AI RESEARCH
P1-KAN: an effective Kolmogorov-Arnold network with application to hydraulic valley optimization
arXiv CS.LG
•
ArXi:2410.03801v5 Announce Type: replace A new Kolmogoro-Arnold network (KAN) is proposed to approximate potentially irregular functions in high dimensions. We provide error bounds for this approximation, assuming that the Kolmogoro-Arnold expansion functions are sufficiently smooth. When the function is only continuous, we also provide universal approximation theorems. We show that it outperforms multilayer perceptrons in terms of accuracy and convergence speed.