k-means clustering
PulseAugur coverage of k-means clustering — every cluster mentioning k-means clustering across labs, papers, and developer communities, ranked by signal.
- instance of spectral clustering 90%
- used by alphaXiv 70%
- instance of alphaXiv 70%
- instance of Gotit.pub 70%
- instance of CatalyzeX 70%
- competes with Gaussian Mixture Models 70%
- instance of CatalyzeX Code Finder for Papers 70%
- competes with hierarchical clustering 70%
- competes with Birch 70%
- instance of Birch 70%
- affiliated with spectral clustering 70%
- used by ScienceCast 60%
8 day(s) with sentiment data
-
New research proves inherent NP-hardness of clustering algorithms
A research paper introduces the Universal Clustering Problem (UCP) to unify and explain the inherent computational difficulty in various clustering algorithms. The study proves that UCP is NP-hard through reductions fro…
-
AI model classifies UAE architectural heritage with 98% accuracy
Researchers have developed a novel multimodal machine learning framework to classify architectural styles in the United Arab Emirates, specifically focusing on residential buildings. This approach leverages OpenAI's CLI…
-
New CopDAG method enhances biomedical data clustering without labels
Researchers have developed a new framework called Copula Adapted Directed Acyclic Graph (CopDAG) to improve the clustering of biomedical data. This method integrates copula models, which handle flexible multivariate dis…
-
LLM-Driven Differential Evolution Algorithm Enhances Portfolio Optimization
Researchers have developed a new algorithm called LLMDE, which integrates large language models (LLMs) into differential evolution for portfolio optimization. This approach aims to reduce the need for manual hyperparame…
-
New method enables exact community recovery in directed stochastic block models
Researchers have developed a new method for exact community recovery in sparse directed stochastic block models. The approach utilizes neighborhood smoothing of connection-probability profiles, clustering vertices based…
-
Unsupervised clustering method aids fault analysis in power systems
Researchers have developed an unsupervised clustering method to analyze fault events in high-voltage power systems using voltage and current signals. The approach utilizes data from the Réseau de Transport d'Électricité…
-
ZAPS pipeline enhances Neural Architecture Search by combining proxy signals and topology
Researchers have developed ZAPS, a novel four-stage pipeline designed to improve Neural Architecture Search (NAS) by efficiently combining proxy signals with architectural topology. This method addresses the limitations…
-
NVIDIA cuML and RAPIDS accelerate ML workflows on GPUs
This tutorial demonstrates how to implement machine learning workflows using NVIDIA's cuML and RAPIDS libraries for GPU acceleration. It covers setting up the GPU environment, accelerating scikit-learn workloads with cu…
-
Sector-Mean Initialization offers faster, deterministic k-means clustering
Researchers have introduced Sector-Mean Initialization, a novel deterministic method for initializing centroids in k-means clustering. This approach partitions data into angular sectors around a global centroid and calc…
-
New CLUES-WEASEL algorithm offers faster, more accurate time series clustering
Researchers have introduced CLUES-WEASEL, a novel algorithm for time series clustering designed to overcome the performance-runtime trade-off common in existing methods. This unsupervised approach extracts features usin…
-
New algorithm optimizes UAV deployment for disaster communication restoration
Researchers have developed a new algorithm, the Hybrid K-means Quantum-Inspired Evolutionary Algorithm (HKQEA), to optimize the deployment of unmanned aerial vehicles (UAVs) for post-disaster wireless communication rest…
-
New sampling pipeline drastically cuts industrial anomaly detection time
Researchers have developed a new method called the Plugin Sampler Pipeline (PSP) to significantly speed up anomaly detection in industrial settings. PSP uses a four-stage adaptive sampling process with 18-dimensional pi…
-
New 'View distance' metric enhances high-dimensional data clustering
Researchers have introduced a novel distance metric called "View distance" designed to improve the performance of clustering algorithms like k-means in high-dimensional data. Unlike Euclidean distance, which can falter …
-
New robust K-means clustering method developed to handle outliers
Researchers have developed a new robust clustering method called MK-means DPD, which utilizes density power divergence and Mahalanobis distance to effectively handle outliers and adapt to heterogeneous clusters. To addr…
-
New hybrid quantum model optimizes stock portfolios
Researchers have introduced Titans-QFWP, a novel hybrid reinforcement learning architecture designed for adaptive portfolio optimization. This system integrates a Quantum Fast Weight Programmer with memory components fo…
-
New dataset FLAME supports NLP research on underrepresented Flemish Dutch
Researchers have introduced FLAME, a new dataset comprising nearly 25,000 personal narratives in Belgian-Dutch (Flemish). This corpus was collected using experience sampling to support Natural Language Processing (NLP) …
-
New theory unifies clustering methods as structured projectors
A new theoretical framework unifies various clustering methods, including k-means, fuzzy c-means, and spectral clustering, by expressing them as structured low-rank projectors. This approach reveals algebraic links betw…
-
New AI framework stages crop stress using satellite imagery
Researchers have developed EigenCL, a new contrastive learning framework designed to stage crop stress using NDRE trajectories from Sentinel-2 satellite imagery. This method aims to provide more accurate and interpretab…
-
Deep clustering methods re-evaluated for effectiveness and evaluation metrics · 2 papers
Two new arXiv papers explore the nuances of deep clustering, a technique that uses neural networks to partition complex data. The first paper questions the necessity of deep learning for clustering, proposing a non-deep…
-
New ICOMT framework enhances clustering interpretability with optimal multi-way trees
Researchers have developed a new computational framework called Interpretable Clustering via Optimal Multi-way Trees (ICOMT) to enhance the interpretability of clustering results. This method utilizes a novel discretiza…