In this video, we take a quick look at five overlooked neuro symbolic AI papers from 2022.
Badreddine et al., "Logic Tensor Networks (journal version)," AIJ 2022
https://www.sciencedirect.com/science/article/abs/pii/S0004370221002009
Sen et al., "Logical Neural Networks for Knowledge Base Completion with Embeddings & Rules," EMNLP 2022
https://preview.aclanthology.org/emnlp-22-ingestion/2022.emnlp-main.255.pdf
Kamienny et al., "End-to-end Symbolic Regression with Transformers," NeurIPS 2022
https://openreview.net/pdf?id=GoOuIrDHG_Y
Nandwani et al., "A Solver-Free Framework for Scalable Learning in Neural ILP Architectures," NeurIPS 2022
https://openreview.net/pdf?id=EqZuN4V_FLF
Shakarian and Simari, "Extensions to Generalized Annotated Logic and an Equivalent Neural Architecture," TransAI 2022
https://ieeexplore.ieee.org/document/9951514
About the channel:
The Neuro Symbolic Channel provides the tutorials, courses, and research results on one of the most exciting areas in artificial intelligence and machine learning. With content originally from the AI course taught at Arizona State University, this channel brings you the latest at the intersection of symbolic methods (e.g., logic programming) and deep learning. Learn about the latest algorithms, Python packages, and progress toward larger goals such as artificial general intelligence (AGI).