1 code implementation • 23 Oct 2023 • Szymon Bobek, Grzegorz J. Nalepa
We tested our method on real and synthetic datasets and compared it with state-of-the-art rule-based explainers such as LORE, EXPLAN and Anchor.
no code implementations • 8 Jun 2023 • Sepideh Pashami, Slawomir Nowaczyk, Yuantao Fan, Jakub Jakubowski, Nuno Paiva, Narjes Davari, Szymon Bobek, Samaneh Jamshidi, Hamid Sarmadi, Abdallah Alabdallah, Rita P. Ribeiro, Bruno Veloso, Moamar Sayed-Mouchaweh, Lala Rajaoarisoa, Grzegorz J. Nalepa, João Gama
We provide an overview of predictive maintenance tasks and accentuate the need and varying purposes for corresponding explanations.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
1 code implementation • 8 Feb 2023 • Victor Rodriguez-Fernandez, David Montalvo, Francesco Piccialli, Grzegorz J. Nalepa, David Camacho
DeepVATS trains, in a self-supervised way, a masked time series autoencoder that reconstructs patches of a time series, and projects the knowledge contained in the embeddings of that model in an interactive plot, from which time series patterns and anomalies emerge and can be easily spotted.
1 code implementation • IEEE Access 2022 • Szymon Bobek, Michal Kuk, Maciej Szelążek, Grzegorz J. Nalepa
In most cases, such application is based on the transformation of an unsupervised clustering task into a supervised one and providing generalised global explanations or local explanations based on cluster centroids.
1 code implementation • 16 Dec 2021 • Szymon Bobek, Michał Kuk, Jakub Brzegowski, Edyta Brzychczy, Grzegorz J. Nalepa
We argue that this can be the bottleneck in the process, especially in cases where domain knowledge exists prior to clustering.
no code implementations • 29 Jul 2020 • Krzysztof Kutt, Dominika Drążyk, Maciej Szelążek, Szymon Bobek, Grzegorz J. Nalepa
The paper describes BIRAFFE2 data set, which is a result of an affective computing experiment conducted between 2019 and 2020, that aimed to develop computer models for classification and recognition of emotion.
no code implementations • 18 Sep 2019 • Mateusz Ślażyński, Salvador Abreu, Grzegorz J. Nalepa
Local Search meta-heuristics have been proven a viable approach to solve difficult optimization problems.