WTSNE: weigth t-Distributed Stochastic Neighbor Embedding

In chenxuepu/WTSNE-R: Weigth T-Distributed Stochastic Neighbor Embedding

Description

weigth t-Distributed Stochastic Neighbor Embedding

Usage

WTSNE(X, ...)

Arguments

X	matrix; Data matrix (each row is an observation, each column is a variable)
...	Other arguments that can be passed to Rtsne

Value

List with the following elements:

Y	Matrix containing the new representations for the objects
N	Number of objects
origD	Original Dimensionality before TSNE (only when X is a data matrix)
perplexity	See above
theta	See above
costs	The cost for every object after the final iteration
itercosts	The total costs (KL-divergence) for all objects in every 50th + the last iteration
stop_lying_iter	Iteration after which the perplexities are no longer exaggerated
mom_switch_iter	Iteration after which the final momentum is used
momentum	Momentum used in the first part of the optimization
final_momentum	Momentum used in the final part of the optimization
eta	Learning rate
exaggeration_factor	Exaggeration factor used to multiply the P matrix in the first part of the optimization
weight	the weight for cost

chenxuepu/WTSNE-R documentation built on Dec. 31, 2020, 9:58 p.m.