中文
相关论文

相关论文: Multi-Exit Kolmogorov-Arnold Networks: enhancing a…

200 篇论文

The domain of laser fusion presents a unique and challenging predictive modeling application landscape for machine learning methods due to high problem complexity and limited training data. Data-driven approaches utilizing prescribed…

机器学习 · 计算机科学 2024-09-16 Rahman Ejaz , Varchas Gopalaswamy , Riccardo Betti , Aarne Lees , Christopher Kanan

This paper tests whether Kolmogorov--Arnold Networks (KAN 2.0) are genuinely more noise-robust than Multi-Layer Perceptrons (MLP) and XGBoost for stellar classification (star/galaxy/quasar, 100,000 SDSS DR17 objects). A naive comparison…

天体物理仪器与方法 · 物理学 2026-05-29 Kristian Sestak

We present a novel approach for verifying properties of Kolmogorov-Arnold Networks (KANs), a class of neural networks characterized by nonlinear, univariate activation functions typically implemented as piecewise polynomial splines or…

机器学习 · 计算机科学 2026-02-09 Noah Schwartz , Chandra Kanth Nagesh , Sriram Sankaranarayanan , Ramneet Kaur , Tuhin Sahai , Susmit Jha

Catastrophic forgetting is a longstanding challenge in continual learning, where models lose knowledge from earlier tasks when learning new ones. While various mitigation strategies have been proposed for Multi-Layer Perceptrons (MLPs),…

机器学习 · 计算机科学 2025-11-18 Mohammad Marufur Rahman , Guanchu Wang , Kaixiong Zhou , Minghan Chen , Fan Yang

We introduce Graph Kolmogorov-Arnold Networks (GKAN), an innovative neural network architecture that extends the principles of the recently proposed Kolmogorov-Arnold Networks (KAN) to graph-structured data. By adopting the unique…

机器学习 · 计算机科学 2024-06-11 Mehrdad Kiamari , Mohammad Kiamari , Bhaskar Krishnamachari

Physics-Informed Neural Networks (PINNs) have emerged as a powerful mesh-free framework for solving ordinary and partial differential equations by embedding the governing physical laws directly into the loss function. However, their…

In this paper, we introduce the KANtrol framework, which utilizes Kolmogorov-Arnold Networks (KANs) to solve optimal control problems involving continuous time variables. We explain how Gaussian quadrature can be employed to approximate the…

最优化与控制 · 数学 2024-09-11 Alireza Afzal Aghaei

We propose a novel approach that enhances multivariate function approximation using learnable path signatures and Kolmogorov-Arnold networks (KANs). We enhance the learning capabilities of these networks by weighting the values obtained by…

机器学习 · 计算机科学 2024-12-10 Hugo Inzirillo , Remi Genet

With increasing penetration of distributed energy resources installed behind the meter, there is a growing need for adequate modelling of composite loads to enable accurate power system simulation analysis. Existing measurement based load…

系统与控制 · 电气工程与系统科学 2025-08-28 Sonam Dorji , Yongkang Sun , Yuchen Zhang , Ghavameddin Nourbakhsh , Yateendra Mishra , Yan Xu

Kolmogorov Arnold Networks is a novel multilayer neuromorphic network that can exhibit higher accuracy than a neural network. It can learn and predict more accurately than neural networks with a smaller number of parameters, and many…

量子物理 · 物理学 2026-01-01 Hikaru Wakaura

Inspired by the Kolmogorov-Arnold representation theorem, KANs offer a novel framework for function approximation by replacing traditional neural network weights with learnable univariate functions. This design demonstrates significant…

机器学习 · 计算机科学 2025-06-10 Zhangchi Zhao , Jun Shu , Deyu Meng , Zongben Xu

AI for partial differential equations (PDEs) has garnered significant attention, particularly with the emergence of Physics-informed neural networks (PINNs). The recent advent of Kolmogorov-Arnold Network (KAN) indicates that there is…

Continual learning (CL), the ability of a model to learn new tasks without forgetting previously acquired knowledge, remains a critical challenge in artificial intelligence, particularly for vision transformers (ViTs) utilizing Multilayer…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Zahid Ullah , Jihie Kim

Understanding and modeling nonlinear dynamical systems is a fundamental challenge across science and engineering. Deep learning has shown remarkable potential for capturing complex system behavior, yet achieving models that are both…

机器学习 · 计算机科学 2026-03-06 Wei Liu , Kiran Bacsa , Loon Ching Tang , Eleni Chatzi

In recent years, the evolution of machine learning techniques has significantly impacted the field of intrusion detection, particularly within the context of the Internet of Things (IoT). As IoT networks expand, the need for robust security…

密码学与安全 · 计算机科学 2024-08-30 Amar Amouri , Mohamad Mahmoud Al Rahhal , Yakoub Bazi , Ismail Butun , Imad Mahgoub

This paper addresses the growing concern of cascading extreme events, such as an extreme earthquake followed by a tsunami, by presenting a novel method for risk assessment focused on these domino effects. The proposed approach develops an…

统计方法学 · 统计学 2026-02-09 Miguel de Carvalho , Clemente Ferrer , Ronny Vallejos

Kolmogorov-Arnold Networks (KAN) models were recently proposed and claimed to provide improved parameter scaling and interpretability compared to conventional multilayer perceptron (MLP) models. Inspired by the KAN architecture, we propose…

While accurate, black-box system identification models lack interpretability of the underlying system dynamics. This paper proposes State-Space Kolmogorov-Arnold Networks (SS-KAN) to address this challenge by integrating Kolmogorov-Arnold…

机器学习 · 计算机科学 2025-06-24 Gonçalo Granjal Cruz , Balazs Renczes , Mark C Runacres , Jan Decuyper

The growing need for accurate and efficient 3D identification of tumors, particularly in liver segmentation, has spurred considerable research into deep learning models. While many existing architectures offer strong performance, they often…

图像与视频处理 · 电气工程与系统科学 2024-12-30 Bhavesh Gyanchandani , Aditya Oza , Abhinav Roy

Traditional constitutive models rely on hand-crafted parametric forms with limited expressivity and generalizability, while neural network-based models can capture complex material behavior but often lack interpretability. To balance these…

机器学习 · 计算机科学 2025-06-05 Prakash Thakolkaran , Yaqi Guo , Shivam Saini , Mathias Peirlinck , Benjamin Alheit , Siddhant Kumar
‹ 上一页 1 8 9 10 下一页 ›