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.

Cited by in corpus (7)

• Learning Long-Term Dependencies in Irregularly-Sampled Time Series
• Convolutional Kernel Networks for Graph-Structured Data
• 1-Dimensional polynomial neural networks for audio signal related problems
• Reservoir Computing meets Recurrent Kernels and Structured Transforms
• CECILIA: Comprehensive Secure Machine Learning Framework
• Polynomial degree reduction in the ${\mathcal{L}}^2$-norm on a symmetric interval for the canonical basis
• On Inductive Biases for Machine Learning in Data Constrained Settings