Neural Network Toolbox™

Update NNT 2.0 self-organizing map

Syntax

• net = nnt2som(PR,[D1,D2,...],W,OLR,OSTEPS,TLR,TND)
  

Description

nnt2som(PR,[D1,D2,...],W,OLR,OSTEPS,TLR,TND) takes these arguments,

PR	R x 2 matrix of min and max values for R input elements
Di	Size of ith layer dimension
W	S x R weight matrix
OLR	Ordering phase learning rate (default = 0.9)
OSTEPS	Ordering phase steps (default = 1000)
TLR	Tuning phase learning rate (default = 0.02)
TND	Tuning phase neighborhood distance (default = 1)

and returns a self-organizing map.

nnt2som assumes that the self-organizing map has a grid topology (gridtop) using link distances (linkdist). This corresponds with the neighborhood function in NNT 2.0.

The new network only outputs 1 for the neuron with the greatest net input. In NNT 2.0 the network would also output 0.5 for that neuron's neighbors.

Once a network has been updated, it can be simulated, initialized, adapted, or trained with sim, init, adapt, or train.

See Also

newsom

Provide feedback about this page

nnt2rb

nntool

© 1984-2008- The MathWorks, Inc.    -   Site Help   -   Patents   -   Trademarks   -   Privacy Policy   -   Preventing Piracy   -   RSS