1 code implementation • 12 May 2023 • Enes Altuncu, Jason R. C. Nurse, Meryem Bagriacik, Sophie Kaleba, Haiyue Yuan, Lisa Bonheme, Shujun Li
In this highly digitised world, fake news is a challenging problem that can cause serious harm to society.
1 code implementation • 21 Apr 2023 • Lisa Bonheme, Marek Grzes
Variational autoencoders (VAEs) are used for transfer learning across various research domains such as music generation or medical image analysis.
no code implementations • 2 Mar 2023 • Théophile Champion, Marek Grześ, Lisa Bonheme, Howard Bowman
The goal of this activity is to solve more complicated tasks using deep active inference.
1 code implementation • 26 Sep 2022 • Lisa Bonheme, Marek Grzes
We show that the discrepancies between the IDE of the mean and sampled representations of a VAE after only a few steps of training reveal the presence of passive variables in the latent space, which, in well-behaved VAEs, indicates a superfluous number of dimensions.
1 code implementation • 17 May 2022 • Lisa Bonheme, Marek Grzes
The ability of Variational Autoencoders (VAEs) to learn disentangled representations has made them popular for practical applications.
1 code implementation • 26 Sep 2021 • Lisa Bonheme, Marek Grzes
However, their mean representations, which are generally used for downstream tasks, have recently been shown to be more correlated than their sampled counterpart, on which disentanglement is usually measured.
no code implementations • SEMEVAL 2020 • Lisa Bonheme, Marek Grzes
This paper presents our submission to task 8 (memotion analysis) of the SemEval 2020 competition.