### Abstract

In a general purpose pulse coupled neural network (PCNN) algorithm the following parameters are used: 2 weight matrices, 3 time constants, 3 normalization factors and 2 further parameters. In a given application, one has to determine the near optimal parameter set to achieve the desired goal. Here a simplified PCNN is described which contains a parameter fitting part, in the least squares sense. Given input and a desired output image, the program is able to determine the optimal value of a selected PCNN parameter. This method can be extended to more general PCNN algorithms, because partial derivatives are not required for the fitting. Only the sum of squares of the differences is used.

Original language | English |
---|---|

Pages (from-to) | 278-285 |

Number of pages | 8 |

Journal | Proceedings of SPIE - The International Society for Optical Engineering |

Volume | 3728 |

Publication status | Published - Jan 1 1999 |

Event | Proceedings of the 1998 9th Workshop on Virtual Intelligence/Dynamic Neural Networks: Neural Networks, Fuzzy Systems, Evolutionary Systems and Virtual Reality/Pulse Coupled Networks Academic/Industrial/NASA/Defence: Tutorial/Technical Interchange - Stockholm, SWE Duration: Jun 22 1998 → Jun 28 1998 |

### ASJC Scopus subject areas

- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering

## Fingerprint Dive into the research topics of 'Parameter adaptation in a simplified Pulse-Coupled Neural Network'. Together they form a unique fingerprint.

## Cite this

*Proceedings of SPIE - The International Society for Optical Engineering*,

*3728*, 278-285.