A type used to hold the details of a t-SNE analysis.
More...
#include <SpecImage.hpp>
|
int | k |
| The number of dimensions in the embedding. More...
|
|
size_t | m |
| The number of rows of the input matrix (and the number of rows of the lower dimensional embedding). This can be interpreted as the number of data points. More...
|
|
size_t | d |
| The number of columns of the input matrix; equivalent to the number of dimensions of the input data. More...
|
|
FPType | kl_divergence |
| The Kullback-Liebler divergence between the input data and the lower-dimensional embedding. More...
|
|
FPType | theta |
| The parameter theta used in t-SNE; it represents a tradeoff between speed and accuracy: 0 is accurate but slow, 1 is faster but loses accuracy. More...
|
|
FPType | perplexity |
| The perplexity used in the t-SNE algorithm. More...
|
|
std::unique_ptr< FPType[], cfree > | embedding |
| The m by k lower-dimensional matrix, stored in column-major order. More...
|
|
int | total_iter |
| The number of iterations that were performed. More...
|
|
template<class FPType>
struct nag::tsne_results< FPType >
A type used to hold the details of a t-SNE analysis.
For more information see: nag::SpecImage::tsne.
Move assignment operator.
The number of columns of the input matrix; equivalent to the number of dimensions of the input data.
The m by k lower-dimensional matrix, stored in column-major order.
The number of dimensions in the embedding.
The Kullback-Liebler divergence between the input data and the lower-dimensional embedding.
The number of rows of the input matrix (and the number of rows of the lower dimensional embedding). This can be interpreted as the number of data points.
The perplexity used in the t-SNE algorithm.
The parameter theta used in t-SNE; it represents a tradeoff between speed and accuracy: 0 is accurate but slow, 1 is faster but loses accuracy.
The number of iterations that were performed.
The documentation for this struct was generated from the following file: