Section: New Software and Platforms


Convolutional Kernel Networks in TensorFlow

Keyword: Machine learning

Scientific Description: This software package implements 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 proposing improvements of the recently-introduced convolutional kernel networks (CKNs) in the context of unsupervised learning, 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).

Functional Description: This is the implementation in TensorFlow of the Convolutional Kernel Networks method for image classification, described in the paper J. Mairal. End-to-End Kernel Learning with Supervised Convolutional Kernel Networks. Adv. Neural Information Processing Systems (NIPS), 2016.