Blogs on probabilistic ML » Lamarr Institute

00 Blog Becker Einfuehrung in Sum Product Networks - Lamarr Institute for Machine Learning (ML) and Artificial Intelligence (AI)

Sum-Product Networks – A new deep architecture for Machine Learning

12. July 2022

Clear semantics with reference to training data, learning of structure and parameters, efficient inference and versatile applicability: this is what Sum-Product Networks combine - a new type of model architecture for Machine Learning....

Plants don’t walk on the street: Using human knowledge for reliable semantic segmentation

17. November 2021

Data-driven sensor interpretation in autonomous driving can sometimes lead to very implausible predictions. A partly human-designed, partly learned rule set can make existing deep neural networks that process low-level sensor information reliable....

Preparation of incomplete data with Markov Random Fields

13. January 2021

In data with gaps, learning models can be challenging and in some cases even impossible. However, generative approaches can assist by filling in incomplete data with meaningful approximations....