cheng-haha/KANs

🕹️The toy examples of Kolmogorov-Arnold Network (Get Started Quickly)

The toy examples of KAN ( Kolmogorov-Arnold Network )

Support MLP, KAN, and KAN derivatives

KAN paper: Kolmogorov-Arnold Networks

KANs:

• KANs
• Efficient-KAN
• FourierKAN
• Two-layer MLP (Toy Version)

Run

python examples/mnist.py --model MLP
python examples/mnist.py --model KAN
python examples/mnist.py --model MNISTFourierKAN

Experiential Settings

• For KAN, a large initial learning rate may be more effective. (You can try lr = 1e-2)
• In my experiments, KAN does converge faster than MLP.