Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Achour, El Mehdi"'
Predictive coding (PC) is an energy-based learning algorithm that performs iterative inference over network activities before weight updates. Recent work suggests that PC can converge in fewer learning steps than backpropagation thanks to its inferen
Externí odkaz:
http://arxiv.org/abs/2408.11979
A general approximation lower bound in $L^p$ norm, with applications to feed-forward neural networks
Publikováno v:
Advances in Neural Information Processing Systems, Dec 2022, New-Orleans, United States
We study the fundamental limits to the expressive power of neural networks. Given two sets $F$, $G$ of real-valued functions, we first prove a general lower bound on how well functions in $F$ can be approximated in $L^p(\mu)$ norm by functions in $G$
Externí odkaz:
http://arxiv.org/abs/2206.04360
Publikováno v:
Journal of Machine Learning Research, 2022, 23 (347), pp.1--56
Imposing orthogonality on the layers of neural networks is known to facilitate the learning by limiting the exploding/vanishing of the gradient; decorrelate the features; improve the robustness. This paper studies the theoretical properties of orthog
Externí odkaz:
http://arxiv.org/abs/2108.05623
We study the optimization landscape of deep linear neural networks with the square loss. It is known that, under weak assumptions, there are no spurious local minima and no local maxima. However, the existence and diversity of non-strict saddle point
Externí odkaz:
http://arxiv.org/abs/2107.13289
Autor:
Achour, El Mehdi
Publikováno v:
Optimisation et contrôle [math.OC]. Université Paul Sabatier-Toulouse III, 2022. Français. ⟨NNT : 2022TOU30202⟩
In this thesis, we study different theoretical aspects of deep learning, in particular optimization, robustness, and approximation. Optimization: We study the optimization landscape of the empirical risk of deep linear neural networks with the square
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______4074::0b1fec299ad06985d6144c29c9798f10
https://theses.hal.science/tel-04122195/file/2022TOU30202b.pdf
https://theses.hal.science/tel-04122195/file/2022TOU30202b.pdf
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.