High-order MS CMAC neural network

A macro structure cerebellar model articulation controller (MS CMAC) was developed by connecting several 1D CMAC in a tree structure, which decomposes a multidimensional problem into a set of 1D subproblems, to reduce the computational complexity in multidimensional CMAC. Additionally, a trapezium s...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2001-05, Vol.12 (3), p.598-603
Main Authors: Jan, J.C., Shih-Lin Hung
Format: Article
Language:English
Subjects:
Acceptability
Algorithms
CMAC
Computational complexity
Dynamical systems
Helium
Interpolation
Joining processes
Learning
Multidimensional systems
Neural networks
Nonlinear systems
Spline
Splines
Studies
Testing
Training
Tree data structures
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A macro structure cerebellar model articulation controller (MS CMAC) was developed by connecting several 1D CMAC in a tree structure, which decomposes a multidimensional problem into a set of 1D subproblems, to reduce the computational complexity in multidimensional CMAC. Additionally, a trapezium scheme is proposed to assist MS CMAC to model nonlinear systems. However, this trapezium scheme cannot perform a real smooth interpolation, and its working parameters are obtained through cross-validation. A quadratic splines scheme is developed herein to replace the trapezium scheme in MS CMAC, named high-order MS CMAC (HMS CMAC). The quadratic splines scheme systematically transforms the stepwise weight contents of CMAC in MS CMAC into smooth weight contents to perform the smooth outputs. Test results affirm that the HMS CMAC has acceptable generalization in continuous function-mapping problems for nonoverlapping association in training instances. Nonoverlapping association in training instances not only significantly reduces the number of training instances needed, but also requires only one learning cycle in the learning stage.
ISSN:1045-9227
2162-237X
1941-0093
2162-2388
DOI:10.1109/72.925562