no code implementations • 7 Feb 2024 • Ali Amirahmadi, Mattias Ohlsson, Kobra Etminani, Olle Melander, Jonas Björk
Using electronic health records data and machine learning to guide future decisions needs to address challenges, including 1) long/short-term dependencies and 2) interactions between diseases and interventions.
no code implementations • 1 Dec 2023 • Hamid Sarmadi, Thorsteinn Rögnvaldsson, Nils Roger Carlsson, Mattias Ohlsson, Ibrahim Wahab, Ola Hall
Deep convolutional neural networks (CNNs) have been shown to predict poverty and development indicators from satellite images with surprising accuracy.
no code implementations • 2 Mar 2022 • Ola Hall, Mattias Ohlsson, Thortseinn Rögnvaldsson
Our review of the field shows that the status of the three core elements of explainable machine learning (transparency, interpretability and domain knowledge) is varied and does not completely fulfill the requirements set up for scientific insights and discoveries.
1 code implementation • 28 Feb 2022 • Abdallah Alabdallah, Mattias Ohlsson, Sepideh Pashami, Thorsteinn Rögnvaldsson
In contrast to such deep learning methods, classical machine learning models deteriorate when the censoring level decreases due to their inability to improve on ranking the events versus other events.
1 code implementation • 16 Nov 2020 • Alexander Galozy, Slawomir Nowaczyk, Mattias Ohlsson
We present an algorithm that uses a referee to dynamically combine the policies of a contextual bandit and a multi-armed bandit.
1 code implementation • 6 Apr 2020 • Najmeh Abiri, Mattias Ohlsson
We propose a new structure for the variational auto-encoders (VAEs) prior, with the weakly informative multivariate Student's t-distribution.
no code implementations • 6 Apr 2020 • Najmeh Abiri, Björn Linse, Patrik Edén, Mattias Ohlsson
Dealing with missing data in data analysis is inevitable.
no code implementations • 25 Sep 2019 • Najmeh Abiri, Mattias Ohlsson
Is it optimal to use the standard Gaussian prior in variational autoencoders?