כתבה
arXiv cs.LG ·
SechKAN: רשתות Kolmogorov-Arnold עם פונקציות Hyperbolic Secant
SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions
SechKAN היא רשת Kolmogorov-Arnold חדשה, המבוססת על פונקציות Hyperbolic Secant. היא נועדה לשפר את יעילות הלמידה והחישוב.
תקציר מקורי באנגליתarXiv:2607.18290v2 Announce Type: replace Abstract: In recent years, Kolmogorov-Arnold Networks (KANs) have attracted increasing attention due to their effectiveness in machine learning and scientific computing, offering a new paradigm for neural network design. In this paper, we present SechKAN, a novel KAN based on hyperbolic secant (sech) functions. The hyperbolic secant basis is adopted for its smooth bell-shaped form, localized responses, and well-behaved gradients. We employ a 1D linear projection to reduce the number of parameters, allowing SechKAN to maintain a model size comparable to that of multilayer perceptrons (MLPs). Experimental results show the effectiveness of SechKAN on function fitting, PDE surrogate modeling, and image classification benchmarks, including MNIST, Fashio
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית