Zobrazeno 1 - 10
of 7 008
pro vyhledávání: '"A. CICHOCKI"'
Normalizing flows, a category of probabilistic models famed for their capabilities in modeling complex data distributions, have exhibited remarkable efficacy in unsupervised anomaly detection. This paper explores the potential of normalizing flows in
Externí odkaz:
http://arxiv.org/abs/2409.00942
Autor:
Iannarelli, Daniele, Ingenito, Antonella, Napoli, Francesco, Cichocki, Filippo, Castaldo, Carmine, De Ninno, Antonella, Mannori, Simone, Cardinali, Alessandro, Taccogna, Francesco
This research work is part of a PhD project aiming to design a new helicon plasma thruster for cargo space missions, within a collaboration between the School of Aerospace Engineering of La Sapienza University and the ENEA Frascati research center. A
Externí odkaz:
http://arxiv.org/abs/2407.21457
This paper introduces a novel family of generalized exponentiated gradient (EG) updates derived from an Alpha-Beta divergence regularization function. Collectively referred to as EGAB, the proposed updates belong to the category of multiplicative gra
Externí odkaz:
http://arxiv.org/abs/2406.00655
Publikováno v:
Bulletin of the Polish Academy of Sciences: Technical Sciences, Vol 66, Iss No 6 (Special Section on Deep Learning: Theory and Practice), Pp 841-848 (2018)
Externí odkaz:
https://doaj.org/article/81768daaea504b11891efba3290294b8
Publikováno v:
Bulletin of the Polish Academy of Sciences: Technical Sciences, Vol 66, Iss No 6 (Special Section on Deep Learning: Theory and Practice), Pp 875-889 (2018)
Externí odkaz:
https://doaj.org/article/95d16acc70134dacb42a8d2c0cb7342c
Publikováno v:
Bulletin of the Polish Academy of Sciences: Technical Sciences, Vol 66, Iss No 6 (Special Section on Deep Learning: Theory and Practice), Pp 757-759 (2018)
Externí odkaz:
https://doaj.org/article/5cfefd1895584cec82886175e13e9519
This preprint presents the current status of research into the development and application of an autonomous, self-driving compost turner. The aim is to overcome challenges in the composting industry, such as adverse working conditions, by automating
Externí odkaz:
http://arxiv.org/abs/2401.13493
Autor:
Everts, Jeffrey C., Cichocki, Bogdan
Publikováno v:
Phys. Rev. Lett. 132, 218303 (2024)
Odd viscosity (OV) is a transport coefficient in, for example, fluids of self-spinning (active) particles or electrons in an external magnetic field. The key feature of OV is that it does not contribute to dissipation in two spatial dimensions. In co
Externí odkaz:
http://arxiv.org/abs/2308.09574
Autor:
Cherniuk, Daria, Abukhovich, Stanislav, Phan, Anh-Huy, Oseledets, Ivan, Cichocki, Andrzej, Gusak, Julia
Tensor decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks. Due to memory and power consumption limitations of mobile or embedded devices, the quantization step is usually nec
Externí odkaz:
http://arxiv.org/abs/2308.04595
In this paper, the problem of image super-resolution for Optical Coherence Tomography (OCT) has been addressed. Due to the motion artifacts, OCT imaging is usually done with a low sampling rate and the resulting images are often noisy and have low re
Externí odkaz:
http://arxiv.org/abs/2306.11750