Learning by optimization in random neural networks
13th International Symposium on Computer and Information Sciences (ISCIS 98), BELEK ANTALYA, Türkiye, 26 - 28 Ekim 1998, cilt.53, ss.143-148, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 53
- Basıldığı Şehir: BELEK ANTALYA
- Basıldığı Ülke: Türkiye
- Sayfa Sayıları: ss.143-148
- Orta Doğu Teknik Üniversitesi Adresli: Evet
Özet
The random neural network model proposed by Gelenbe has a number of interesting features in addition to a well established theory. Gelenbe has also developed a learning algorithm for the recurrent random network model using gradient descent of a quadratic error function. We present a quadratic optimization approach for learning in the random neural network, particularly for image texture reconstruction.