### Abstract

In this paper we introduce two forms of Unsymmetric Principal Component Analysis (UPCA), namely the cross-correlation UPCA and the linear approximation UPCA problem. Both are concerned with the SVD of the input-teacher crosscorrelation matrix itself (first problem) or after prewhitening (second problem). The second problem is also equivalent to reduced-rank Wiener filtering. For the former problem, we propose an unsymmetric linear model for extracting one or more components using lateral inhibition connections in the hidden layer. The numerical convergence properties of the model are theoretically established. For the linear approximation UPCA problem, we can apply Back-Propagation extended either using a straightforward deflation procedure or with the use of lateral orthogonalizing connections in the hidden layer. All proposed models were tested and the simulation results confirm the theoretical expectations.

Original language | English (US) |
---|---|

Title of host publication | Neural Networks for Signal Processing |

Publisher | Publ by IEEE |

Pages | 50-59 |

Number of pages | 10 |

ISBN (Print) | 0780301188 |

State | Published - Dec 1 1991 |

Event | Proceedings of the 1991 Workshop on Neural Networks for Signal Processing - NNSP-91 - Princeton, NJ, USA Duration: Sep 30 1991 → Oct 2 1991 |

### Publication series

Name | Neural Networks for Signal Processing |
---|

### Other

Other | Proceedings of the 1991 Workshop on Neural Networks for Signal Processing - NNSP-91 |
---|---|

City | Princeton, NJ, USA |

Period | 9/30/91 → 10/2/91 |

### All Science Journal Classification (ASJC) codes

- Engineering(all)

## Fingerprint Dive into the research topics of 'Neural networks for extracting Unsymmetric Principal Components'. Together they form a unique fingerprint.

## Cite this

*Neural Networks for Signal Processing*(pp. 50-59). (Neural Networks for Signal Processing). Publ by IEEE.