Search Results for author:
Found 7 papers, 5 papers with code
aedFaCT: Scientific Fact-Checking Made Easier via Semi-Automatic Discovery of Relevant Expert Opinions
In this highly digitised world, fake news is a challenging problem that can cause serious harm to society.
How good are variational autoencoders at transfer learning?
Variational autoencoders (VAEs) are used for transfer learning across various research domains such as music generation or medical image analysis.
Deconstructing deep active inference
The goal of this activity is to solve more complicated tasks using deep active inference.
FONDUE: an algorithm to find the optimal dimensionality of the latent representations of variational autoencoders
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.
How do Variational Autoencoders Learn? Insights from Representational Similarity
The ability of Variational Autoencoders (VAEs) to learn disentangled representations has made them popular for practical applications.
Be More Active! Understanding the Differences between Mean and Sampled Representations of Variational Autoencoders
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.
SESAM at SemEval-2020 Task 8: Investigating the Relationship between Image and Text in Sentiment Analysis of Memes
This paper presents our submission to task 8 (memotion analysis) of the SemEval 2020 competition.
