36. TAKEAWAYS 📚
• Signals are everywhere
• Autoregressive CNN > CNN > RNN
• Cluster in embedding space
• Use GANs not just to generate
• Combine DL and classics if you can
• It works for NLP, speech and other sequences as well!
38. Home reading
1. When Recurrent Models Don't Need To Be Recurrent
2. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
3. DEEP TEMPORAL CLUSTERING: FULLY UNSUPERVISED LEARNING OF TIME-DOMAIN FEATURES
4. REAL-VALUED (MEDICAL) TIME SERIES GENERATION WITH RECURRENT CONDITIONAL GANS
5. Time-series Extreme Event Forecasting with Neural Networks at Uber
FB: @rachnogstyle
MEDIUM: @alexrachnog
Hinweis der Redaktion
Wind speed, temperature, pressure, sun spots
Animal and bacterias populations
Economy, finance, exchange rates, spreads
Marketing: activity of business, sales
Industry: electric load, power consumption, voltage, sensors
Web: clicks, logs
Genomics: time series of gene expression during cell cycle
Biomedicine: physiological signals (EEG), heart-rate, patient temperature.