Modular Learning in Neural Networks: A Modularized Approach to Neural Network Classification (Sixth-Generation Computer Technology Series)

Hrycej, Tomas

ISBN 10: 0471571547 / ISBN 13: 9780471571544

Published by John Wiley & Sons Inc, 1992

About this Item

Zustand: Sehr gut | Seiten: 235 | Sprache: Englisch | Produktart: Bücher | Keine Beschreibung verfügbar.

Seller Inventory # 37408107/202

Bibliographic Details

• Title: Modular Learning in Neural Networks: A Modularized Approach to Neural Network Classification (Sixth-Generation Computer Technology Series)
• Publisher: John Wiley & Sons Inc
• Publication Date: 1992
• Language: English
• ISBN 10: 0471571547
• ISBN 13: 9780471571544
• Binding: Hardcover
• Condition: Sehr gut
• Seller catalogs:
  • Bücher

About this title

Synopsis

Provides evidence that modular learning is helpful in improving learning performance. Numerous approaches were tested including decomposition of learning into modules using various learning types (supervised and unsupervised learning); decomposition of the mapping to be represented (linear and nonlinear parts); decomposition of the neural network to minimize harmful interaction during learning; decomposition of the application task into subtasks that are learned separately; and decomposition into a knowledge-based part and a learning part. These methods were tested on two ``benchmark'' cases--a medical classification problem (7,200 cases of thyroid disorder) and a handwritten digits classification problem (20,000 cases).