Dergiler / Electrica / 2003 / Cilt: 3 Sayı: 1

MODULAR AND HIERARCHICAL SPECIALIZATION IN NEURAL NETWORKS

Sayfa
719–726
Yayın Tarihi
2012-01-09
DOI
—
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Further we illustrate that a deliberate mix of hierarchically imposed evaluation functions will improve network accuracy and learning speed.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Modularity and hierarchy are fundamental notions in structured system design.
📊
Temel Bulgular & Veri:By subdividing a large and unstructured problem into smaller and tractable chunks, design automation becomes possible.
💡
Sonuç & Katkı:Further we illustrate that a deliberate mix of hierarchically imposed evaluation functions will improve network accuracy and learning speed.
🔬Tür:Araştırma Makalesi
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:Alan Parametreleri

Abstract

Modularity and hierarchy are fundamental notions in structured system design. By subdividing a large and unstructured problem into smaller and tractable chunks, design automation becomes possible. In this paper we discuss the use of modularity and hierarchy for functional specialization during the development of neural networks. We study the behavioral differences and requirements for back-propagation training of feed-forward networks. Further we illustrate that a deliberate mix of hierarchically imposed evaluation functions will improve network accuracy and learning speed.

🔖

Bu Makaleye Atıf Yap

BERG, A. T., SPAANENBURG, L. (2012). MODULAR AND HIERARCHICAL SPECIALIZATION IN NEURAL NETWORKS. Electrica, Cilt: 3 Sayı: 1, 719–726. https://ajindex.com/articles/1017729

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...