Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Maennel, Hartmut"'
When modeling physical properties of molecules with machine learning, it is desirable to incorporate $SO(3)$-covariance. While such models based on low body order features are not complete, we formulate and prove general completeness properties for h
Externí odkaz:
http://arxiv.org/abs/2409.02730
Autor:
Unke, Oliver T., Stöhr, Martin, Ganscha, Stefan, Unterthiner, Thomas, Maennel, Hartmut, Kashubin, Sergii, Ahlin, Daniel, Gastegger, Michael, Sandonas, Leonardo Medrano, Tkatchenko, Alexandre, Müller, Klaus-Robert
Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes. Accurate MD simulations require computationally demanding quantum-mechanical calculations, being practically limited to short timescales and few atom
Externí odkaz:
http://arxiv.org/abs/2205.08306
Recent results suggest that reinitializing a subset of the parameters of a neural network during training can improve generalization, particularly for small training sets. We study the impact of different reinitialization methods in several convoluti
Externí odkaz:
http://arxiv.org/abs/2109.00267
Existing work on understanding deep learning often employs measures that compress all data-dependent information into a few numbers. In this work, we adopt a perspective based on the role of individual examples. We introduce a measure of the computat
Externí odkaz:
http://arxiv.org/abs/2106.09647
Autor:
Maennel, Hartmut, Alabdulmohsin, Ibrahim, Tolstikhin, Ilya, Baldock, Robert J. N., Bousquet, Olivier, Gelly, Sylvain, Keysers, Daniel
We study deep neural networks (DNNs) trained on natural image data with entirely random labels. Despite its popularity in the literature, where it is often used to study memorization, generalization, and other phenomena, little is known about what DN
Externí odkaz:
http://arxiv.org/abs/2006.10455
Autor:
Maennel, Hartmut
Assume we have potential "causes" $z\in Z$, which produce "events" $w$ with known probabilities $\beta(w|z)$. We observe $w_1,w_2,...,w_n$, what can we say about the distribution of the causes? A Bayesian estimate will assume a prior on distributions
Externí odkaz:
http://arxiv.org/abs/2004.00115
Autor:
Penedones, Hugo, Riquelme, Carlos, Vincent, Damien, Maennel, Hartmut, Mann, Timothy, Barreto, Andre, Gelly, Sylvain, Neu, Gergely
We consider the core reinforcement-learning problem of on-policy value function approximation from a batch of trajectory data, and focus on various issues of Temporal Difference (TD) learning and Monte Carlo (MC) policy evaluation. The two methods ar
Externí odkaz:
http://arxiv.org/abs/1906.07987
Autor:
Penedones, Hugo, Vincent, Damien, Maennel, Hartmut, Gelly, Sylvain, Mann, Timothy, Barreto, Andre
Temporal-Difference learning (TD) [Sutton, 1988] with function approximation can converge to solutions that are worse than those obtained by Monte-Carlo regression, even in the simple case of on-policy evaluation. To increase our understanding of the
Externí odkaz:
http://arxiv.org/abs/1807.03064
Deep neural networks are often trained in the over-parametrized regime (i.e. with far more parameters than training examples), and understanding why the training converges to solutions that generalize remains an open problem. Several studies have hig
Externí odkaz:
http://arxiv.org/abs/1803.08367
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.