Development and applications of a sequential, minimal, radial basis function (RBF) neural network learning algorithm
This thesis presents a new sequential learning algorithm for realizing a minimal Radial Basis Function (RBF) neural network, referred to as M-RAN (Minimal Resource Allocation Network). Unlike most of the classical RBF neural networks with the number of hidden neurons fixed apriori, the network st...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
2010
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/39014 |
| _version_ | 1826115727316221952 |
|---|---|
| author | Lu, Ying Wei. |
| author2 | Narasimhan, Sundararajan |
| author_facet | Narasimhan, Sundararajan Lu, Ying Wei. |
| author_sort | Lu, Ying Wei. |
| collection | NTU |
| description | This thesis presents a new sequential learning algorithm for realizing a minimal
Radial Basis Function (RBF) neural network, referred to as M-RAN (Minimal
Resource Allocation Network). Unlike most of the classical RBF neural networks
with the number of hidden neurons fixed apriori, the network structure is dynamic
in the proposed M-RAN algorithm. |
| first_indexed | 2024-10-01T03:59:52Z |
| format | Thesis |
| id | ntu-10356/39014 |
| institution | Nanyang Technological University |
| last_indexed | 2024-10-01T03:59:52Z |
| publishDate | 2010 |
| record_format | dspace |
| spelling | ntu-10356/390142023-07-04T15:27:29Z Development and applications of a sequential, minimal, radial basis function (RBF) neural network learning algorithm Lu, Ying Wei. Narasimhan, Sundararajan School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems This thesis presents a new sequential learning algorithm for realizing a minimal Radial Basis Function (RBF) neural network, referred to as M-RAN (Minimal Resource Allocation Network). Unlike most of the classical RBF neural networks with the number of hidden neurons fixed apriori, the network structure is dynamic in the proposed M-RAN algorithm. Master of Engineering 2010-05-21T03:45:06Z 2010-05-21T03:45:06Z 1997 1997 Thesis http://hdl.handle.net/10356/39014 NANYANG TECHNOLOGICAL UNIVERSITY 123 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems Lu, Ying Wei. Development and applications of a sequential, minimal, radial basis function (RBF) neural network learning algorithm |
| title | Development and applications of a sequential, minimal, radial basis function (RBF) neural network learning algorithm |
| title_full | Development and applications of a sequential, minimal, radial basis function (RBF) neural network learning algorithm |
| title_fullStr | Development and applications of a sequential, minimal, radial basis function (RBF) neural network learning algorithm |
| title_full_unstemmed | Development and applications of a sequential, minimal, radial basis function (RBF) neural network learning algorithm |
| title_short | Development and applications of a sequential, minimal, radial basis function (RBF) neural network learning algorithm |
| title_sort | development and applications of a sequential minimal radial basis function rbf neural network learning algorithm |
| topic | DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems |
| url | http://hdl.handle.net/10356/39014 |
| work_keys_str_mv | AT luyingwei developmentandapplicationsofasequentialminimalradialbasisfunctionrbfneuralnetworklearningalgorithm |