DeepProbCEP is a neuro-symbolic architecture based on Event Calculus and Logic Programming that can perform Complex Event Processing (CEP), i.e. detecting patterns of interrelated events that form situations of interest, in particular when they tend to be uncommon, which means that only sparse, noisy data is available.
DeepProbCEP features in
Relevant DeepProbCEP publications are:
- Marc Vilamala, Liam Hiley, Yulia Hicks, Alun Preece, Federico Cerutti, A Pilot Study on Detecting Violence in Videos Fusing Proxy Models, Fusion 2019, 2019.
- Marc Vilamala, Harrison Taylor, Tianwei Xing, Luis Garcia, Mani Srivastava, Lance Kaplan, Alun Preece, Angelika Kimmig, Federico Cerutti, DeepProbCEP: A Hybrid Neuro-Symbolic Approach for Complex Event Processing in Noisy and Adversarial Settings, ICLP 2020, 2020.