Zobrazeno 1 - 10
of 116
pro vyhledávání: '"Taheri, Mahsa"'
Neural networks have become standard tools in many areas, yet many important statistical questions remain open. This paper studies the question of how much data are needed to train a ReLU feed-forward neural network. Our theoretical and empirical res
Externí odkaz:
http://arxiv.org/abs/2405.16696
Since statistical guarantees for neural networks are usually restricted to global optima of intricate objective functions, it is not clear whether these theories really explain the performances of actual outputs of neural-network pipelines. The goal
Externí odkaz:
http://arxiv.org/abs/2205.04491
Publikováno v:
In Journal of Statistical Planning and Inference January 2025 234
Autor:
Barros, Joaquim, Costelha, Hugo, Bento, David, Brites, Nelson, Luís, Rui, Patrício, Hugo, Cunha, Vitor, Bento, Luís, Miranda, Tiago, Coelho, Paulo, Azenha, Miguel, Neves, Carlos, Salehian, Hamidreza, Moniz, Gonçalo, Nematollahi, Mojtaba, Teixeira, Abel, Taheri, Mahsa, Mezhyrych, Anton, Hosseinpour, Emad, Correia, Tales, Kazemi, Hamid, Hassanshahi, Omid, Rashiddel, Alireza, Esmail, Briar
Publikováno v:
In Tunnelling and Underground Space Technology incorporating Trenchless Technology Research May 2024 147
Neural networks have become standard tools in the analysis of data, but they lack comprehensive mathematical theories. For example, there are very few statistical guarantees for learning neural networks from data, especially for classes of estimators
Externí odkaz:
http://arxiv.org/abs/2006.00294
Publikováno v:
In Process Biochemistry July 2023 130:272-280
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Tunnelling and Underground Space Technology incorporating Trenchless Technology Research November 2022 129
Publikováno v:
In Neural Networks October 2021 142:148-161