Reliable and Efficient Neuro-symbolic AI

Teaching methods

Frontal lectures, lab sessions, presentations by students

Assessment methods

• In order to pass the course students need a minimum of  80% class attendande
• The final grade is based on a presentation on the last day of the course. 

Bibliography

Darwiche, Adnan. Modeling and reasoning with Bayesian networks. Cambridge university press, 2009.
Darwiche, Adnan, and Pierre Marquis. "A knowledge compilation map." Journal of Artificial Intelligence Research 17 (2002): 229-264.
Xu, Jingyi, et al. "A semantic loss function for deep learning with symbolic knowledge." International conference on machine learning. PMLR, 2018.
Vergari, Antonio, et al. "A compositional atlas of tractable circuit operations for probabilistic inference." Advances in Neural Information Processing Systems 34 (2021): 13189-13201.
Maene, Jaron, Vincent Derkinderen, and Pedro Zuidberg Dos Martires. "KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI." The Thirteenth International Conference on Learning Representations.
Loconte, Lorenzo, et al. "What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?." Transactions on Machine Learning Research.

Further literature will be provided during the course.