39 citations · 70 across the 7 of their papers we have counts for
8 papers
Optimal sports betting strategies in practice: an experimental review
Matej Uhrín, Gustav Šourek, Ondřej Hubáček +1
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…
Learning with Molecules beyond Graph Neural Networks
Gustav Sourek, Filip Zelezny, Ondrej Kuzelka
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 compl…
Beyond Graph Neural Networks with Lifted Relational Neural Networks
Gustav Sourek, Filip Zelezny, Ondrej Kuzelka
We demonstrate a declarative differentiable programming framework based on the language of Lifted Relational Neural Networks, where small parameterized logic programs are used to e…
Lossless Compression of Structured Convolutional Models via Lifting
Gustav Sourek, Filip Zelezny, Ondrej Kuzelka
Lifting is an efficient technique to scale up graphical models generalized to relational domains by exploiting the underlying symmetries. Concurrently, neural models are continuous…
Stacked Structure Learning for Lifted Relational Neural Networks
Gustav Sourek, Martin Svatos, Filip Zelezny +2
Lifted Relational Neural Networks (LRNNs) describe relational domains using weighted first-order rules which act as templates for constructing feed-forward neural networks. While p…
Estimating Sequence Similarity from Read Sets for Clustering Next-Generation Sequencing data
Petr Ryšavý, Filip Železný
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 me…
Lifted Relational Neural Networks
Gustav Sourek, Vojtech Aschenbrenner, Filip Zelezny +1
We propose a method combining relational-logic representations with neural network learning. A general lifted architecture, possibly reflecting some background domain knowledge, is…
A Revised Publication Model for ECML PKDD
Hendrik Blockeel, Kristian Kersting, Siegfried Nijssen +1
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 c…