Timezone: »

Recurrent Kernel Networks
Dexiong Chen · Laurent Jacob · Julien Mairal

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #81

Substring kernels are classical tools for representing biological sequences or text. However, when large amounts of annotated data is available, models that allow end-to-end training such as neural networks are often prefered. 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.

Author Information

Dexiong Chen (Inria)
Laurent Jacob (CNRS)
Julien Mairal (Inria)

More from the Same Authors