Kolmogorov-Arnold Networks
78 papers with code • 0 benchmarks • 0 datasets
Papers presenting models which utilize Kolmogorov-Arnold networks as their underlying architecture.
Benchmarks
These leaderboards are used to track progress in Kolmogorov-Arnold Networks
Most implemented papers
KAN: Kolmogorov-Arnold Networks
Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs).
TKAN: Temporal Kolmogorov-Arnold Networks
remigenet/tkan
•
•
Recurrent Neural Networks (RNNs) have revolutionized many areas of machine learning, particularly in natural language and data sequence processing.
U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation
duttapallabi2907/u-vixlstm
•
•
We further delved into the potential of U-KAN as an alternative U-Net noise predictor in diffusion models, demonstrating its applicability in generating task-oriented model architectures.
BSRBF-KAN: A combination of B-splines and Radial Basis Functions in Kolmogorov-Arnold Networks
In this paper, we introduce BSRBF-KAN, a Kolmogorov Arnold Network (KAN) that combines B-splines and radial basis functions (RBFs) to fit input vectors during data training.
FC-KAN: Function Combinations in Kolmogorov-Arnold Networks
In this paper, we introduce FC-KAN, a Kolmogorov-Arnold Network (KAN) that leverages combinations of popular mathematical functions such as B-splines, wavelets, and radial basis functions on low-dimensional data through element-wise operations.
Deep Learning Alternatives of the Kolmogorov Superposition Theorem
predictiveintelligencelab/jaxpi
•
•
This paper explores alternative formulations of the Kolmogorov Superposition Theorem (KST) as a foundation for neural network design.
LSS-SKAN: Efficient Kolmogorov-Arnold Networks based on Single-Parameterized Function
In the final accuracy tests, LSS-SKAN exhibited superior performance on the MNIST dataset compared to all tested pure KAN variants.
Kolmogorov-Arnold Networks are Radial Basis Function Networks
ZiyaoLi/fast-kan
•
•
This short paper is a fast proof-of-concept that the 3-order B-splines used in Kolmogorov-Arnold Networks (KANs) can be well approximated by Gaussian radial basis functions.
Wav-KAN: Wavelet Kolmogorov-Arnold Networks
zavareh1/Wav-KAN
•
•
In this paper, we introduce Wav-KAN, an innovative neural network architecture that leverages the Wavelet Kolmogorov-Arnold Networks (Wav-KAN) framework to enhance interpretability and performance.
A First Look at Kolmogorov-Arnold Networks in Surrogate-assisted Evolutionary Algorithms
We employ KANs for regression and classification tasks, focusing on the selection of promising solutions during the search process, which consequently reduces the number of expensive function evaluations.
