Neural network autoencoders for unevenly sampled time series

Code accompanying "An unsupervised neural network that outperforms on classification of unevenly sampled time series".

• Code for scores/figures is found in figures.ipynb
• Autoencoder network architecture is defined in autoencoder.py
• Experiments for simulated data are found in autoencoder.main
• Experiments for light curve data are found in survey_autoencoder.main
  • Light curve data is in ./data
• Model weights are saved in ./keras_logs