深度学习与时间序列 Auto Encoder Journal 2016

2016

• Li, X.ac, Peng, L.a, Hu, Y.ac, Shao, J.b, Chi, T.a (2016). Deep learning architecture for air quality predictions. Environmental Science and Pollution Research. 23(22), pages 22408-22417

  Summary: This paper proposed a novel spatiotemporal deep learning (STDL)-based air quality prediction method that inherently considers spatial and temporal correlations. A stacked autoencoder (SAE) model is used to extract inherent air quality features.

  Notes:

  • Model Train -> greedy layer-wise manner
  • Top layer -> logistic regression
  • Fine-tuning connection weights -> Back-propagation
  • Model sizes -> several ccombinations