Herve Glotin — accepted AI-conference papers

2018

Spline Filters For End-to-End Deep Learning

Randall Balestriero, Romain Cosentino, Herve Glotin, Richard Baraniuk

ICML 2018oral

We propose to tackle the problem of end-to-end learning for raw waveform signals by introducing learnable continuous time-frequency atoms. The derivation of these filters is achieved by defining a functional space with a given smoothness order and boundary conditions. From this space, we derive the…

Cited by 36 Source ↗PDF ↗code ↗Scholar ↗

2017

Fast Chirplet Transform to Enhance CNN Machine Listening - Validation on Animal calls and Speech

Herve Glotin, Julien Ricard, Randall Balestriero

ICLR 2017workshop

The scattering framework offers an optimal hierarchical convolutional decomposition according to its kernels. Convolutional Neural Net (CNN) can be seen asan optimal kernel decomposition, nevertheless it requires large amount of trainingdata to learn its kernels. We propose a trade-off between the…

Cited by 5 Source ↗Scholar ↗