Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Maziarka, Łukasz"'
Autor:
Kuciński, Łukasz, Drzewakowski, Witold, Olko, Mateusz, Kozakowski, Piotr, Maziarka, Łukasz, Nowakowska, Marta Emilia, Kaiser, Łukasz, Miłoś, Piotr
Time series methods are of fundamental importance in virtually any field of science that deals with temporally structured data. Recently, there has been a surge of deterministic transformer models with time series-specific architectural biases. In th
Externí odkaz:
http://arxiv.org/abs/2403.05713
Autor:
Maziarka, Łukasz, Majchrowski, Dawid, Danel, Tomasz, Gaiński, Piotr, Tabor, Jacek, Podolak, Igor, Morkisz, Paweł, Jastrzębski, Stanisław
Self-supervised learning holds promise to revolutionize molecule property prediction - a central task to drug discovery and many more industries - by enabling data efficient learning from scarce experimental data. Despite significant progress, non-pr
Externí odkaz:
http://arxiv.org/abs/2110.05841
One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks. At the same time finding a joint, adaptable representation of data is one of the key challenges in the multi-t
Externí odkaz:
http://arxiv.org/abs/2110.03498
Autor:
Wołczyk, Maciej, Proszewska, Magdalena, Maziarka, Łukasz, Zięba, Maciej, Wielopolski, Patryk, Kurczab, Rafał, Śmieja, Marek
Modern generative models achieve excellent quality in a variety of tasks including image or text generation and chemical molecule modeling. However, existing methods often lack the essential ability to generate examples with requested properties, suc
Externí odkaz:
http://arxiv.org/abs/2109.09011
Autor:
Sendera, Marcin, Śmieja, Marek, Maziarka, Łukasz, Struski, Łukasz, Spurek, Przemysław, Tabor, Jacek
We propose FlowSVDD -- a flow-based one-class classifier for anomaly/outliers detection that realizes a well-known SVDD principle using deep learning tools. Contrary to other approaches to deep SVDD, the proposed model is instantiated using flow-base
Externí odkaz:
http://arxiv.org/abs/2108.04907
Graph neural networks have recently become a standard method for analysing chemical compounds. In the field of molecular property prediction, the emphasis is now put on designing new model architectures, and the importance of atom featurisation is of
Externí odkaz:
http://arxiv.org/abs/2012.04444
We investigate the problem of training neural networks from incomplete images without replacing missing values. For this purpose, we first represent an image as a graph, in which missing pixels are entirely ignored. The graph image representation is
Externí odkaz:
http://arxiv.org/abs/2010.13914
Autor:
Maziarka, Łukasz, Śmieja, Marek, Sendera, Marcin, Struski, Łukasz, Tabor, Jacek, Spurek, Przemysław
Publikováno v:
2021, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
We propose OneFlow - a flow-based one-class classifier for anomaly (outlier) detection that finds a minimal volume bounding region. Contrary to density-based methods, OneFlow is constructed in such a way that its result typically does not depend on t
Externí odkaz:
http://arxiv.org/abs/2010.03002
Autor:
Maziarka, Łukasz, Danel, Tomasz, Mucha, Sławomir, Rataj, Krzysztof, Tabor, Jacek, Jastrzębski, Stanisław
Publikováno v:
Graph Representation Learning workshop and Machine Learning and the Physical Sciences workshop at NeurIPS 2019
Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug discovery ind
Externí odkaz:
http://arxiv.org/abs/2002.08264
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.