Urmăriți
Mohamed El Amine Seddik
Mohamed El Amine Seddik
Researcher at TII
Adresă de e-mail confirmată pe tii.ae - Pagina de pornire
Titlu
Citat de
Citat de
Anul
Random matrix theory proves that deep learning representations of gan-data behave as gaussian mixtures
MEA Seddik, C Louart, M Tamaazousti, R Couillet
International Conference on Machine Learning, 8573-8582, 2020
812020
Learning more universal representations for transfer-learning
Y Tamaazousti, H Le Borgne, C Hudelot, M Tamaazousti
IEEE transactions on pattern analysis and machine intelligence 42 (9), 2212-2224, 2019
782019
Deep Multi-class Adversarial Specularity Removal
J Lin, MEA Seddik, M Tamaazousti, Y Tamaazousti, A Bartoli
arXiv preprint arXiv:1904.02672, 2019
462019
Soil moisture estimation using Sentinel-1/-2 imagery coupled with cycleGAN for time-series gap filing
N Efremova, MEA Seddik, E Erten
IEEE Transactions on Geoscience and Remote Sensing 60, 1-11, 2021
362021
Kernel Random Matrices of Large Concentrated Data: The Example of GAN-Generated Images
MEA Seddik, M Tamaazousti, R Couillet
ICASSP 2019 - IEEE International Conference on Acoustics, Speech and Signal …, 2019
262019
How bad is training on synthetic data? a statistical analysis of language model collapse
MEA Seddik, SW Chen, S Hayou, P Youssef, M Debbah
arXiv preprint arXiv:2404.05090, 2024
202024
A Kernel Random Matrix-Based Approach for Sparse PCA
MEA Seddik, M Tamaazousti, R Couillet
ICLR 2019 - International Conference on Learning Representations, 2019
172019
When random tensors meet random matrices
MEA Seddik, M Guillaud, R Couillet
The Annals of Applied Probability 34 (1A), 203-248, 2024
162024
The unexpected deterministic and universal behavior of large softmax classifiers
MEA Seddik, C Louart, R Couillet, M Tamaazousti
International Conference on Artificial Intelligence and Statistics, 1045-1053, 2021
122021
Deep miner: a deep and multi-branch network which mines rich and diverse features for person re-identification
A Benzine, MEA Seddik, J Desmarais
arXiv preprint arXiv:2102.09321, 2021
112021
Generative collaborative networks for single image super-resolution
MEA Seddik, M Tamaazousti, J Lin
Neurocomputing 398, 293-303, 2020
112020
Node feature kernels increase graph convolutional network robustness
MEA Seddik, C Wu, JF Lutzeyer, M Vazirgiannis
International Conference on Artificial Intelligence and Statistics, 6225-6241, 2022
102022
Do Vision and Language Encoders Represent the World Similarly?
M Maniparambil, R Akshulakov, YAD Djilali, M El Amine Seddik, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
92024
Falcon2-11b technical report
Q Malartic, NR Chowdhury, R Cojocaru, M Farooq, G Campesan, ...
arXiv preprint arXiv:2407.14885, 2024
62024
Lightweight neural networks from pca & lda based distilled dense neural networks
MEA Seddik, H Essafi, A Benzine, M Tamaazousti
2020 IEEE International Conference on Image Processing (ICIP), 3060-3064, 2020
52020
SMArtCast: Predicting soil moisture interpolations into the future using Earth observation data in a deep learning framework
CJ Foley, S Vaze, MEA Seddiq, A Unagaev, N Efremova
arXiv preprint arXiv:2003.10823, 2020
52020
From outage probability to ALOHA MAC layer performance analysis in distributed WSNs
V Toldov, L Clavier, N Mitton
2018 IEEE Wireless Communications and Networking Conference (WCNC), 1-6, 2018
52018
Deciphering lasso-based classification through a large dimensional analysis of the iterative soft-thresholding algorithm
M Tiomoko, E Schnoor, MEA Seddik, I Colin, A Virmaux
International Conference on Machine Learning, 21449-21477, 2022
42022
Learning from low rank tensor data: A random tensor theory perspective
MEA Seddik, M Tiomoko, A Decurninge, M Panov, M Gauillaud
Uncertainty in Artificial Intelligence, 1858-1867, 2023
32023
Neural Networks Classify through the Class-wise Means of their Representations
MEA Seddik, M Tamaazousti
32021
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–20