Edouard Couplet

According to our database, Edouard Couplet authored at least 6 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Investigating latent representations and generalization in deep neural networks for tabular data.

Edouard Couplet, Pierre Lambert, Michel Verleysen, John A. Lee, Cyril de Bodt

Neurocomputing, 2024

Estimated neighbour sets and smoothed sampled global interactions are sufficient for a fast approximate tSNE.

Pierre Lambert, Edouard Couplet, Cyril de Bodt, John A. Lee

Proceedings of the 32nd European Symposium on Artificial Neural Networks, 2024

Forget early exaggeration in t-SNE: early hierarchization preserves global structure.

John A. Lee, Edouard Couplet, Pierre Lambert, Ludovic Journaux, Dounia Mulders, Cyril de Bodt, Michel Verleysen

Proceedings of the 32nd European Symposium on Artificial Neural Networks, 2024

2023

Natively Interpretable t-SNE.

Edouard Couplet, Pierre Lambert, Michel Verleysen, Dounia Mulders, John A. Lee, Cyril de Bodt

Proceedings of the Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023

Nesterov momentum and gradient normalization to improve t-SNE convergence and neighborhood preservation, without early exaggeration.

Pierre Lambert, John A. Lee, Edouard Couplet, Cyril de Bodt

Proceedings of the 31st European Symposium on Artificial Neural Networks, 2023

On the number of latent representations in deep neural networks for tabular data.

Edouard Couplet, Pierre Lambert, Michel Verleysen, John A. Lee, Cyril de Bodt

Proceedings of the 31st European Symposium on Artificial Neural Networks, 2023