Pierrick Pochelu

According to our database, Pierrick Pochelu authored at least 8 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2024

JaxDecompiler: Redefining Gradient-Informed Software Design.

Pierrick Pochelu

CoRR, 2024

Mastering Computer Vision Inference Frameworks.

Pierrick Pochelu, Oscar Castro-López

Proceedings of the Companion of the 15th ACM/SPEC International Conference on Performance Engineering, 2024

2022

Ensembles of Deep Neural Networks distributed and parallel for the energy industry. (Ensembles de réseaux de neurones répartis et parallèles appliqués au domaine de l'énergie).

Pierrick Pochelu

PhD thesis, 2022

Deep Learning Inference Frameworks Benchmark.

Pierrick Pochelu

CoRR, 2022

Weakly Supervised Faster-RCNN+FPN to classify animals in camera trap images.

Pierrick Pochelu, Clara Erard, Philippe Cordier, Serge G. Petiton, Bruno Conche

Proceedings of the IVSP 2022: 4th International Conference on Image, Video and Signal Processing, Singapore, March 18, 2022

A Deep Neural Networks ensemble workflow from hyperparameter search to inference leveraging GPU clusters.

Pierrick Pochelu, Serge G. Petiton, Bruno Conche

Proceedings of the HPC Asia 2022: International Conference on High Performance Computing in Asia-Pacific Region, Virtual Event, Japan, January 12, 2022

Distributed Ensembles of Reinforcement Learning Agents for Electricity Control.

Pierrick Pochelu, Bruno Conche, Serge G. Petiton

Proceedings of the IEEE International Conference on Omni-layer Intelligent Systems, 2022

2021

An efficient and flexible inference system for serving heterogeneous ensembles of deep neural networks.

Pierrick Pochelu, Serge G. Petiton, Bruno Conche

Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), 2021