Kolmogorov Arnold Network

Kolmogorov-Arnold Networks (KANs) are a novel type of neural network architecture that uses learnable activation functions placed on edges, rather than nodes, offering a potential alternative to traditional Multi-Layer Perceptrons (MLPs). Current research focuses on improving KAN efficiency and accuracy through variations like SincKANs and EKANs (Equivariant KANs), exploring their application in diverse fields such as image processing, function approximation, and solving partial differential equations. The significance of KANs lies in their potential for enhanced interpretability and performance in specific tasks, although comparisons with MLPs reveal varying degrees of success depending on the application and dataset characteristics.

Papers

November 18, 2024

KAN/MultKAN with Physics-Informed Spline fitting (KAN-PISF) for ordinary/partial differential equation discovery of nonlinear dynamic systems
Ashish Pal, Satish Nagarajaiah
Machine Learning Model Nonlinear Dynamic Kolmogorov Arnold Network Nonlinear Model B Spline Nonlinear Function

November 15, 2024

KAT to KANs: A Review of Kolmogorov-Arnold Networks and the Neural Leap Forward
Divesh Basina, Joseph Raj Vishal, Aarya Choudhary, Bharatesh Chakravarthi
Kolmogorov Arnold Network Data Dimensionality High Dimensional Space KAN Layer

November 11, 2024

November 9, 2024

November 8, 2024

On Training of Kolmogorov-Arnold Networks
Shairoz Sohail
Training Data Multi Layer Kolmogorov Arnold Network Stable Training Training Instability

November 6, 2024

Human-in-the-Loop Feature Selection Using Interpretable Kolmogorov-Arnold Network-based Double Deep Q-Network
Md Abrar Jahin, M. F. Mridha, Nilanjan Dey
Inherent Interpretability Kolmogorov Arnold Network Human in the Loop Interpretable Way Double Deep Q Network

November 4, 2024

Fairness-Utilization Trade-off in Wireless Networks with Explainable Kolmogorov-Arnold Networks
Masoud Shokrnezhad, Hamidreza Mazandarani, Tarik Taleb
Deep Neural Network Kolmogorov Arnold Network Wireless Network Power Allocation Fairness Objective

November 1, 2024

October 31, 2024

Using Structural Similarity and Kolmogorov-Arnold Networks for Anatomical Embedding of 3-hinge Gyrus
Minheng Chen, Chao Cao, Tong Chen, Yan Zhuang, Jing Zhang, Yanjun Lyu, Xiaowei Yu, Lu Zhang, Tianming Liu, Dajiang Zhu
Kolmogorov Arnold Network Brain Network Anatomical Structure Structural Similarity Structural Connectome Human Hippocampus Cortical Folding Pattern

October 25, 2024

LArctan-SKAN: Simple and Efficient Single-Parameterized Kolmogorov-Arnold Networks using Learnable Trigonometric Function
Zhijie Chen, Xinglin Zhang
High Efficiency Kolmogorov Arnold Network MNIST Dataset Learned Function

October 22, 2024

KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements
Md Meftahul Ferdaus, Mahdi Abdelguerfi, Elias Ioup, David Dobson, Kendall N. Niles, Ken Pathak, Steven Sloan
Convolutional Neural Network Convolutional Layer Kolmogorov Arnold Network Element Level Information

October 20, 2024

Integrating Symbolic Neural Networks with Building Physics: A Study and Proposal
Xia Chen, Guoquan Lv, Xinwei Zhuang, Carlos Duarte, Stefano Schiavon, Philipp Geyer
Neural Network Data Driven Study Feature Predictive Model Neuro Symbolic Kolmogorov Arnold Network Proposal Balance Refinement Knowledge Discovery Physic Guided Architecture

October 19, 2024

October 18, 2024

Multifidelity Kolmogorov-Arnold Networks
Amanda A. Howard, Bruno Jacob, Panos Stinis
Kolmogorov Arnold Network High Fidelity Fidelity Model

October 17, 2024

From PINNs to PIKANs: Recent Advances in Physics-Informed Machine Learning
Juan Diego Toscano, Vivek Oommen, Alan John Varghese, Zongren Zou, Nazanin Ahmadi Daryakenari, Chenxi Wu, George Em Karniadakis
LeArning Abstract Physic Informed Neural Network Recent Advance Kolmogorov Arnold Network Computational Approach Scientific Machine Learning PINN Method Physic Informed Machine

October 15, 2024

KA-GNN: Kolmogorov-Arnold Graph Neural Networks for Molecular Property Prediction
Longlong Li, Yipeng Zhang, Guanghui Wang, Kelin Xia
Graph Neural Network Human Prediction Kolmogorov Arnold Network Molecular Property Prediction Molecular Property GNN Cl

Kolmogorov Arnold Network

Papers

KAN/MultKAN with Physics-Informed Spline fitting (KAN-PISF) for ordinary/partial differential equation discovery of nonlinear dynamic systems

KAT to KANs: A Review of Kolmogorov-Arnold Networks and the Neural Leap Forward

KLCBL: An Improved Police Incident Classification Model

Can KAN Work? Exploring the Potential of Kolmogorov-Arnold Networks in Computer Vision

SPIKANs: Separable Physics-Informed Kolmogorov-Arnold Networks

A Survey on Kolmogorov-Arnold Network

On Training of Kolmogorov-Arnold Networks

Human-in-the-Loop Feature Selection Using Interpretable Kolmogorov-Arnold Network-based Double Deep Q-Network

Fairness-Utilization Trade-off in Wireless Networks with Explainable Kolmogorov-Arnold Networks

A KAN-based Interpretable Framework for Process-Informed Prediction of Global Warming Potential

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

Using Structural Similarity and Kolmogorov-Arnold Networks for Anatomical Embedding of 3-hinge Gyrus

LArctan-SKAN: Simple and Efficient Single-Parameterized Kolmogorov-Arnold Networks using Learnable Trigonometric Function

KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements

Integrating Symbolic Neural Networks with Building Physics: A Study and Proposal

LSS-SKAN: Efficient Kolmogorov-Arnold Networks based on Single-Parameterized Function

HiPPO-KAN: Efficient KAN Model for Time Series Analysis

Multifidelity Kolmogorov-Arnold Networks

From PINNs to PIKANs: Recent Advances in Physics-Informed Machine Learning

KA-GNN: Kolmogorov-Arnold Graph Neural Networks for Molecular Property Prediction