Explanation-Based Neural Network Learning
A Lifelong Learning Approach
Authors: Thrun, Sebastian
Free PreviewBuy this book
- About this book
-
Lifelong learning addresses situations in which a learner faces a series of different learning tasks providing the opportunity for synergy among them. Explanation-based neural network learning (EBNN) is a machine learning algorithm that transfers knowledge across multiple learning tasks. When faced with a new learning task, EBNN exploits domain knowledge accumulated in previous learning tasks to guide generalization in the new one. As a result, EBNN generalizes more accurately from less data than comparable methods. Explanation-Based Neural Network Learning: A Lifelong Learning Approach describes the basic EBNN paradigm and investigates it in the context of supervised learning, reinforcement learning, robotics, and chess.
`The paradigm of lifelong learning - using earlier learned knowledge to improve subsequent learning - is a promising direction for a new generation of machine learning algorithms. Given the need for more accurate learning methods, it is difficult to imagine a future for machine learning that does not include this paradigm.'
From the Foreword by Tom M. Mitchell.
- Table of contents (6 chapters)
-
-
Introduction
Pages 1-17
-
Explanation-Based Neural Network Learning
Pages 19-48
-
The Invariance Approach
Pages 49-92
-
Reinforcement Learning
Pages 93-129
-
Empirical Results
Pages 131-176
-
Table of contents (6 chapters)
Recommended for you
Bibliographic Information
- Bibliographic Information
-
- Book Title
- Explanation-Based Neural Network Learning
- Book Subtitle
- A Lifelong Learning Approach
- Authors
-
- Sebastian Thrun
- Series Title
- The Springer International Series in Engineering and Computer Science
- Series Volume
- 357
- Copyright
- 1996
- Publisher
- Springer US
- Copyright Holder
- Kluwer Academic Publishers
- eBook ISBN
- 978-1-4613-1381-6
- DOI
- 10.1007/978-1-4613-1381-6
- Hardcover ISBN
- 978-0-7923-9716-8
- Softcover ISBN
- 978-1-4612-8597-7
- Series ISSN
- 0893-3405
- Edition Number
- 1
- Number of Pages
- XVI, 264
- Topics
