KAN Layer based on MATLAB Deep Learning Toolbox

版本 1.0.1 (6.9 KB) 作者: Chuguang Pan
Kolmogorov-Arnold Networks (KAN) constructed based on MATLAB Deep Learning Toolbox.
0.0
(0)
19.0 次下载
更新 2026/2/9

查看许可证

Kolmogorov-Arnold Networks (KANs) are theoretically grounded alternatives to conventional Multilayer Perceptrons (MLPs). KANs are built upon the Kolmogorov-Arnold representation theorem, a profound mathematical result stating that any multivariate continuous function can be expressed through a finite composition of univariate continuous functions and binary additions. For more details about KANs, the interested readers can refer to the KAN: Kolmogorov-Arnold Networks.
The KAN Layer built here is based on the MATLAB Deep Learning Toolbox and exploit its power automatic differentiation capability provided by dlarray. It is worth noting that the current KAN Layer only receives feature input (e.g., feature vectors with "CB" format) and outputs same data format ("CB"). If you want to embed this KAN layer in deep learning pipeline, the input data format from the last layer must be "CB".

引用格式

Chuguang Pan (2026). KAN Layer based on MATLAB Deep Learning Toolbox (https://ww2.mathworks.cn/matlabcentral/fileexchange/183210-kan-layer-based-on-matlab-deep-learning-toolbox), MATLAB Central File Exchange. 检索时间: .

MATLAB 版本兼容性
创建方式 R2025b
兼容 R2024a 到 R2026a 的版本
平台兼容性
Windows macOS Linux
标签 添加标签
在新标签页中打开
版本 已发布 发行说明
1.0.1

Add some descriptions about KAN for better understanding.
1.0.0