Results 161 to 170 of about 2,256,882 (213)

KAN versus MLP on Irregular or Noisy Function

2025 15th IEEE International Conference on Pattern Recognition Systems (ICPRS)
In this paper, we compare the performance of Kolmogorov-Arnold Networks (KANs) and Multi-Layer Perceptrons (MLPs) Networks on irregular or noisy functions.
Chen Zeng, Jiahui Wang, Haoran Shen, Qiao Wang   +3 more
semanticscholar   +1 more source

Kan-Wen Ma

BMJ, 2017
Kan-Wen Ma was a distinguished authority on the history of Chinese medicine. In China, he is credited with establishing the term “traditional Chinese medicine” (TCM) for the treasure house of knowledge that exists in ancient texts. He introduced Western audiences to a wider understanding of the antiquity of TCM and the complex and subtle contributions ...
J A, Jewell, Sheila, Hillier
openaire   +2 more sources

ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLU

arXiv.org
Limited by the complexity of basis function (B-spline) calculations, Kolmogorov-Arnold Networks (KAN) suffer from restricted parallel computing capability on GPUs. This paper proposes a novel ReLU-KAN implementation that inherits the core idea of KAN. By
Qi Qiu, Tao Zhu, Helin Gong, L. Chen, Huansheng Ning   +4 more
semanticscholar   +1 more source

Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis

International Conference on Advanced Data Mining and Applications
Kolmogorov-Arnold Networks (KAN) has recently attracted significant attention as a promising alternative to traditional Multi-Layer Perceptrons (MLP). Despite their theoretical appeal, KAN require validation on large-scale benchmark datasets. Time series
C. Dong, L. Zheng, Weitong Chen, W. Zhang   +3 more
semanticscholar   +1 more source

TCNN-KAN: Optimized CNN by Kolmogorov-Arnold Network and Pruning Techniques for sEMG Gesture Recognition

IEEE journal of biomedical and health informatics
Surface electromyography (sEMG) is a non-invasive technique that records the electrical signals generated by muscle activity. sEMG signals are widely used in the field of biomedical and health informatics for diagnosing and monitoring neuromuscular ...
M. A. Al-qaness, Sike Ni
semanticscholar   +1 more source

PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets

Computers & graphics
Kolmogorov-Arnold Networks (KANs) have recently gained attention as an alternative to traditional Multilayer Perceptrons (MLPs) in deep learning frameworks.
Ali Kashefi
semanticscholar   +1 more source

Physics Informed Kolmogorov-Arnold Neural Networks for Dynamical Analysis via Efficent-KAN and WAV-KAN

arXiv.org
Physics-informed neural networks have proven to be a powerful tool for solving differential equations, leveraging the principles of physics to inform the learning process.
Subhajit Patra, Sonali Panda, B. Parida, Mahima Arya, Kurt Jacobs, Denys I. Bondar, Abhijit Sen   +6 more
semanticscholar   +1 more source

KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networks

International Conference on Machine Learning
Time series anomaly detection (TSAD) underpins real-time monitoring in cloud services and web systems, allowing rapid identification of anomalies to prevent costly failures.
Quan Zhou, Changhua Pei, Fei Sun, Jing Han, Zhengwei Gao, Dan Pei, Haiming Zhang, Gaogang Xie, Jianhui Li   +8 more
semanticscholar   +1 more source

KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation

ECCV Workshops
Segmentation of crop fields is essential for enhancing agricultural productivity, monitoring crop health, and promoting sustainable practices. Deep learning models adopted for this task must ensure accurate and reliable predictions to avoid economic ...
Daniele Rege Cambrin, Eleonora Poeta, Eliana Pastor, T. Cerquitelli, Elena Baralis, Paolo Garza   +5 more
semanticscholar   +1 more source

KAN See in the Dark

IEEE Signal Processing Letters
Low-lightimage enhancement methods are difficult to fit the complex nonlinear relationship between normal and low-light images due to uneven illumination and noise effects.
Aoxiang Ning, Minglong Xue, Jinhong He, Chengyun Song   +3 more
semanticscholar   +1 more source