Kolmogorov--Arnold Networks
PulseAugur coverage of Kolmogorov--Arnold Networks — every cluster mentioning Kolmogorov--Arnold Networks across labs, papers, and developer communities, ranked by signal.
16 day(s) with sentiment data
-
KANs show comparable, sometimes inferior, performance to MLPs and GNNs in aerodynamics research · 3 sources tracked
A new research paper compares the performance of Kolmogorov Arnold Networks (KANs) against Multilayer Perceptrons (MLPs) and Graph Neural Networks (GNNs) for aerodynamic prediction tasks. While KANs demonstrate good per…
-
New AI model enhances mild cognitive impairment detection using EEG data
Researchers have developed a new interpretable concept-guided polynomial tabular Kolmogorov-Arnold Network (CPTabKAN) for detecting mild cognitive impairment (MCI) using EEG data. This novel approach maps EEG-derived fe…
-
New metrics assess hardware inference complexity of Kolmogorov-Arnold Networks
A new paper introduces hardware-oriented metrics for evaluating the inference complexity of Kolmogorov-Arnold Networks (KANs). These metrics, including Real Multiplications (RM), Bit Operations (BOP), and Number of Addi…
-
Low-power analogue neural networks use trainable nonlinear connections
Researchers have developed low-power analogue neural networks that utilize trainable nonlinear connections, inspired by Kolmogorov-Arnold networks. These networks compute directly with analogue device physics, placing t…
-
New SKANs offer parameter-efficient alternative to KANs
Researchers have introduced Structural Kolmogorov-Arnold Convolutions (SKANs) as a more parameter-efficient alternative to existing Convolutional Kolmogorov-Arnold Networks (KANs). The new approach repositions learnable…
-
New LoadKAN framework combines KAN and attention for interpretable electricity load forecasting
Researchers have developed LoadKAN, a novel framework for electricity load forecasting that integrates a feature-isolated temporal attention mechanism with a Kolmogorov-Arnold Network (KAN). This hybrid approach aims to…
-
Kolmogorov-Arnold Networks proposed for transparent EEG seizure detection
A new arXiv paper reviews the limitations of traditional deep learning models for electroencephalogram (EEG) seizure detection, highlighting issues with interpretability, data requirements, and computational costs. The …
-
New GRNGC Framework Enhances Causal Discovery in Complex Industrial Processes
Researchers have developed a new gradient-based causal discovery framework called GRNGC, designed to overcome limitations in existing neural network-based Granger causality models. GRNGC reduces computational costs by u…
-
New Kolmogorov-Arnold Network Variants Explore Clifford Algebras and Monotonicity
Researchers have introduced Clifford Kolmogorov-Arnold Networks (ClKANs), a novel architecture designed for function approximation within arbitrary Clifford Algebra spaces. This new architecture incorporates randomized …
-
New KAN Frameworks and Variants Enhance Research and Efficiency
Researchers have developed KANLib, a new framework designed to streamline research on Kolmogorov-Arnold Networks (KANs) by unifying features from existing implementations like PyKAN, EfficientKAN, and FastKAN. Concurren…
-
ShapKAN framework enhances KAN interpretability and compression
A new framework called ShapKAN has been developed to address the challenges of pruning Kolmogorov-Arnold Networks (KANs). This method utilizes Shapley values to evaluate node importance in a manner that is invariant to …
-
Hybrid KAN-MLP model boosts human activity recognition accuracy
Researchers have developed a hybrid neural network architecture, KAN-MLP-Mixer, that combines the precision of Kolmogorov-Arnold Networks (KANs) with the noise robustness and efficiency of Multi-Layer Perceptrons (MLPs)…
-
Sparsified KANs offer interpretable quantum state tomography
Researchers have developed a sparsified Kolmogorov-Arnold Network (KAN) to improve interpretability in quantum state tomography. This method allows the network not only to reconstruct quantum states with high fidelity b…
-
New framework boosts pulsar magnetosphere simulation accuracy
Researchers have developed an adaptive framework for simulating pulsar magnetospheres, utilizing physics-informed Kolmogorov-Arnold networks. This new method significantly improves accuracy and reduces training time com…
-
KANs accelerate machine learning on FPGAs for ultrafast inference
Researchers have developed a novel approach to accelerate machine learning on Field-Programmable Gate Arrays (FPGAs) using Kolmogorov-Arnold Networks (KANs). This method aims to achieve ultrafast inference and online le…
-
GS-KAN offers parameter-efficient alternative to Kolmogorov-Arnold Networks
Researchers have introduced GS-KAN, a novel architecture that enhances the efficiency of Kolmogorov-Arnold Networks (KANs). By utilizing shared basis functions and learnable linear transformations, GS-KAN significantly …
-
Kolmogorov-Arnold networks infer hidden biological forces from pressure data
Researchers have developed a novel method using Kolmogorov-Arnold networks to infer hidden forces driving biological systems from limited observational data. This approach was successfully applied to reconstruct the mus…
-
KAN-PCA generalizes PCA with neural networks for financial analysis
Researchers have developed a new method called KAN-PCA, which uses Kolmogorov-Arnold Networks to generalize classical Principal Component Analysis (PCA). This approach replaces linear projections with learned B-spline f…
-
New RBF-KAN and RBF-SKAN architectures tackle multidimensional function approximation
Researchers have introduced novel hierarchical neural network architectures, RBF-KAN and RBF-SKAN, designed for approximating complex multidimensional functions and learning random field models. These architectures leve…
-
New KAN-BiGRU model boosts legal document analysis
Researchers have developed a new model combining BiGRU with a Kolmogorov-Arnold Network (KAN) block to improve the classification and summarization of legal documents. This approach addresses challenges like multilingua…