Conference Papers Year : 2019

Recurrent Kernel Networks

Abstract

Substring kernels are classical tools for representing biological sequences or text. However, when large amounts of annotated data are available, models that allow end-to-end training such as neural networks are often preferred. Links between recurrent neural networks (RNNs) and substring kernels have recently been drawn, by formally showing that RNNs with specific activation functions were points in a reproducing kernel Hilbert space (RKHS). In this paper, we revisit this link by generalizing convolutional kernel networks—originally related to a relaxation of the mismatch kernel—to model gaps in sequences. It results in a new type of recurrent neural network which can be trained end-to-end with backpropagation, or without supervision by using kernel approximation techniques. We experimentally show that our approach is well suited to biological sequences, where it outperforms existing methods for protein classification tasks.
Fichier principal
Vignette du fichier
neurips_2019.pdf (584.18 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02151135 , version 1 (07-06-2019)
hal-02151135 , version 2 (17-10-2019)

Identifiers

Cite

Dexiong Chen, Laurent Jacob, Julien Mairal. Recurrent Kernel Networks. NeurIPS 2019 - Thirty-third Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada. ⟨hal-02151135v2⟩
472 View
473 Download

Altmetric

Share

More