self-organizing map
PulseAugur coverage of self-organizing map — every cluster mentioning self-organizing map across labs, papers, and developer communities, ranked by signal.
-
Machine learning deciphers timbre of Chinese Hulusi instrument
Researchers have employed machine learning to analyze the timbre of the hulusi, a free-reed wind instrument originating from Yunnan, China. Using the COMSAR framework and Kohonen self-organizing maps, the study focused …
-
New framework Refine-POI uses LLMs for better POI recommendations
Researchers have developed Refine-POI, a novel framework designed to enhance next point-of-interest (POI) recommendations using large language models (LLMs). This approach tackles two key issues: the preservation of sem…
-
New codebook layout enables massive self-organizing maps on single GPU
Researchers have developed a novel feature-major codebook layout for sparse-binary self-organizing maps, significantly improving memory efficiency and training speed. This optimization allows for the creation of much la…
-
New research explores advanced techniques for continual learning in AI models · 8 sources tracked
Researchers are developing new methods for continual learning, which aims to enable AI models to learn new information without forgetting previously acquired knowledge. One approach, "Class Incremental Continual Learnin…
-
TabSOM method enhances deep learning for tabular data with improved interpretability
Researchers have developed TabSOM, a novel method for encoding tabular data into image representations to enhance the application of deep learning models. Unlike previous approaches that only consider individual feature…
-
New database abstraction integrates Self-Organizing Maps for topology-driven data exploration
Researchers have introduced a new database abstraction called a queryable data map, designed to integrate Self-Organizing Maps (SOMs) directly within database systems. This abstraction allows users to explore data topol…
-
Self-Organizing Maps: An Underappreciated Clustering Algorithm
This article examines clustering algorithms, focusing on Self-Organizing Maps (SOMs) and their underappreciated potential. The author advocates for a deeper look into SOMs, suggesting that tuning them can yield signific…
-
Unsupervised AI models can learn sensitive attributes, violating fairness
Researchers have demonstrated that unsupervised machine learning representations can inadvertently encode sensitive attributes like age and income, even when these attributes are excluded from the training data. A new m…
-
New SOCP method improves ML model calibration by discovering data groups
Researchers have developed Self-Organized Conformal Prediction (SOCP), a new calibration scheme designed to improve the reliability of machine learning models, particularly in safety-critical applications. SOCP utilizes…
-
FloatSOM framework accelerates distributed Self-Organizing Maps with flexible topologies
Researchers have developed FloatSOM, a new framework designed for large-scale Self-Organizing Map (SOM) analysis that overcomes memory limitations on GPUs. This framework enables multi-GPU execution and supports out-of-…