Deep Multiple Kernel Learning

Abstract

Deep learning methods have predominantly been applied to large artificial neural networks. Despite their state-of-the-art performance, these large networks typically do not generalize well to datasets with limited sample sizes. In this paper, we take a different approach by learning multiple layers of kernels. We combine kernels at each layer and then optimize over an estimate of the support vector machine leave-one-out error rather than the dual objective function. Our experiments on a variety of datasets show that each layer successively increases performance with only a few base kernels.

4 pages, 1 figure, 1 table, conference paper

Cited by in corpus (7)

• Going Deeper with Contextual CNN for Hyperspectral Image Classification
• Learning with Hierarchical Gaussian Kernels
• Deep Kernel Supervised Hashing for Node Classification in Structural Networks
• Totally Deep Support Vector Machines
• LMKL-Net: A Fast Localized Multiple Kernel Learning Solver via Deep Neural Networks
• Cascaded Coarse-to-Fine Deep Kernel Networks for Efficient Satellite Image Change Detection
• Regularization for Multiple Kernel Learning via Sum-Product Networks