Zobrazeno 1 - 10
of 119
pro vyhledávání: '"Jäger, Manfred"'
Existing multi-relational graph neural networks use one of two strategies for identifying informative relations: either they reduce this problem to low-level weight learning, or they rely on handcrafted chains of relational dependencies, called meta-
Externí odkaz:
http://arxiv.org/abs/2309.17113
Publikováno v:
In Cretaceous Research September 2024 161
Publikováno v:
In Palaeoworld April 2024 33(2):267-283
Learning on sets is increasingly gaining attention in the machine learning community, due to its widespread applicability. Typically, representations over sets are computed by using fixed aggregation functions such as sum or maximum. However, recent
Externí odkaz:
http://arxiv.org/abs/2012.08482
Euclidean Markov decision processes are a powerful tool for modeling control problems under uncertainty over continuous domains. Finite state imprecise, Markov decision processes can be used to approximate the behavior of these infinite models. In th
Externí odkaz:
http://arxiv.org/abs/2006.14923
Robustness of neural networks has recently attracted a great amount of interest. The many investigations in this area lack a precise common foundation of robustness concepts. Therefore, in this paper, we propose a rigorous and flexible framework for
Externí odkaz:
http://arxiv.org/abs/2006.11122
Autor:
Jaeger, Manfred, Schulte, Oliver
A generative probabilistic model for relational data consists of a family of probability distributions for relational structures over domains of different sizes. In most existing statistical relational learning (SRL) frameworks, these models are not
Externí odkaz:
http://arxiv.org/abs/2004.10984
We introduce an extension of the multi-instance learning problem where examples are organized as nested bags of instances (e.g., a document could be represented as a bag of sentences, which in turn are bags of words). This framework can be useful in
Externí odkaz:
http://arxiv.org/abs/1810.11514
Autor:
Jaeger, Manfred, Schulte, Oliver
A subtle difference between propositional and relational data is that in many relational models, marginal probabilities depend on the population or domain size. This paper connects the dependence on population size to the classic notion of projectivi
Externí odkaz:
http://arxiv.org/abs/1807.00564
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.