Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Zelezny, Filip"'
Publikováno v:
IMA Journal of Management Mathematics (2021) 00
We investigate the most popular approaches to the problem of sports betting investment based on modern portfolio theory and the Kelly criterion. We define the problem setting, the formal investment strategies, and review their common modifications us
Externí odkaz:
http://arxiv.org/abs/2107.08827
We demonstrate a deep learning framework which is inherently based in the highly expressive language of relational logic, enabling to, among other things, capture arbitrarily complex graph structures. We show how Graph Neural Networks and similar mod
Externí odkaz:
http://arxiv.org/abs/2011.03488
Publikováno v:
Machine Learning, volume 110, pages 1695 - 1738 (2021)
We demonstrate a declarative differentiable programming framework based on the language of Lifted Relational Neural Networks, where small parameterized logic programs are used to encode relational learning scenarios. When presented with relational da
Externí odkaz:
http://arxiv.org/abs/2007.06286
Lifting is an efficient technique to scale up graphical models generalized to relational domains by exploiting the underlying symmetries. Concurrently, neural models are continuously expanding from grid-like tensor data into structured representation
Externí odkaz:
http://arxiv.org/abs/2007.06567
Lifted Relational Neural Networks (LRNNs) describe relational domains using weighted first-order rules which act as templates for constructing feed-forward neural networks. While previous work has shown that using LRNNs can lead to state-of-the-art r
Externí odkaz:
http://arxiv.org/abs/1710.02221
Autor:
Ryšavý, Petr, Železný, Filip
To cluster sequences given only their read-set representations, one may try to reconstruct each one from the corresponding read set, and then employ conventional (dis)similarity measures such as the edit distance on the assembled sequences. This appr
Externí odkaz:
http://arxiv.org/abs/1705.06125
We propose a method combining relational-logic representations with neural network learning. A general lifted architecture, possibly reflecting some background domain knowledge, is described through relational rules which may be handcrafted or learne
Externí odkaz:
http://arxiv.org/abs/1508.05128
Publikováno v:
In International Journal of Forecasting April-June 2019 35(2):783-796
ECML PKDD is the main European conference on machine learning and data mining. Since its foundation it implemented the publication model common in computer science: there was one conference deadline; conference submissions were reviewed by a program
Externí odkaz:
http://arxiv.org/abs/1207.6324
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.