AI News, BOOK REVIEW: Speaker: Sophie Watson: Machine learning training

AAAI-20 Tutorial Forum

In several real-world scenarios, decision making involves complex reasoning, i.e., the ability to answer complex probabilistic queries (e.g., involving logical constraints), which allow only a limited amount of time to be answered.

On one side of the spectrum we have recent neural estimators, e.g., variational autoencoders, which have very limited inference capabilities, and intractable classical probabilistic graphical models like bayesian and markov networks.

Lastly, we will showcase several successful application scenarios where probabilistic circuits have been employed as an alternative to or in conjunction with intractable models, including image classification, completion and generation, scene understanding, activity recognition, language and speech modeling, bioinformatics, collaborative filtering, verification and diagnosis.