Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Tiomoko ali, Hafiz"'
Autor:
Tiomoko ali, Hafiz
Motivée par les récentes avancées dans l'analyse théorique des performances des algorithmes d'apprentissage automatisé, cette thèse s'intéresse à l'analyse de performances et à l'amélioration de la classification nonsupervisée de données
Externí odkaz:
http://www.theses.fr/2018SACLC074/document
Autor:
Tiomoko ali, Hafiz
Publikováno v:
Autre [cs.OH]. Université Paris-Saclay, 2018. Français. ⟨NNT : 2018SACLC074⟩
Spurred by recent advances on the theoretical analysis of the performances of the data-driven machine learning algorithms, this thesis tackles the performance analysis and improvement of high dimensional data and graph clustering. Specifically, in th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______212::05c5c8f71720628688b6a865bc061ded
https://tel.archives-ouvertes.fr/tel-01891093
https://tel.archives-ouvertes.fr/tel-01891093
Autor:
Tiomoko Ali, Hafiz, Couillet, Romain
Publikováno v:
Journal of Machine Learning Research
Journal of Machine Learning Research, Microtome Publishing, 2018, 18 (10), pp.1-49
Journal of Machine Learning Research, Microtome Publishing, 2018, 18 (10), pp.1-49
12 pages, 3 figures, Accepted for publication in the IEEE Transactions on Vehicular Technology; International audience; In this article, we propose and study the performance of spectral community detection for a family of "α-normalized" adjacency ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::cf53421f442e2313ecaf6bb305b85a03
https://hal.archives-ouvertes.fr/hal-01957623/document
https://hal.archives-ouvertes.fr/hal-01957623/document
Publikováno v:
Journal of Machine Learning Research
Journal of Machine Learning Research, Microtome Publishing, 2016, 17 (178), pp.1-35
Journal of Machine Learning Research, 2016, 17 (178), pp.1-35
Journal of Machine Learning Research, Microtome Publishing, 2016, 17 (178), pp.1-35
Journal of Machine Learning Research, 2016, 17 (178), pp.1-35
International audience; In this article, a study of the mean-square error (MSE) performance of linear echo-state neural networks is performed, both for training and testing tasks. Considering the realistic setting of noise present at the network node
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f0e0aade73328c98c47705597e489442
https://hal.science/hal-01322809
https://hal.science/hal-01322809
Publikováno v:
International Conference on Machine Learning (ICML), New York, USA, 2016
International Conference on Machine Learning (ICML 2016)
International Conference on Machine Learning (ICML 2016), Jun 2016, New York, United States
International Conference on Machine Learning (ICML 2016)
International Conference on Machine Learning (ICML 2016), Jun 2016, New York, United States
International audience; Recurrent neural networks, especially in their linear version, have provided many qualitative insights on their performance under different configurations. This article provides, through a novel random matrix framework, the qu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::4f773b944a0196fda1b4604c419231a8
https://hal.science/hal-01812026
https://hal.science/hal-01812026
Autor:
TIOMOKO ALI, Hafiz, Couillet, Romain
Publikováno v:
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'16), Shanghai, China
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'16), Shanghai, China, Mar 2016, Shanguai, China. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'16), Shanghai, China, 2016
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'16), Shanghai, China, Mar 2016, Shanguai, China
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'16), Shanghai, China, Mar 2016, Shanguai, China. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'16), Shanghai, China, 2016
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'16), Shanghai, China, Mar 2016, Shanguai, China
International audience; This article proposes a spectral analysis of dense random graphs generated by (a modified version of) the degree-corrected stochastic block model, for a setting where the inter block probabilities differ by O(n^(−1/2)) with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3e1878d235c93a3b229f97479512e985
https://hal.archives-ouvertes.fr/hal-01322797/file/Tiomoko2016Performance.pdf
https://hal.archives-ouvertes.fr/hal-01322797/file/Tiomoko2016Performance.pdf
Publikováno v:
IEEE Statistical Signal Processing Workshop 2016 (SSP'16), Palma de Majorca, Spain
IEEE Statistical Signal Processing Workshop 2016 (SSP'16), Palma de Majorca, Spain, Jun 2016, Palma de Majorca, Spain
SSP
IEEE Statistical Signal Processing Workshop 2016 (SSP'16), Palma de Majorca, Spain, Jun 2016, Palma de Majorca, Spain. IEEE Statistical Signal Processing Workshop 2016 (SSP'16), Palma de Majorca, Spain
IEEE Statistical Signal Processing Workshop 2016 (SSP'16), Palma de Majorca, Spain, Jun 2016, Palma de Majorca, Spain
SSP
IEEE Statistical Signal Processing Workshop 2016 (SSP'16), Palma de Majorca, Spain, Jun 2016, Palma de Majorca, Spain. IEEE Statistical Signal Processing Workshop 2016 (SSP'16), Palma de Majorca, Spain
International audience; This article proposes a first theoretical performance analysis of the training phase of large dimensional linear echo-state networks. This analysis is based on advanced methods of random matrix theory. The results provide some
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1ab36250df62b9a4707feb82759d9da9
https://hal.archives-ouvertes.fr/hal-01633450v2/document
https://hal.archives-ouvertes.fr/hal-01633450v2/document