Leland McInnes, John Healy, & James Melville (2018)
arXiv.
DOI: https://doi.org/10.48550/arxiv.1802.03426
Abstract. Introduces UMAP, a manifold learning technique based on Riemannian geometry and algebraic topology that offers visualisation quality comparable to t-SNE with better preservation of global structure and dramatically faster computation.
Tags: dimensionality-reduction visualisation manifold-learning
Cited in: