Hessian Locally Linear Embedding
An S4 Class implementing Hessian Locally Linear Embedding (HLLE)
HLLE uses local hessians to approximate the curvines and is an extension to non-convex subsets in lowdimensional space.
funA function that does the embedding and returns a dimRedResult object.
stdparsThe standard parameters for the function.
Dimensionality reduction methods are S4 Classes that either be used
directly, in which case they have to be initialized and a full
list with parameters has to be handed to the @fun()
slot, or the method name be passed to the embed function and
parameters can be given to the ..., in which case
missing parameters will be replaced by the ones in the
@stdpars.
HLLE can take the following parameters:
neighborhood size
number of output dimensions
Own implementation, sticks to the algorithm in Donoho and Grimes (2003). Makes use of sparsity to speed up final embedding.
Donoho, D.L., Grimes, C., 2003. Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data. PNAS 100, 5591-5596. doi:10.1073/pnas.1031596100
Other dimensionality reduction methods: AutoEncoder-class,
DRR-class,
DiffusionMaps-class,
DrL-class, FastICA-class,
FruchtermanReingold-class,
Isomap-class,
KamadaKawai-class, LLE-class,
MDS-class, NNMF-class,
PCA-class, PCA_L1-class,
UMAP-class,
dimRedMethod-class,
dimRedMethodList, kPCA-class,
nMDS-class, tSNE-class
dat <- loadDataSet("3D S Curve", n = 300)
## directy use the S4 class:
hlle <- HLLE()
emb <- hlle@fun(dat, hlle@stdpars)
## using embed():
emb2 <- embed(dat, "HLLE", knn = 45)
plot(emb, type = "2vars")
plot(emb2, type = "2vars")Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.