139 citations · 145 across the 5 of their papers we have counts for
6 papers
Acoustic domain shift in spoken language identification from systematic domain generalization evaluation to real-world application
Francois Derrida, Raphaël Duroselle, Thomas Courtat +1
Domain Generalization (DG) aims to develop models that remain robust to conditions unseen during training. While DG has been systematically studied in computer vision through contr…
Compression of Recurrent Neural Networks using Matrix Factorization
Lucas Maison, Hélion du Mas des Bourboux, Thomas Courtat
Compressing neural networks is a key step when deploying models for real-time or embedded applications. Factorizing the model's matrices using low-rank approximations is a promisin…
A light neural network for modulation detection under impairments
Thomas Courtat, Hélion du Mas des Bourboux
We present a neural network architecture able to efficiently detect modulation scheme in a portion of I/Q signals. This network is lighter by up to two orders of magnitude than oth…
Stochastic simulation of urban environments. Application to Path-loss in wireless systems
Thomas Courtat, Laurent Decreusefond, Phillipe Martins
We are interested in the assessment of electromagnetic Path-Loss in complex environments. The Path-loss is the attenuation function of the electromagnetic power at a distance $…
Hypergraphs and City Street Networks
Thomas Courtat, Catherine Gloaguen, Stéphane Douady
The map of a city's streets constitutes a particular case of spatial complex network. However a city is not limited to its topology: it is above all a geometrical object whose part…
Mathematics and Morphogenesis of the City: A Geometrical Approach
Thomas Courtat, Catherine Gloaguen, Stephane Douady
Cities are living organisms. They are out of equilibrium, open systems that never stop developing and sometimes die. The local geography can be compared to a shell constraining its…