Picture for Mathieu Léonardon

Mathieu Léonardon

DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables

Add code
Apr 18, 2023
Viaarxiv icon

Energy Consumption Analysis of pruned Semantic Segmentation Networks on an Embedded GPU

Add code
Jun 13, 2022
Figure 1 for Energy Consumption Analysis of pruned Semantic Segmentation Networks on an Embedded GPU
Figure 2 for Energy Consumption Analysis of pruned Semantic Segmentation Networks on an Embedded GPU
Viaarxiv icon

Leveraging Structured Pruning of Convolutional Neural Networks

Add code
Jun 13, 2022
Figure 1 for Leveraging Structured Pruning of Convolutional Neural Networks
Figure 2 for Leveraging Structured Pruning of Convolutional Neural Networks
Figure 3 for Leveraging Structured Pruning of Convolutional Neural Networks
Figure 4 for Leveraging Structured Pruning of Convolutional Neural Networks
Viaarxiv icon

Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes

Add code
May 11, 2021
Figure 1 for Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes
Figure 2 for Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes
Figure 3 for Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes
Figure 4 for Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes
Viaarxiv icon

Continuous Pruning of Deep Convolutional Networks Using Selective Weight Decay

Add code
Dec 22, 2020
Figure 1 for Continuous Pruning of Deep Convolutional Networks Using Selective Weight Decay
Figure 2 for Continuous Pruning of Deep Convolutional Networks Using Selective Weight Decay
Figure 3 for Continuous Pruning of Deep Convolutional Networks Using Selective Weight Decay
Figure 4 for Continuous Pruning of Deep Convolutional Networks Using Selective Weight Decay
Viaarxiv icon