1 code implementation • 13 Mar 2024 • John Martinsson, Olof Mogren, Maria Sandsten, Tuomas Virtanen
In this work we propose an audio recording segmentation method based on an adaptive change point detection (A-CPD) for machine guided weak label annotation of audio recording segments.
no code implementations • 7 Mar 2024 • Martin Willbo, Aleksis Pirinen, John Martinsson, Edvin Listo Zec, Olof Mogren, Mikael Nilsson
In this work we systematically examine model sensitivities with respect to several color- and texture-based distortions on the input EO data during inference, given models that have been trained without such distortions.
no code implementations • 22 Jun 2023 • Marcus Toftås, Emilie Klefbom, Edvin Listo Zec, Martin Willbo, Olof Mogren
Decentralized deep learning requires dealing with non-iid data across clients, which may also change over time due to temporal shifts.
no code implementations • 19 Jun 2023 • Edvin Listo Zec, Olof Mogren
The grammatical gender of Swedish nouns is a mystery.
1 code implementation • 4 Apr 2023 • Aleksis Pirinen, Olof Mogren, Mårten Västerdal
To the best of our knowledge, we are the first to tackle the task of dense water flow intensity prediction; earlier works have considered predicting flow intensities at a sparse set of locations at a time.
1 code implementation • 30 Jan 2023 • Edvin Listo Zec, Johan Östman, Olof Mogren, Daniel Gillblad
Personalized decentralized learning is a promising paradigm for distributed learning, enabling each node to train a local model on its own data and collaborate with other nodes to improve without sharing any data.
no code implementations • 23 Jun 2022 • Ebba Ekblom, Edvin Listo Zec, Olof Mogren
This is an even harder problem when the data is decentralized over several clients in a federated learning setup, as problems such as client drift and non-iid data make it hard for federated averaging to converge.
1 code implementation • 17 Jun 2022 • Edvin Listo Zec, Ebba Ekblom, Martin Willbo, Olof Mogren, Sarunas Girdzijauskas
We study the problem of training personalized deep learning models in a decentralized peer-to-peer setting, focusing on the setting where data distributions differ between the clients and where different clients have different local learning tasks.
1 code implementation • 18 Jul 2021 • Noa Onoszko, Gustav Karlsson, Olof Mogren, Edvin Listo Zec
We tackle the non-convex problem of learning a personalized deep learning model in a decentralized setting.
no code implementations • 1 Feb 2021 • Agrin Hilmkil, Sebastian Callh, Matteo Barbieri, Leon René Sütfeld, Edvin Listo Zec, Olof Mogren
We perform an extensive sweep over the number of clients, ranging up to 32, to evaluate the impact of distributed compute on task performance in the federated averaging setting.
no code implementations • 1 Jan 2021 • Edvin Listo Zec, John Martinsson, Olof Mogren, Leon René Sütfeld, Daniel Gillblad
In this paper, we propose a federated learning framework using a mixture of experts to balance the specialist nature of a locally trained model with the generalist knowledge of a global model in a federated learning setting.
1 code implementation • 5 Oct 2020 • Edvin Listo Zec, Olof Mogren, John Martinsson, Leon René Sütfeld, Daniel Gillblad
In federated learning, clients share a global model that has been trained on decentralized local client data.
1 code implementation • 16 Jun 2020 • David Ericsson, Adam Östberg, Edvin Listo Zec, John Martinsson, Olof Mogren
The model is trained in two steps: first to filter sensitive information in the spectrogram domain, and then to generate new and private information independent of the filtered one.
no code implementations • 14 Jun 2020 • John Martinsson, Edvin Listo Zec, Daniel Gillblad, Olof Mogren
Data privacy is an increasingly important aspect of many real-world Data sources that contain sensitive information may have immense potential which could be unlocked using the right privacy enhancing transformations, but current methods often fail to produce convincing output.
no code implementations • ICLR 2018 • Mikael Kågebäck, Olof Mogren
Deep neural networks have been tremendously successful in a number of tasks.
no code implementations • WS 2017 • Olof Mogren, Richard Johansson
We also show that using the auxiliary task of learning the relation type speeds up convergence and improves the prediction accuracy for the word generation task.
1 code implementation • WS 2016 • Simon Almgren, Sean Pavlov, Olof Mogren
We propose an approach for named entity recognition in medical data, using a character-based deep bidirectional recurrent neural network.
2 code implementations • 29 Nov 2016 • Olof Mogren
Generative adversarial networks have been proposed as a way of efficiently training deep generative neural networks.