25 citations · 26 across the 3 of their papers we have counts for
3 papers
cs.AI2024
Learning with Logical Constraints but without Shortcut Satisfaction
Zenan Li, Zehua Liu, Yuan Yao +4
Recent studies in neuro-symbolic learning have explored the integration of logical knowledge into deep learning via encoding logical constraints as an additional loss function. How…
cs.AI2024★ 1 cited
Softened Symbol Grounding for Neuro-symbolic Systems
Zenan Li, Yuan Yao, Taolue Chen +4
Neuro-symbolic learning generally consists of two separated worlds, i.e., neural network training and symbolic constraint solving, whose success hinges on symbol grounding, a funda…
cs.LG2019★ 25 cited
Operational Calibration: Debugging Confidence Errors for DNNs in the Field
Zenan Li, Xiaoxing Ma, Chang Xu +3
Trained DNN models are increasingly adopted as integral parts of software systems, but they often perform deficiently in the field. A particularly damaging problem is that DNN mode…