topological data analysis
PulseAugur coverage of topological data analysis — every cluster mentioning topological data analysis across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Topological features enhance AI model generalizability for firn image classification
A new research paper explores the use of topological features to improve the generalizability and explainability of convolutional neural networks (CNNs) for classifying firn images. Firn, which is granular snow within g…
-
Topological data analysis predicts solar wind streams from coronal holes
Researchers have developed a novel method using topological data analysis to predict high-speed solar wind streams originating from coronal holes. By analyzing the topology of extreme ultraviolet solar images, the syste…
-
New Flood bifiltration method enhances scalable 2-parameter persistent homology
Researchers have introduced the sublevel Flood bifiltration, a new method designed to make computing 2-parameter persistent homology more scalable for large datasets. This approach extends the existing Flood filtration …
-
New dashboard system addresses interpretation uncertainty in topological data analysis
Researchers have developed TopoLA, a dashboard system designed to present analytical outputs from Topological Data Analysis (TDA) in a way that acknowledges interpretation uncertainty. The system applies Zigzag Persiste…
-
Topology tools enhance graph diffusion models in machine learning
Researchers are exploring the application of low-dimensional topology, specifically Morse theory and cobordism theory, to enhance machine learning models. Their proposed pipeline, MG-Diff, leverages discrete Morse theor…
-
New LandscapeSHAP method assigns credit in topological data analysis
Researchers have developed LandscapeSHAP, a novel method for attributing machine learning model predictions to specific features derived from topological data analysis. This approach specifically addresses the challenge…
-
New Topological Steering Framework Enhances LLM Behavioral Control
Researchers have introduced a new framework called Topological Steering, which leverages topological data analysis to control undesirable behaviors in large language models. This method uses persistence diagrams to repr…
-
New research tackles challenges in large graphical models
Two new research papers from arXiv's Statistics > Machine Learning section explore advanced techniques for analyzing large and complex graphical models. The first paper introduces symbolic algorithms and topological dat…
-
Persistent homology objectively identifies artistic styles and AI fakes
Researchers have demonstrated the effectiveness of persistent homology (PH), a technique from topological data analysis, in objectively identifying and differentiating artistic styles. This method can distinguish betwee…
-
New framework uses topology and AI to model multicellular patterns
Researchers have developed a new framework called TI$^2$PS that integrates topological data analysis with inverse surrogate modeling to estimate parameters for agent-based models (ABMs) of multicellular pattern formatio…
-
New framework enables structured learning on topological data analysis representations
Researchers have developed a new framework for learning over structured representations generated by the Mapper algorithm from topological data analysis. This approach treats the full Mapper construction as an integral …
-
Vision models offer efficient 2D damage classification for 3D point clouds
Researchers have developed two methods for classifying damage in 3D point cloud data (PCD). The first, 3D PCD-based damage assessment (3PDA), uses topological data analysis (TDA) to compress geometric structures into fe…
-
Topological Data Analysis Enhances Machine Learning for Porous Media Permeability Prediction
Researchers have developed a novel approach combining topological data analysis (TDA) with machine learning (ML) to predict the permeability of porous media. This method extracts structural, topological, and network fea…
-
Topological Data Analysis Enhances Tennis Match Prediction Accuracy
Researchers have developed novel methods for predicting tennis match outcomes by applying topological data analysis and graph theory to ATP singles match data from 2000-2025. One approach uses lower-star filtration on p…
-
New Betti Number Filtration Clustering Algorithm Outperforms State-of-the-Art
Researchers have introduced a new clustering algorithm called Betti Number Filtration-based Topological Clustering (BFTC). This method utilizes topological data analysis, specifically persistent homology, to capture com…
-
Topological Data Analysis Predicts Alzheimer's Conversion Risk
Researchers have developed a novel method using persistent homology to predict the conversion risk from mild cognitive impairment (MCI) to Alzheimer's disease (AD). This approach analyzes clinical trajectories as point …
-
Deep Learning Models Show Promise for Sleep Apnea Classification via EEG
Researchers have developed deep learning models to classify sleep apnea from electroencephalogram (EEG) signals, aiming to reduce the resource-intensive nature of traditional polysomnography. The study compared various …
-
New research explores quantum advantage and noise resistance in topological data analysis
Two new research papers explore advancements in topological data analysis (TDA), a machine learning technique that uses topology to find patterns in data. The first paper introduces normalized persistence, a variant of …
-
New LLM Agent Automates Topological Analysis for Medical Images
Researchers have developed TopoAgent, an LLM-based framework designed to automate the selection and application of topological descriptors for medical image analysis. This agentic system utilizes a Perception-Reasoning-…
-
TopoTTA framework integrates topological data analysis for anomaly segmentation
Researchers have developed TopoTTA, a novel framework that integrates topological data analysis into test-time adaptation for anomaly segmentation. This approach uses persistent homology to enforce geometric and structu…