Visualizing Similarity Data with a Mixture of Maps

111 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Stochastic k-Neighborhood Selection for Supervised and Unsupervised Learning (2013, background): “Uni- SNE (Cook et al., 2007) alters the definition of q i (j) by the addition of a small constant: q i (j) ∝ exp −−z i − z j 2 + κ.”
The Elastic Embedding Algorithm for Dimensionality Reduction (2010, background): “Some versions of SNE have been proposed that slightly simplify the gradient by symmetrising the objective function (Venna & Kaski, 2007) or the probabilities (Cook et al., 2007), but the normalisation term in the qnm terms still makes it very nonlinear.”
Visualizing Data using t-SNE (2008, methodology): “Once the SNE cost function has been optimized using simulated annealing, the background mixing proportion can be increased to allow some gaps to form between natural clusters as shown by Cook et al. (2007).”
Contextualizing Multiple Tasks via Learning to Decompose (2021, background): “Meaningful local maps could be discovered by learning κ for all instances [10, 49].”