Výsledky vyhledávání - "KSIĄŻEK, KAMIL"

Report

HyperInterval: Hypernetwork approach to training weight interval regions in continual learning

Autor: Krukowski, Patryk, Bielawska, Anna, Książek, Kamil, Wawrzyński, Paweł, Batorski, Paweł, Spurek, Przemysław

Recently, a new Continual Learning (CL) paradigm was presented to control catastrophic forgetting, called Interval Continual Learning (InterContiNet), which relies on enforcing interval constraints on the neural network parameter space. Unfortunately

Externí odkaz: http://arxiv.org/abs/2405.15444

Zobrazit plný text záznamu

Report

HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning

Autor: Książek, Kamil, Spurek, Przemysław

Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. Many continual learning (CL) strategies are trying to overcome this problem. One of the most effective is the hypernetwork-based appr

Externí odkaz: http://arxiv.org/abs/2310.00113

Zobrazit plný text záznamu

Report

Improving Autoencoder Training Performance for Hyperspectral Unmixing with Network Reinitialisation

Autor: Książek, Kamil, Głomb, Przemysław, Romaszewski, Michał, Cholewa, Michał, Grabowski, Bartosz, Búza, Krisztián

Neural networks, in particular autoencoders, are one of the most promising solutions for unmixing hyperspectral data, i.e. reconstructing the spectra of observed substances (endmembers) and their relative mixing fractions (abundances), which is neede

Externí odkaz: http://arxiv.org/abs/2109.13748

Zobrazit plný text záznamu

Akademický článek

Assessment of symptom severity in psychotic disorder patients based on heart rate variability and accelerometer mobility data

Autor: Książek, Kamil, Masarczyk, Wilhelm, Głomb, Przemysław, Romaszewski, Michał, Stokłosa, Iga, Ścisło, Piotr, Dębski, Paweł, Pudlo, Robert, Buza, Krisztián, Gorczyca, Piotr, Piegza, Magdalena

Publikováno v: In Computers in Biology and Medicine June 2024 176

Zobrazit plný text záznamu

Report

Hard hat wearing detection based on head keypoint localization

Autor: Wójcik, Bartosz, Żarski, Mateusz, Książek, Kamil, Miszczak, Jarosław Adam, Skibniewski, Mirosław Jan

Publikováno v: Bull. Pol. Acad. Sci. Tech. Sci. Vol. 71, No. 6, pp. e147340 (2023)

In recent years, a lot of attention is paid to deep learning methods in the context of vision-based construction site safety systems, especially regarding personal protective equipment. However, despite all this attention, there is still no reliable

Externí odkaz: http://arxiv.org/abs/2106.10944

Zobrazit plný text záznamu

Report

Hyperspectral classification of blood-like substances using machine learning methods combined with genetic algorithms in transductive and inductive scenarios

Autor: Pałka, Filip, Książek, Wojciech, Pławiak, Paweł, Romaszewski, Michał, Książek, Kamil

This study is focused on applying genetic algorithms (GA) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspectral images with blood and five visually similar substances to test GA-

Externí odkaz: http://arxiv.org/abs/2011.02188

Zobrazit plný text záznamu