Modular Learning in Neural Networks A Modularized Approach to Neural Network Classification |
|
Author:
| Hrycej, Tomas |
Series title: | Sixth Generation Computer Technologies Ser. |
ISBN: | 978-0-471-57154-4 |
Publication Date: | Oct 1992 |
Publisher: | John Wiley & Sons, Incorporated
|
Imprint: | Wiley-Interscience |
Book Format: | Hardback |
List Price: | USD $135.00 |
Book Description:
|
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...
More DescriptionProvides 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).