Explanation-Based Neural Network Learning

1. Front Matter

   Pages i-xv

   PDF

2. Introduction

   • Sebastian Thrun

   Pages 1-17

3. Explanation-Based Neural Network Learning

   • Sebastian Thrun

   Pages 19-48

4. The Invariance Approach

   • Sebastian Thrun

   Pages 49-92

5. Reinforcement Learning

   • Sebastian Thrun

   Pages 93-129

6. Empirical Results

   • Sebastian Thrun

   Pages 131-176

7. Discussion

   • Sebastian Thrun

   Pages 177-193

8. Back Matter

   Pages 195-264

   PDF

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.

• algorithms
• artificial neural network
• knowledge
• learning
• lifelong learning
• machine learning
• neural networks
• reinforcement learning
• robot
• robotics
• supervised learning

• Carnegie Mellon University, USA

  Sebastian Thrun

Policies and ethics