Neuro Causal and Symbolic AI

General statement. We plan to invite two types of submissions:

1. Research papers that discuss novel research within nCSI.
2. Retrospective papers discussing both the impact, consequences, and lessons learned from classical papers within nCSI and the connection within topics of the nCSI spectrum themselves.

Research Topics. Topics of interest comprise, but are not limited to:

• new methods on combining symbolic- and causal reasoning with (neural) learning module
• learning algorithms and architectures for neural-causal models
• theoretical and empirical analysis of symbolic/causal models
• applications of nCSI methods to real world problems

To provide a heads-up for topics which are not listed above, but that are welcome at the workshop:

• structured / relational / lifted methods for reasoning and representation learning
• object-centric methods for inference and learning grounded in cognition (such as intuitive causal or physics reasoning)

Submission Policy:

• Submissions should be of 4 to 5 pages length, excluding references. We ask authors to use the supplementary material only for minor details that do not fit in the main paper.
• Papers should be fully anonymized for double-blind review.
• Papers should use the NeurIPS 2022 style file.
• We welcome submissions that are currently under review at other venues but they need abide by the other points in this submission policy.
• We welcome submissions that have been published elsewhere as long as they are being adapted to the discussion of nCSI and abide by the other points in this submission policy.