Spline Filters For End-to-End Deep Learning

Randall Balestriero, Romain Cosentino, Herve Glotin, Richard Baraniuk
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:364-373, 2018.

Abstract

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 parametric analytical filters. Their differentiability property allows gradient-based optimization. As such, one can utilize any Deep Neural Network (DNN) with these filters. This enables us to tackle in a front-end fashion a large scale bird detection task based on the freefield1010 dataset known to contain key challenges, such as the dimensionality of the inputs data ($>100,000$) and the presence of additional noises: multiple sources and soundscapes.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-balestriero18a, title = {Spline Filters For End-to-End Deep Learning}, author = {Balestriero, Randall and Cosentino, Romain and Glotin, Herve and Baraniuk, Richard}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {364--373}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/balestriero18a/balestriero18a.pdf}, url = {https://proceedings.mlr.press/v80/balestriero18a.html}, abstract = {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 parametric analytical filters. Their differentiability property allows gradient-based optimization. As such, one can utilize any Deep Neural Network (DNN) with these filters. This enables us to tackle in a front-end fashion a large scale bird detection task based on the freefield1010 dataset known to contain key challenges, such as the dimensionality of the inputs data ($>100,000$) and the presence of additional noises: multiple sources and soundscapes.} }
Endnote
%0 Conference Paper %T Spline Filters For End-to-End Deep Learning %A Randall Balestriero %A Romain Cosentino %A Herve Glotin %A Richard Baraniuk %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-balestriero18a %I PMLR %P 364--373 %U https://proceedings.mlr.press/v80/balestriero18a.html %V 80 %X 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 parametric analytical filters. Their differentiability property allows gradient-based optimization. As such, one can utilize any Deep Neural Network (DNN) with these filters. This enables us to tackle in a front-end fashion a large scale bird detection task based on the freefield1010 dataset known to contain key challenges, such as the dimensionality of the inputs data ($>100,000$) and the presence of additional noises: multiple sources and soundscapes.
APA
Balestriero, R., Cosentino, R., Glotin, H. & Baraniuk, R.. (2018). Spline Filters For End-to-End Deep Learning. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:364-373 Available from https://proceedings.mlr.press/v80/balestriero18a.html.

Related Material