Enhancing Neural Function Approximation: The XNet Outperforming KAN
원문 초록
XNet is a single-layer neural network architecture that leverages Cauchy integral-based activation functions for high-order function approximation. Through theoretical analysis, we show that the Cauchy activation functions used in XNet can achieve arbitrary-order polynomial convergence, fundamentally outperforming traditional MLPs and Kolmogorov-Arnold Networks (KANs) that rely on increased depth or B-spline activations. Our extensive experiments on function approximation, PDE solving, and reinforcement learning demonstrate XNet's superior performance - reducing approximation error by up to 50000 times and accelerating training by up to 10 times compared to existing approaches. These results establish XNet as a highly efficient architecture for both scientific computing and AI applications.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models
Automated Modeling Method for Pathloss Model Discovery
"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding
TK-Mamba: Marrying KAN with Mamba for Text-Driven 3D Medical Image Segmentation
X-KAN: Optimizing Local Kolmogorov-Arnold Networks via Evolutionary Rule-Based Machine Learning
Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output Codes
토론
이 논문과 연결된 포럼 글이 아직 없습니다.