shallow Gaussian Processes
• Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
• A Fine-Grained Spectral Perspective on Neural Networks
• Probabilistic Numeric Convolutional Neural Networks
• Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit