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%
- instance of Flash-KMeans 90%
- used by alphaXiv 70%
- instance of alphaXiv 70%
- used by IArxiv 70%
- competes with Gaussian Mixture Models 70%
- competes with hierarchical clustering 70%
- affiliated with spectral clustering 70%
- instance of CatalyzeX Code Finder for Papers 70%
- competes with Birch 70%
- instance of Birch 70%
- instance of Gotit.pub 60%
7 day(s) with sentiment data
-
E-means algorithm achieves tenfold epoch compression over k-means
A new machine learning algorithm called E-means has been introduced, demonstrating a tenfold reduction in training epochs compared to traditional k-means clustering. This advancement, presented in a research context, su…
-
K-Means Clustering for Customer Segmentation Explained
This article details the application of unsupervised machine learning techniques, specifically K-Means clustering, for customer segmentation. It outlines the process of transforming raw transaction data into a customer-…
-
New credibility clustering method automates insurance risk allocation
A new paper proposes an automated method called "credibility clustering" for risk group allocation in group life insurance. This data-driven approach combines the Bühlmann-Straub model with k-means clustering to classif…
-
Meta FAIR's e-means algorithm offers 10x speedup over k-means
Meta FAIR has introduced e-means, a novel algorithm designed to replace the traditional Lloyd's k-means for clustering tasks. This new method utilizes exponential moving averages with mini-batch updates, achieving compa…
-
New study explores clustering for human gene score data classification
Researchers have explored clustering techniques on high-dimensional human gene score data to classify target cells. Using two datasets, a complete gene score dataset and a selected kinase-gene dataset, they applied four…
-
New color extraction method aligns with human perception
Researchers have developed a new framework for dominant color extraction that better aligns with human perception. This method utilizes a novel Human Color Dictionary (HCD) created from an experiment where 110 participa…
-
New pipeline audits IoT data quality for better sensor network analysis
A new processing pipeline for analyzing heterogeneous IoT data has been developed and applied to a long-term LoRaWAN network dataset. The pipeline focuses on auditing data quality and performing bivariate analysis, spec…
-
K-Means Linked to Normalized RBF Assignments in New Research
A new research paper explores the relationship between K-Means clustering and normalized radial basis function (RBF) assignments, proposing that K-Means can be viewed as the zero-temperature limit of these assignments. …
-
New EGiME method improves model evaluation in few-shot learning
Researchers have introduced EGiME, a novel semi-supervised method for evaluating pre-trained models in few-shot learning scenarios. This approach assesses feature-extraction quality by analyzing the clustering structure…
-
AI method clusters public transport vehicles using deep features and color
Researchers have developed a new unsupervised method for clustering public transport vehicles using a combination of deep morphological features and color histograms. This approach leverages a frozen DINOv2 Vision Trans…
-
ControlFlow3D framework enhances point cloud upsampling using multi-view knowledge distillation
Researchers have introduced ControlFlow3D, a novel framework designed to enhance point cloud upsampling by distilling knowledge from multi-view images into a lightweight generation network. This method utilizes a struct…
-
Flash-KMeans optimizes GPU clustering by addressing memory bottlenecks
This article delves into the performance bottlenecks of K-Means clustering on modern GPUs, identifying DRAM bandwidth saturation and atomic memory write contention as key issues. It introduces Flash-KMeans, an IO-aware …
-
Machine unlearning method enhances federated clustering fairness
Researchers have developed a method for machine unlearning in federated socially fair k-means clustering, which aims to minimize the largest group-average squared distance to cluster centers. This approach maintains sep…
-
SHAP explanations show significant variability, new study finds
A new paper published on arXiv details the phenomenon of "explanation multiplicity" within SHAP, a widely used method for interpreting AI model decisions. Researchers found that SHAP explanations can vary significantly …
-
Graph-based WiFi trajectory analysis achieves 68.97% accuracy in floor separation
Researchers have developed a novel graph-based method for distinguishing between floors in multi-story indoor environments using WiFi signal data. The approach constructs a graph from WiFi fingerprints and their transit…
-
Leaner Transformers Efficiently Learn K-Means Clustering Algorithms
Researchers have developed a more efficient transformer model capable of executing Lloyd's algorithm for k-means clustering. This new model requires a smaller embedding size compared to previous iterations, reducing com…
-
Mixture-of-Experts models show mixed results in crypto trading
A new research paper explores the use of Mixture-of-Experts (MoE) models in cryptocurrency order execution, specifically examining training stability and failure modes. The study found that while MoE architectures did n…
-
LLMs' moral reasoning trajectories and contextual morality explored in new research
Researchers are exploring how large language models (LLMs) handle moral reasoning and context. One study introduces "moral reasoning trajectories" to analyze how LLMs switch between ethical frameworks during decision-ma…
-
New BalLOT method enhances balanced k-means clustering with optimal transport
Researchers have introduced BalLOT, a novel approach to balanced k-means clustering that utilizes optimal transport. This method aims to provide a fast and effective solution, supported by theoretical guarantees and emp…
-
New T-ARC clustering method corrects k-means geometric bias using topology
Researchers have introduced T-ARC, a novel topology-aware randomized clustering method designed to overcome the geometric biases inherent in traditional k-means clustering. This new approach integrates topological infor…