Uniform Manifold Approximation and Projection
GPTKB entity
Statements (40)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:dimensionality_reduction_algorithm
|
| gptkbp:abbreviation |
gptkb:UMAP
|
| gptkbp:application |
clustering
feature engineering visualizing high-dimensional data |
| gptkbp:arXivID |
1802.03426
|
| gptkbp:author |
Leland McInnes, John Healy, James Melville
|
| gptkbp:citation |
2018
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction |
| gptkbp:developer |
gptkb:James_Melville
gptkb:Leland_McInnes gptkb:John_Healy |
| gptkbp:feature |
scalable to large datasets
fast runtime compared to t-SNE preserves local and global structure supports supervised and unsupervised learning |
| gptkbp:field |
gptkb:machine_learning
gptkb:data_visualization manifold learning |
| gptkbp:implementationLibrary |
gptkb:umap-learn
|
| gptkbp:implementedIn |
gptkb:Python
|
| gptkbp:input |
high-dimensional data
|
| gptkbp:license |
gptkb:BSD_license
|
| gptkbp:openSource |
true
|
| gptkbp:output |
low-dimensional embedding
|
| gptkbp:parameter |
gptkb:Metric
min_dist n_components n_neighbors |
| gptkbp:publicationYear |
2018
|
| gptkbp:relatedTo |
gptkb:t-SNE
Principal Component Analysis |
| gptkbp:supportsAlgorithm |
nonlinear dimensionality reduction
|
| gptkbp:uses |
stochastic gradient descent
nearest neighbor graph |
| gptkbp:website |
https://umap-learn.readthedocs.io/en/latest/
|
| gptkbp:bfsParent |
gptkb:UMAP
gptkb:t-distributed_Stochastic_Neighbor_Embedding |
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
Uniform Manifold Approximation and Projection
|