# Fast and Good Initialization of RBF Networks

**Dietmar Bauer** ;

**Jonas Sjöberg
** (Institutionen för signaler och system, Mekatronik)
**Proceeding of the 18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, 28 - 30 April 2010** (2010)

[Konferensbidrag, refereegranskat]

In this paper a new method for fast initialization of radial basis function (RBF) networks is proposed. A grid of possible positions and widths for the basis functions is defined and new nodes to the RBF network are introduced one at the time. The definition of the grid points is done in a specific way which leads to algorithms which are computationally inexpensive due to the fact that intermediate results can be reused and do not need to be re-computed. If the grid is dense one obtains estimators close to estimators resulting from an exhaustive search for the initial parameters which leads to a lower risk to be caught in local minima in the minimization which follows.
The usefulness of the approach is demonstrated in a simulation example.

(öppna i nytt fönster)

**Det verkar som att din webbläsare saknar möjlighet att visa PDF. Klicka Öppna i nytt fönster för att läsa.**

### Länka till denna publikation

### Dela på webben

### Skapa referens, olika format (klipp och klistra)

**Harvard**

Bauer, D. och Sjöberg, J. (2010) *Fast and Good Initialization of RBF Networks*.

** BibTeX **

@conference{

Bauer2010,

author={Bauer, Dietmar and Sjöberg, Jonas},

title={Fast and Good Initialization of RBF Networks},

booktitle={Proceeding of the 18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, 28 - 30 April 2010},

abstract={In this paper a new method for fast initialization of radial basis function (RBF) networks is proposed. A grid of possible positions and widths for the basis functions is defined and new nodes to the RBF network are introduced one at the time. The definition of the grid points is done in a specific way which leads to algorithms which are computationally inexpensive due to the fact that intermediate results can be reused and do not need to be re-computed. If the grid is dense one obtains estimators close to estimators resulting from an exhaustive search for the initial parameters which leads to a lower risk to be caught in local minima in the minimization which follows.
The usefulness of the approach is demonstrated in a simulation example.},

year={2010},

}

** RefWorks **

RT Conference Proceedings

SR Electronic

ID 123732

A1 Bauer, Dietmar

A1 Sjöberg, Jonas

T1 Fast and Good Initialization of RBF Networks

YR 2010

T2 Proceeding of the 18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, 28 - 30 April 2010

AB In this paper a new method for fast initialization of radial basis function (RBF) networks is proposed. A grid of possible positions and widths for the basis functions is defined and new nodes to the RBF network are introduced one at the time. The definition of the grid points is done in a specific way which leads to algorithms which are computationally inexpensive due to the fact that intermediate results can be reused and do not need to be re-computed. If the grid is dense one obtains estimators close to estimators resulting from an exhaustive search for the initial parameters which leads to a lower risk to be caught in local minima in the minimization which follows.
The usefulness of the approach is demonstrated in a simulation example.

LA eng

LK http://publications.lib.chalmers.se/records/fulltext/local_123732.pdf

OL 30

Denna post skapades 2010-07-07. Senast ändrad 2017-06-28.

CPL Pubid: 123732