Towards deep kernel machines

Julien Mairal
(INRIA Grenoble, France)


In this talk, we introduce a new image representation based on a multilayer kernel machine. Unlike traditional kernel methods where data representation is decoupled from the prediction task, we learn how to shape the kernel with supervision. We proceed by first introducing an unsupervised image model called convolutional kernel networks (CKNs); then, we derive backpropagation rules to take advantage of labeled training data. The resulting model is a new type of convolutional neural network, where optimizing the filters at each layer is equivalent to learning a linear subspace in a reproducing kernel Hilbert space (RKHS).

We show that our method achieves reasonably competitive performance for image classification on some standard " deep learning " datasets such as CIFAR-10 and SVHN, and also for image super-resolution, demonstrating the applicability of our approach to a large variety of image-related tasks.