Yuto Kurosaki

Papers

Total Citations

H-Index

About

Yuto Kurosaki is a researcher in pattern recognition and neural networks, with a focus on unsupervised learning and self-organizing maps (SOM). His most cited work, “Effect of grouping in vector recognition system based on SOM” (2016), examines how grouping strategies influence vector classifiers built on SOM—a topology-preserving neural network used for clustering and pattern recognition. By analyzing the interplay between grouping and classification accuracy, Kurosaki contributes to improving the robustness of SOM-based systems in image recognition and other pattern analysis tasks. Though his citation count remains modest, his work addresses foundational challenges in unsupervised learning, offering insights that support more efficient and interpretable recognition models. Kurosaki’s research is particularly relevant for students and researchers exploring neural network architectures for clustering and feature extraction, and his focus on SOM optimization highlights a practical path toward enhancing machine learning systems in data-scarce or high-dimensional settings.