T-Distributed Stochastic Neighbor Embedding
Incrustación de vecinos estocásticos distribuidos en t (t-SNE)
- Date
- 2008 · confidence high
- Place
- Toronto, Ontario, Canada
- Credited to
- Laurens van der Maaten y Geoffrey Hinton
- Field
- Knowledge & symbols
What it is
A nonlinear dimensionality-reduction technique that maps high-dimensional data into two or three dimensions while preserving neighborhood structure, developed by Laurens van der Maaten and Geoffrey Hinton.
What it led to
- standard tool for visualizing machine-learning and single-cell genomics data
- influence on later techniques such as UMAP
- widespread use in interpreting deep neural network models