Search Results for author: Jérémy Rapin

Found 8 papers, 3 papers with code

Does Zero-Shot Reinforcement Learning Exist?

no code implementations29 Sep 2022 Ahmed Touati, Jérémy Rapin, Yann Ollivier

A zero-shot RL agent is an agent that can solve any RL task in a given environment, instantly with no additional planning or learning, after an initial reward-free learning phase.

Contrastive Learning reinforcement-learning +1

Decoding speech from non-invasive brain recordings

no code implementations25 Aug 2022 Alexandre Défossez, Charlotte Caucheteux, Jérémy Rapin, Ori Kabeli, Jean-Rémi King

Model comparison and ablation analyses show that these performances directly benefit from our original design choices, namely the use of (i) a contrastive objective, (ii) pretrained representations of speech and (iii) a common convolutional architecture simultaneously trained across several participants.

Contrastive Learning EEG

ROMUL: Scale Adaptative Population Based Training

no code implementations1 Jan 2021 Daniel Haziza, Jérémy Rapin, Gabriel Synnaeve

In most pragmatic settings, data augmentation and regularization are essential, and require hyperparameter search.

Data Augmentation Image Classification +1

Population Based Training for Data Augmentation and Regularization in Speech Recognition

no code implementations8 Oct 2020 Daniel Haziza, Jérémy Rapin, Gabriel Synnaeve

It compares favorably to a baseline that does not change those hyperparameters over the course of training, with an 8% relative WER improvement.

Data Augmentation speech-recognition +1

Inspirational Adversarial Image Generation

1 code implementation17 Jun 2019 Baptiste Rozière, Morgane Riviere, Olivier Teytaud, Jérémy Rapin, Yann Lecun, Camille Couprie

We design a simple optimization method to find the optimal latent parameters corresponding to the closest generation to any input inspirational image.

Image Generation

NMF with Sparse Regularizations in Transformed Domains

1 code implementation29 Jul 2014 Jérémy Rapin, Jérôme Bobin, Anthony Larue, Jean-Luc Starck

In this article, we show how a sparse NMF algorithm coined non-negative generalized morphological component analysis (nGMCA) can be extended to impose non-negativity in the direct domain along with sparsity in a transformed domain, with both analysis and synthesis formulations.

Sparse and Non-Negative BSS for Noisy Data

1 code implementation26 Aug 2013 Jérémy Rapin, Jérôme Bobin, Anthony Larue, Jean-Luc Starck

In this context, it is fundamental that the sources to be estimated present some diversity in order to be efficiently retrieved.

Cannot find the paper you are looking for? You can Submit a new open access paper.