AI RESEARCH
In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks
arXiv CS.AI
•
ArXi:2603.15250v1 Announce Type: cross Symbolic regression aims to replace black-box predictors with concise analytical expressions that can be inspected and validated in scientific machine learning. Kolmogoro-Arnold Networks (KANs) are well suited to this goal because each connection between adjacent units (an "edge") is parametrised by a learnable univariate function that can, in principle, be replaced by a symbolic operator.