On the rate of convergence in topology preserving neural networks (Q808996)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 4209918
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | On the rate of convergence in topology preserving neural networks |
scientific article; zbMATH DE number 4209918 |
Statements
On the rate of convergence in topology preserving neural networks (English)
0 references
1991
0 references
Kohonen learning (and his feature maps) attracts still more attention of neural network people. Perhaps everybody who worked with it faced the question of proper choice of time-dependent gain and shrinking coefficients as well as the good choice of the ``mexican hut''. The paper uses Gaussian type of the latter and shows that this ``neighborhood interaction function'' leads to a faster convergence.
0 references
topology preserving unsupervised neural network
0 references
rate of self- organization to final equilibrium state
0 references
error measure functional
0 references
Kohonen learning
0 references
feature maps
0 references
mexican hut
0 references
neighborhood interaction function
0 references
0 references
0.9231361
0 references
0.88939923
0 references
0 references
0.8757961
0 references
0.87548125
0 references
0.8725295
0 references
