1 code implementation • 6 Mar 2024 • Håkon Hanisch Kjærnli, Lluis Mas-Ribas, Aida Ashrafi, Gleb Sizov, Helge Langseth, Odd Erik Gundersen
Because most of the training data does not reflect such changes, the models present poor performance on the new out-of-distribution scenarios and, therefore, the impact of such events cannot be reliably anticipated ahead of time.
no code implementations • 16 Dec 2023 • Inga Strümke, Helge Langseth
The diffusion model learns the data manifold to which the original and thus the reconstructed data samples belong, by training on a large number of data points.
1 code implementation • 29 Aug 2023 • Bjørnar Vassøy, Helge Langseth, Benjamin Kille
An emerging definition of fairness in machine learning requires that models are oblivious to demographic user information, e. g., a user's gender or age should not influence the model.
no code implementations • 16 May 2023 • Bjørnar Vassøy, Helge Langseth
In the current landscape of ever-increasing levels of digitalization, we are facing major challenges pertaining to scalability.
no code implementations • 10 Aug 2022 • Emil Blixt Hansen, Helge Langseth, Nadeem Iftikhar, Simon Bøgh
With ModularHI, the operator chooses which sensor inputs are available, and then ModularHI will compute a baseline model based on data collected during a burn-in state.
no code implementations • 29 Apr 2021 • Yanzhe Bekkemoen, Helge Langseth
Several explanation methods have been developed, but they do not provide mechanisms for users to interact with the explanations.
1 code implementation • 19 Jul 2020 • Tárik S. Salem, Helge Langseth, Heri Ramampiaro
The ensembled prediction intervals are aggregated as a split normal mixture accounting for possible multimodality and asymmetricity of the posterior predictive distribution, and resulting in prediction intervals that capture aleatoric and epistemic uncertainty.
no code implementations • 15 Jan 2020 • Bjørn Magnus Mathisen, Agnar Aamodt, Kerstin Bach, Helge Langseth
The main motivation for this work is to automate the construction of similarity measures using machine learning, while keeping training time as low as possible.
2 code implementations • 9 Aug 2019 • Andrés R. Masegosa, Rafael Cabañas, Helge Langseth, Thomas D. Nielsen, Antonio Salmerón
Recent advances in statistical inference have significantly expanded the toolbox of probabilistic modeling.
no code implementations • 1 Feb 2019 • Tárik S. Salem, Karan Kathuria, Heri Ramampiaro, Helge Langseth
Keeping the electricity production in balance with the actual demand is becoming a difficult and expensive task in spite of an involvement of experienced human operators.
no code implementations • 24 Jan 2019 • Georgios K. Pitsilis, Heri Ramampiaro, Helge Langseth
This work addresses the challenges related to attacks on collaborative tagging systems, which often comes in a form of malicious annotations or profile injection attacks.
no code implementations • 7 Oct 2018 • Ming Zeng, Haoxiang Gao, Tong Yu, Ole J. Mengshoel, Helge Langseth, Ian Lane, Xiaobing Liu
To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention.
1 code implementation • 13 Jan 2018 • Georgios K. Pitsilis, Heri Ramampiaro, Helge Langseth
This paper addresses the important problem of discerning hateful content in social media.
no code implementations • 7 Dec 2017 • Basant Agarwal, Heri Ramampiaro, Helge Langseth, Massimiliano Ruocco
Our experimental results show that the proposed approach outperforms existing state-of-the-art approaches on user-generated noisy social media data, such as Twitter texts, and achieves highly competitive performance on a cleaner corpus.
no code implementations • ICML 2017 • Andres Masegosa, Thomas D. Nielsen, Helge Langseth, Dario Ramos-Lopez, Antonio Salmeron, Anders L. Madsen
Making inferences from data streams is a pervasive problem in many modern data analysis applications.
1 code implementation • 22 Jun 2017 • Massimiliano Ruocco, Ole Steinar Lillestøl Skrede, Helge Langseth
In recent years, research has been done on applying Recurrent Neural Networks (RNNs) as recommender systems.
1 code implementation • 4 Apr 2017 • Andrés R. Masegosa, Ana M. Martínez, Darío Ramos-López, Rafael Cabañas, Antonio Salmerón, Thomas D. Nielsen, Helge Langseth, Anders L. Madsen
The AMIDST Toolbox is a software for scalable probabilistic machine learning with a spe- cial focus on (massive) streaming data.