Neural computation of alpha parameter with the use of differential gain, wavelength and number of quantum-wells


CELEBI F., Danisman K., YILDIRIM R.

Conference on Photonics - Design, Technology and Packaging, Perth, Avustralya, 10 - 12 Aralık 2003, cilt.5277, ss.346-349 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 5277
  • Doi Numarası: 10.1117/12.523297
  • Basıldığı Şehir: Perth
  • Basıldığı Ülke: Avustralya
  • Sayfa Sayıları: ss.346-349
  • Erciyes Üniversitesi Adresli: Evet

Özet

A different method to determine a (Alpha) parameter for different number of Quantum-wells is presented. The Levenberg-Marquardt algorithm is used to train the Artificial Neural Networks(ANNs) which has a quadratic speed of convergence. Both the computed and the test results are in very good agreement with the experimental results reported elsewhere.