Skip to Main content Skip to Navigation
Conference papers

Recurrent Kernel Networks

Dexiong Chen 1 Laurent Jacob 2 Julien Mairal 1 
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
2 Statistique en grande dimension pour la génomique
PEGASE - Département PEGASE [LBBE]
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.
Complete list of metadata

Cited literature [41 references]  Display  Hide  Download
Contributor : Dexiong Chen Connect in order to contact the contributor
Submitted on : Thursday, October 17, 2019 - 3:47:23 PM
Last modification on : Friday, February 4, 2022 - 3:21:14 AM


Files produced by the author(s)


  • HAL Id : hal-02151135, version 2
  • ARXIV : 1906.03200



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⟩



Record views


Files downloads