paper-with-me

Papers

Recurrent Kernel Networks

2019-06-07 · NeurIPS 2019 12 · Dexiong Chen, Laurent Jacob, Julien Mairal

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.

📄 PDF Abstract BibTeX arXiv:1906.03200

Code (1)

claying/RKN pytorch

Similar Papers 제목 키워드 기반

Reservoir Computing meets Recurrent Kernels and Structured Transforms

2020-06-12 · NeurIPS 2020 12 · Jonathan Dong, Ruben Ohana, Mushegh Rafayelyan, Florent Krzakala

Reservoir Computing is a class of simple yet efficient Recurrent Neural Networks where internal weights are fixed at random and only a linear output layer is trained. In the large size limit, such random neural networks …

Time SeriesTime Series AnalysisTime Series Prediction

The Recurrent Neural Tangent Kernel

2020-06-18 · ICLR 2021 1 · Sina Al-E-Mohammad, Zichao Wang, Randall Balestriero, Richard Baraniuk

The study of deep neural networks (DNNs) in the infinite-width limit, via the so-called neural tangent kernel (NTK) approach, has provided new insights into the dynamics of learning, generalization, and the impact of ini…

Learning Scalable Deep Kernels with Recurrent Structure

2016-10-27 · Maruan Al-Shedivat, Andrew Gordon Wilson, Yunus Saatchi, Zhiting Hu 외

Many applications in speech, robotics, finance, and biology deal with sequential data, where ordering matters and recurrent structures are common. However, this structure cannot be easily captured by standard kernel func…

Autonomous DrivingGaussian ProcessesSmart Grid Prediction

Enhanced Recurrent Neural Tangent Kernels for Non-Time-Series Data

2020-12-09 · Sina AlEMohammad, Randall Balestriero, Zichao Wang, Richard Baraniuk

Kernels derived from deep neural networks (DNNs) in the infinite-width regime provide not only high performance in a range of machine learning tasks but also new theoretical insights into DNN training dynamics and genera…

GPUTime SeriesTime Series Analysis

Framing RNN as a kernel method: A neural ODE approach

2021-06-02 · NeurIPS 2021 12 · Adeline Fermanian, Pierre Marion, Jean-Philippe Vert, Gérard Biau

Building on the interpretation of a recurrent neural network (RNN) as a continuous-time neural differential equation, we show, under appropriate conditions, that the solution of a RNN can be viewed as a linear function o…