Jaringan neural Untuk Pengenalan Pola yang Invarian Terhadap Translasi Dan Rotan
Analog coupled neurons (CN) can be used in trainable pattern recognition systems. A training algorithm called Coupled Neuron Rule (CNR) is used to implement classification functions. A character recognition.system involving an invariance network and a trainable classifier is proposed. The invariance...
| Main Author: | |
|---|---|
| Format: | Article |
| Published: |
[Yogyakarta] : Universitas Gadjah Mada
1996
|
| Subjects: |
| Summary: | Analog coupled neurons (CN) can be used in trainable pattern recognition systems. A training algorithm called Coupled Neuron Rule (CNR) is used to implement classification functions.
A character recognition.system involving an invariance network and a trainable classifier is proposed. The invariance net can be trained to produce a set of outputs that are insensitive to translation and rotation of the retinal input patterns. The outputs of the invariance net are scrambled. When these outputs are fed to a trainable classifier, the final outputs are descrambled and the original patterns are reproduced in standard position and orientation |
|---|