| SOM Toolbox | Online documentation | http://www.cis.hut.fi/projects/somtoolbox/ |
[Neurons] = neural_gas(D,n,epochs,alpha0,lambda0)
NEURAL_GAS Quantizes the data space using the neural gas algorithm.
Neurons = neural_gas(D, n, epochs, [alpha0], [lambda0])
C = neural_gas(D,50,10);
sM = som_map_struct(sD);
sM.codebook = neural_gas(sD,size(sM.codebook,1),10);
Input and output arguments ([]'s are optional):
D (matrix) the data matrix, size dlen x dim
(struct) a data struct
n (scalar) the number of neurons
epochs (scalar) the number of training epochs (the number of
training steps is dlen*epochs)
[alpha0] (scalar) initial step size, 0.5 by default
[lambda0] (scalar) initial decay constant, n/2 by default
Neurons (matrix) the neuron matrix, size n x dim
See also SOM_MAKE, KMEANS.