no code implementations • 23 Jan 2024 • Nikita Kozodoi, Elizaveta Zinovyeva, Simon Valentin, João Pereira, Rodrigo Agundez
We also show that our approach produces article embeddings that encode article similarity and demand dynamics and are useful for other downstream business tasks beyond forecasting.
no code implementations • 18 Nov 2021 • João Pereira, Erik S. G. Stroes, Aeilko H. Zwinderman, Evgeni Levin
One of the most popular approaches to explain model global predictions is the permutation importance where the performance on permuted data is benchmarked against the baseline.
no code implementations • 17 Nov 2021 • Troy Maaslandand, João Pereira, Diogo Bastos, Marcus de Goffau, Max Nieuwdorp, Aeilko H. Zwinderman, Evgeni Levin
One of the most common pitfalls often found in high dimensional biological data sets are correlations between the features.
no code implementations • 1 Aug 2019 • João Pereira, Margarida Silveira
Unsupervised representation learning using deep generative models (e. g., variational autoencoders) has been used to learn expressive feature representations of sequences that can make downstream tasks, such as anomaly detection, easier to execute and more accurate.
no code implementations • 31 Jul 2019 • João Pereira, Albert Groen, Erik Stroes, Evgeni Levin
We propose the Graph Space Embedding (GSE), a technique that maps the input into a space where interactions are implicitly encoded, with little computations required.
no code implementations • 2019 IEEE International Conference on Big Data and Smart Computing (BigComp) 2019 • João Pereira, Margarida Silveira
Our results on the publicly available ECG5000 electrocardiogram dataset show the ability of the proposed approach to detect anomalous heartbeats in a fully unsupervised fashion, while providing structured and expressive data representations.
Ranked #1 on Unsupervised Anomaly Detection on ECG5000
no code implementations • 17 Dec 2018 • João Pereira, Margarida Silveira
In this paper, we propose a generic, unsupervised and scalable framework for anomaly detection in time series data, based on a variational recurrent autoencoder.