LVQu {nnlib2Rcpp}

Unsupervised LVQ

Description

Unsupervised (clustering) Learning Vector Quantization (LVQ) NN.

Usage

LVQu(
  data,
  max_number_of_desired_clusters,
  number_of_training_epochs,
  neighborhood_size,
  show_nn )

Arguments

data

data to be clustered, a numeric matrix, (2d, cases in rows, variables in columns). By default, initial weights are set to random values in [0 1], so data should also be in 0 to 1 range.

max_number_of_desired_clusters

clusters to be produced (at most)

number_of_training_epochs

number of training epochs, aka presentations of all training data to ANN during training.

neighborhood_size

integer >=1, specifies affected neighbor output nodes during training. if 1 (Single Winner) the ANN is somewhat similar to k-means.

show_nn

boolean, option to display the (trained) ANN internal structure.

Value

Returns a vector of integers containing a cluster id for each data case (row).

Note

Function LVQu employs an unsupervised LVQ for clustering data (Kohonen 1988). This LVQ variant is described as Unsupervised Learning LVQ in Simpson (1991) and is a simplified 1-D version of Self-Organizing-Map (SOM). Its parameter neighborhood_size controls the encoding mode (where neighborhood_size=1 is Single-Winner Unsupervised encoding, similar to k-means, while an odd valued neighborhood_size > 1 means Multiple-Winner Unsupervised encoding mode). Initial weights are random (uniform distribution) in 0 to 1 range. As these weights represent cluster center coordinates (the class reference vector), it is important that input data is also scaled to this range.

(This function uses Rcpp to employ 'som_nn' class in nnlib2.)

Author(s)

Vasilis N. Nikolaidis <[e-mail]>

References

Kohonen, T (1988). Self-Organization and Associative Memory, Springer-Verlag.; Simpson, P. K. (1991). Artificial neural systems: Foundations, paradigms, applications, and implementations. New York: Pergamon Press.

Philippidis, TP & Nikolaidis, VN & Kolaxis, JG. (1999). Unsupervised pattern recognition techniques for the prediction of composite failure. Journal of acoustic emission. 17. 69-81.

See Also

LVQs (supervised LVQ module),

Examples

# LVQ expects data in 0 to 1 range, so scale...
iris_s<-as.matrix(iris[1:4])
c_min<-apply(iris_s,2,FUN = "min")
c_max<-apply(iris_s,2,FUN = "max")
c_rng<-c_max-c_min
iris_s<-sweep(iris_s,2,FUN="-",c_min)
iris_s<-sweep(iris_s,2,FUN="/",c_rng)

cluster_ids<-LVQu(iris_s,5,100)
plot(iris_s, pch=cluster_ids, main="LVQ-clustered Iris data")