Recurrent Kernel Networks - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Recurrent Kernel Networks

Résumé

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
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

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

Identifiants

Citer

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⟩
428 Consultations
445 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More