Predictive variational autoencoder for learning robust representations of time-series data
Variational autoencoders (VAEs) have been used extensively to discover low-dimensional latent factors governing neural activity and animal behavior. However, without careful model selection, the uncovered latent factors may reflect noise in the data rather than true underlying features, rendering such representations unsuitable for scientific interpretation. Existing solutions to this problem involve introducing additional measured variables or data augmentations specific to a particular data type. We propose a VAE architecture that predicts the next point in time and show that it mitigates the learning of spurious features. In addition, we introduce a model selection metric based on smoothness over time in the latent space. We show that together these two constraints on VAEs to be smooth over time produce robust latent representations and faithfully recover latent factors on synthetic datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Model SelectionTime SeriesSimilar Papers 제목 키워드 기반
Hybrid Variational Autoencoder for Time Series Forecasting
Variational autoencoders (VAE) are powerful generative models that learn the latent representations of input data as random variables. Recent studies show that VAE can flexibly learn the complex temporal dynamics of time…
Time SeriesTime Series AnalysisTime Series ForecastingVariational InferenceOn Disentanglement in Gaussian Process Variational Autoencoders
Complex multivariate time series arise in many fields, ranging from computer vision to robotics or medicine. Often we are interested in the independent underlying factors that give rise to the high-dimensional data we ar…
DisentanglementTime SeriesTime Series AnalysisLearning Disentangled Representations of Satellite Image Time Series
In this paper, we investigate how to learn a suitable representation of satellite image time series in an unsupervised manner by leveraging large amounts of unlabeled data. Additionally , we aim to disentangle the repres…
Change Detectionimage-classificationImage ClassificationImage Retrieval+7EXCODER: EXplainable Classification Of DiscretE time series Representations
Deep learning has significantly improved time series classification, yet the lack of explainability in these models remains a major challenge. While Explainable AI (XAI) techniques aim to make model decisions more transp…
Time Series ClassificationTime Series AnalysisAnomaly Detection of Wind Turbine Time Series using Variational Recurrent Autoencoders
Ice accumulation in the blades of wind turbines can cause them to describe anomalous rotations or no rotations at all, thus affecting the generation of electricity and power output. In this work, we investigate the probl…
Anomaly DetectionTime SeriesTime Series Analysis