Awesome Easy-to-Use Deep Time Series Modeling based on PaddlePaddle, including comprehensive functionality modules like TSDataset, Analysis, Transform, Models, AutoTS, and Ensemble, etc., supporting versatile tasks like time series forecasting, representation learning, and anomaly detection, etc., featured with quick tracking of SOTA deep models.

cost informer time-series-analysis paddlepaddle time-series-forecasting time-series-models deepar time-series-anomaly-detection n-beats nbeats nhits paddlets ts2vec n-hits time-series-representation-learning

• Updated Apr 17, 2026
• Python

End-to-end ML pipeline predicting TV ad memorability from EEG brain signals. Compares handcrafted spectral features vs. deep temporal embeddings (TS2Vec, FEMBA) for unaided recall classification. MSc thesis — Politecnico di Milano.

python machine-learning time-series thesis scikit-learn eeg classification polimi marketing-analytics thesis-project ts2vec advertising-analytics neuromarketing

• Updated Apr 24, 2026
• Jupyter Notebook

Develop a self-supervised learning algorithm to extract deep features from millions of unlabeled signal data to identify abnormal driving behaviors

deep-learning time-series signal transfer-learning abnormal-behavior-detection self-supervised-learning abnormal-detection ts2vec

• Updated Mar 26, 2023
• Jupyter Notebook