Zobrazeno 1 - 10
of 847
pro vyhledávání: '"Smieja, Marek"'
Autor:
Gaiński, Piotr, Koziarski, Michał, Maziarz, Krzysztof, Segler, Marwin, Tabor, Jacek, Śmieja, Marek
Single-step retrosynthesis aims to predict a set of reactions that lead to the creation of a target molecule, which is a crucial task in molecular discovery. Although a target molecule can often be synthesized with multiple different reactions, it is
Externí odkaz:
http://arxiv.org/abs/2406.18739
Collaborative self-supervised learning has recently become feasible in highly distributed environments by dividing the network layers between client devices and a central server. However, state-of-the-art methods, such as MocoSFL, are optimized for n
Externí odkaz:
http://arxiv.org/abs/2406.08267
Autor:
Suwała, Adrian, Wójcik, Bartosz, Proszewska, Magdalena, Tabor, Jacek, Spurek, Przemysław, Śmieja, Marek
Conditional GANs are frequently used for manipulating the attributes of face images, such as expression, hairstyle, pose, or age. Even though the state-of-the-art models successfully modify the requested attributes, they simultaneously modify other i
Externí odkaz:
http://arxiv.org/abs/2309.12033
Graph Neural Networks (GNNs) play a fundamental role in many deep learning problems, in particular in cheminformatics. However, typical GNNs cannot capture the concept of chirality, which means they do not distinguish between the 3D graph of a chemic
Externí odkaz:
http://arxiv.org/abs/2307.02198
Autor:
Przewięźlikowski, Marcin, Pyla, Mateusz, Zieliński, Bartosz, Twardowski, Bartłomiej, Tabor, Jacek, Śmieja, Marek
Self-supervised learning (SSL) is a powerful technique for learning robust representations from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo are able to reach quality on par with super
Externí odkaz:
http://arxiv.org/abs/2306.06082
Nowadays artificial neural network models achieve remarkable results in many disciplines. Functions mapping the representation provided by the model to the probability distribution are the inseparable aspect of deep learning solutions. Although softm
Externí odkaz:
http://arxiv.org/abs/2304.05243
Deep learning has achieved impressive performance in many domains, such as computer vision and natural language processing, but its advantage over classical shallow methods on tabular datasets remains questionable. It is especially challenging to sur
Externí odkaz:
http://arxiv.org/abs/2304.03543
Deep clustering has been dominated by flat models, which split a dataset into a predefined number of groups. Although recent methods achieve an extremely high similarity with the ground truth on popular benchmarks, the information contained in the fl
Externí odkaz:
http://arxiv.org/abs/2303.03389
Continual Learning aims to bring machine learning into a more realistic scenario, where tasks are learned sequentially and the i.i.d. assumption is not preserved. Although this setting is natural for biological systems, it proves very difficult for m
Externí odkaz:
http://arxiv.org/abs/2207.04874
Deep neural networks present impressive performance, yet they cannot reliably estimate their predictive confidence, limiting their applicability in high-risk domains. We show that applying a multi-label one-vs-all loss reveals classification ambiguit
Externí odkaz:
http://arxiv.org/abs/2206.13923