Skip to content
- vaeST: A Two-Stage Longitudinal Variational Autoencoder for Spatiotemporal Data (Author: Samuel Berchuck)
- This is supplementary code for the following two manuscripts:
- Berchuck, S., Mukherjee, S., and Medeiros, F. “Estimating Rates of Progression and Predicting Future Visual Fields in Glaucoma Using a Deep Variational Autoencoder”. Scientific Reports (2019).
- Berchuck, S., Medeiros, F., and Mukherjee, S. “Scalable Modeling of Spatiotemporal Data using the Variational Autoencoder: an Application in Glaucoma”. Under Revision.
-
![](https://sites.duke.edu/sib2/files/2019/11/vaeST-300x300.png)
- spBFA: Spatial Bayesian Factor Analysis (Author: Samuel Berchuck)
- Berchuck, S., Janko, M., Pan, W., Medeiros, F., and Mukherjee, S. “Bayesian Non-Parametric Factor Analysis for Longitudinal Spatial Surfaces”. Under Revision.
![](https://sites.duke.edu/sib2/files/2019/11/spbfa-300x120.png)
- spCP: Spatially Varying Change Points (Author: Samuel Berchuck)
- Berchuck S.I., Mwanza J.C., and Warren J.L. A spatially varying change points model for monitoring glaucoma progression using visual field data, Spatial Statistics (2019).
![](https://sites.duke.edu/sib2/files/2018/11/yep-300x189.png)
![](https://sites.duke.edu/sib2/files/2018/11/womblR-300x212.png)