no code implementations • 19 Jan 2023 • Guanpu Chen, Gehui Xu, Fengxiang He, Yiguang Hong, Leszek Rutkowski, DaCheng Tao
This paper takes conjugate transformation to the formulation of non-convex multi-player games, and casts the complementary problem into a variational inequality (VI) problem with a continuous pseudo-gradient mapping.
no code implementations • 24 Oct 2022 • Mateusz Godzik, Jacek Dajda, Marek Kisiel-Dorohinicki, Aleksander Byrski, Leszek Rutkowski, Patryk Orzechowski, Joost Wagenaar, Jason H. Moore
The discussed modifications are evaluated based on a number of difficult continuous-optimization benchmarks.
no code implementations • 12 Dec 2021 • Shiye Lei, Zhuozhuo Tu, Leszek Rutkowski, Feng Zhou, Li Shen, Fengxiang He, DaCheng Tao
Bayesian neural networks (BNNs) have become a principal approach to alleviate overconfident predictions in deep learning, but they often suffer from scaling issues due to a large number of distribution parameters.
no code implementations • 13 Jul 2020 • Paweł Staszewski, Maciej Jaworski, Jinde Cao, Leszek Rutkowski
The idea of neural codes, based on fully connected layers activations, is extended by incorporating the information contained in convolutional layers.
no code implementations • 8 Jul 2019 • Patryk Najgebauer, Rafal Scherer, Leszek Rutkowski
Image compression is one of the essential methods of image processing.
no code implementations • 5 Oct 2016 • Krzysztof Cpalka, Marcin Zalasinski, Leszek Rutkowski
Vertical sections correspond to the initial, middle, and final time moments of the signing process.
no code implementations • 4 Oct 2016 • Marcin Korytkowski, Leszek Rutkowski, Rafał Scherer
This paper presents a novel approach to visual objects classification based on generating simple fuzzy classifiers using local image features to distinguish between one known class and other classes.
no code implementations • 26 Apr 2015 • Patryk Najgebauer, Janusz Rygal, Tomasz Nowak, Jakub Romanowski, Leszek Rutkowski, Sviatoslav Voloshynovskiy, Rafal Scherer
For this purpose, we use a certain level of tolerance between values of descriptors, as values of feature descriptors are almost never equal but similar between different images.