Probabilistic Deep Learning via Hierarchical Stochastic Partial Differential Equations

  • Hostettler, Roland (Project Member)
  • Karvonen, Toni (Project Member)
  • Särkkä, Simo (Principal investigator)
  • Bahrami Rad, Ali (Project Member)
  • Emzir, Muhammad (Project Member)
  • Gao, Rui (Project Member)
  • Sarmavuori, Juha (Project Member)
  • Tronarp, Filip (Project Member)
  • Raitoharju, Matti (Project Member)
  • Purisha, Zenith (Project Member)

Project Details


Deep learning, using either artificial neural networks or probabilistic deep Gaussian processes, is a popular machine learning technique with a strong optimization-based engineering tradition that has obtained its popularity through the ever-increasing computational power. In this project, our aim is to develop a novel family of hierarchical stochastic partial differential equation models and methods which can be used to replace deep GPs as scalable fully probabilistic alternatives to the problem of deep learning. This leads to computational advantages and clear statistical interpretation of all the random fields and parameters. The project includes a vivid industry-academia linkage, with internships to both sides as well as research visits to internationally well-known universities.
Short titleDEEP-SPDE
Effective start/end date01/01/201831/12/2019

UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):

  • SDG 7 - Affordable and Clean Energy


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.