IBM Neuro-Symbolic AI Summer School Day 1: Logical Neural Networks (Makondo)

LNN — single model for neural and logical, weighted Łukasiewicz logic, sound and complete, gradient-based optimization.

IBM Neuro-Symbolic AI Summer School 2022. Image: LinkedIn.

IBM NeuroSymbolicAI Summer School 2022 Day 1: Logical Neural Networks (LNN) given by Ndivhuwo MAKONDO:

• One single model for both neural and logical representations
• Weighted Łukasiewicz (real-valued) logic
• Proven to be sound and strongly complete
• Upward/downward (reverse) inference
• Uncertainty bounds allow representations of “don’t-know” and contradiction
• Gradient-based optimization

Ryan Riegel, Alexander Gray, Francois Luus, Naweed Khan, Ndivhuwo MAKONDO, Ismail Yunus Akhalwaya, Haifeng Qian, et al. 2020. “Logical Neural Networks.” arXiv [cs.AI]. arXiv. http://arxiv.org/abs/2006.13155.

Summer School site: https://ibm.github.io/neuro-symbolic-ai/events/ns-summerschool2022/

Originally posted on LinkedIn.