Learning and logic are distinct and remarkable approaches to prediction. Machine learning has experienced a surge in popularity because it is robust to noise and achieves high performance; however, ML experiences many issues with knowledge transfer and extrapolation. In contrast, logic is easily intepreted, and logical rules are easy to chain and transfer between systems; however, inductive logic is brittle to noise. We then explore the premise of combining learning with inductive logic into AI Reasoning Systems. Specifically, we summarize findings from PAC learning (conceptual graphs, robust logics, knowledge infusion) and deep learning (DSRL, $\partial$ILP, DeepLogic) by reproducing proofs of tractability, presenting algorithms in pseudocode, highlighting results, and synthesizing between fields. We conclude with suggestions for integrated models by combining the modules listed above and with a list of unsolved (likely intractable) problems.
Conditional Performance Guarantee for Large Reasoning Models
Nanyang Technological University, Singapore(南洋理工大学);Southern University of Science(南方科技大学);The Chinese University of Hong Kong, Shenzhen, China(香港中文大学(深圳))
Department of Statistics and Data Science(统计与数据科学系);Department of Statistics(统计系);Data Science, Southern University of Science(数据科学,南方科技大学);College of Computing(计算学院);College of Computing and Data Science(计算与数据科学学院);School of Statistics(统计学系);School of Statistics and Data Science(统计与数据科学系);School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen(人工智能学院,香港中文大学(深圳));Shenzhen Loop Area Institute(深圳河套学院)