CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting.
Gerald WooChenghao LiuDoyen SahooAkshat KumarSteven C. H. HoiPublished in: ICLR (2022)
Keyphrases
- learning algorithm
- learning tasks
- learning systems
- knowledge acquisition
- online learning
- data sets
- active learning
- external representations
- learning scheme
- empirical studies
- learning process
- prior knowledge
- support vector machine
- artificial neural networks
- reinforcement learning
- information systems
- short term
- genetic algorithm
- learning problems
- machine learning
- neural network