Design of dynamical associative memories via finite-state recurrent neural networks
Sonlu durumlu dinamik yapay sinir ağları ile çağrışımlı bellek tasarımı
- Tez No: 138902
- Danışmanlar: PROF. DR. CÜNEYT GÜZELİŞ
- Tez Türü: Doktora
- Konular: Elektrik ve Elektronik Mühendisliği, Electrical and Electronics Engineering
- Anahtar Kelimeler: Associative memory, Hopfield network, information storage, information retrieval, image reconstruction, Associative memory, Hopfield network, information storage, information retrieval, image reconstruction
- Yıl: 2003
- Dil: İngilizce
- Üniversite: Dokuz Eylül Üniversitesi
- Enstitü: Fen Bilimleri Enstitüsü
- Ana Bilim Dalı: Elektrik-Elektronik Mühendisliği Ana Bilim Dalı
- Bilim Dalı: Elektrik Elektronik Bilim Dalı
- Sayfa Sayısı: 128
Özet
ABSTRACT Information retrieval capability of recurrent neural networks and performances of their formerly-proposed design procedures are questioned in this thesis work. Five novel design methods for discrete Hopfield recurrent network model to restore prototype static vectors from their distorted versions along the operation on a finite state-space are then introduced. Qualitative properties provided by these methods are verified analytically, while quantitative ones are estimated by conducting computer experiments. A comparison of each proposed method with the conventional design procedures is presented in terms of these properties. The performances of the resulting networks are finally demonstrated on benchmark static information retrieval applications, namely character recognition and image reconstruction.
Özet (Çeviri)
ABSTRACT Information retrieval capability of recurrent neural networks and performances of their formerly-proposed design procedures are questioned in this thesis work. Five novel design methods for discrete Hopfield recurrent network model to restore prototype static vectors from their distorted versions along the operation on a finite state-space are then introduced. Qualitative properties provided by these methods are verified analytically, while quantitative ones are estimated by conducting computer experiments. A comparison of each proposed method with the conventional design procedures is presented in terms of these properties. The performances of the resulting networks are finally demonstrated on benchmark static information retrieval applications, namely character recognition and image reconstruction.
Benzer Tezler
- Yeni bir hata değişik delta ağ maddeli arttırılmış delta ağı (ADA)
Başlık çevirisi yok
M.EBRU KOLUSAYIN
Yüksek Lisans
Türkçe
1998
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrolİstanbul Teknik ÜniversitesiKontrol ve Bilgisayar Mühendisliği Ana Bilim Dalı
DOÇ. DR. MEHMET BÜLENT ÖRENCİK
- Mimari tasarımda bedenlenmiş empatik ve estetik 'öteki oluş' deneyimi
Embodied empathic and aesthetic 'becoming other' in architectural design
IŞIL İZLEM YAZ
Yüksek Lisans
Türkçe
2024
Mimarlıkİstanbul Teknik ÜniversitesiMimarlık Ana Bilim Dalı
PROF. DR. ELMİRA AYŞE GÜR
- Okunabilir kopyalama algoritmalı DSM sisteminin gerçeklenmesi
Başlık çevirisi yok
ÖZGÜR KORAY ŞAHİNGÖZ
Yüksek Lisans
Türkçe
1998
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrolİstanbul Teknik ÜniversitesiKontrol ve Bilgisayar Mühendisliği Ana Bilim Dalı
DOÇ. DR. TAKUHİ NADİA ERDOĞAN
- Kent meydanı: Kamusal-estetik çerçevede eleştirel bir değerlendirme
Urban square: A critical approach within the concepts of 'public' and 'aesthetics
NEVBAHAR ATALAY
- Hücresel yapay sinir ağları için iki öğrenme algoritması ve görüntü işleme uygulamaları
Two learning algorithms for cellular neural networks and their image processing applications
SİNAN KARAMAHMUT
Yüksek Lisans
Türkçe
1994
Elektrik ve Elektronik Mühendisliğiİstanbul Teknik ÜniversitesiDOÇ.DR. CÜNEYT GÜZELİŞ