Search Results for author: Maxime Pelcat

Found 10 papers, 4 papers with code

Gegelati: Lightweight Artificial Intelligence through Generic and Evolvable Tangled Program Graphs

no code implementations15 Dec 2020 Karol Desnos, Nicolas Sourbier, Pierre-Yves Raumer, Olivier Gesny, Maxime Pelcat

The impact of customizable instructions on the outcome of a training process is demonstrated on a state-of-the-art reinforcement learning environment.

NoiseBreaker: Gradual Image Denoising Guided by Noise Analysis

no code implementations18 Feb 2020 Florian Lemarchand, Erwan Nogues, Maxime Pelcat

When the target noise is complex, e. g. composed of an unknown mixture of primary noises with unknown intensity, fully supervised solutions are limited by the difficulty to build a suited training set for the problem.

Image Denoising

Electro-Magnetic Side-Channel Attack Through Learned Denoising and Classification

2 code implementations16 Oct 2019 Florian Lemarchand, Cyril Marlin, Florent Montreuil, Erwan Nogues, Maxime Pelcat

This paper proposes an upgraded electro-magnetic side-channel attack that automatically reconstructs the intercepted data.

Classification Denoising +1

The Challenge of Multi-Operand Adders in CNNs on FPGAs: How not to solve it!

1 code implementation30 Jun 2018 Kamel Abdelouahab, François Berry, Maxime Pelcat

Convolutional Neural Networks (CNNs) are computationally intensive algorithms that currently require dedicated hardware to be executed.

Distributed, Parallel, and Cluster Computing Hardware Architecture

Hardware Automated Dataflow Deployment of CNNs

no code implementations4 May 2017 Kamel Abdelouahab, Maxime Pelcat, Jocelyn Serot, Cedric Bourrasset, Jean-Charles Quinton, François Berry

Deep Convolutional Neural Networks (CNNs) are the state of the art systems for image classification and scene understating.

Other Computer Science

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