Learning to Learn

  • Sebastian Thrun
  • Lorien Pratt

Table of contents

  1. Front Matter
    Pages i-viii
  2. Overview Articles

    1. Front Matter
      Pages 1-1
    2. Sebastian Thrun, Lorien Pratt
      Pages 3-17
    3. Lorien Pratt, Barbara Jennings
      Pages 19-43
    4. Anthony Robins
      Pages 45-67
  3. Prediction/Supervised Learning

    1. Front Matter
      Pages 69-69
    2. Jonathan Baxter
      Pages 71-94
    3. Rich Caruana
      Pages 95-133
    4. Nathan Intrator, Shimon Edelman
      Pages 135-157
    5. Sebastian Thrun
      Pages 181-209
  4. Relatedness

    1. Front Matter
      Pages 211-211
    2. Sebastian Thrun, Joseph O’Sullivan
      Pages 235-257
  5. Control

    1. Front Matter
      Pages 259-259
    2. Jürgen Schmidhuber, Jieyu Zhao, Nicol N. Schraudolph
      Pages 293-309
    3. Richard Maclin, Jude W. Shavlik
      Pages 311-347
  6. Back Matter
    Pages 349-354

About this book

Introduction

Over the past three decades or so, research on machine learning and data mining has led to a wide variety of algorithms that learn general functions from experience. As machine learning is maturing, it has begun to make the successful transition from academic research to various practical applications. Generic techniques such as decision trees and artificial neural networks, for example, are now being used in various commercial and industrial applications.
Learning to Learn is an exciting new research direction within machine learning. Similar to traditional machine-learning algorithms, the methods described in Learning to Learn induce general functions from experience. However, the book investigates algorithms that can change the way they generalize, i.e., practice the task of learning itself, and improve on it.
To illustrate the utility of learning to learn, it is worthwhile comparing machine learning with human learning. Humans encounter a continual stream of learning tasks. They do not just learn concepts or motor skills, they also learn bias, i.e., they learn how to generalize. As a result, humans are often able to generalize correctly from extremely few examples - often just a single example suffices to teach us a new thing.
A deeper understanding of computer programs that improve their ability to learn can have a large practical impact on the field of machine learning and beyond. In recent years, the field has made significant progress towards a theory of learning to learn along with practical new algorithms, some of which led to impressive results in real-world applications.
Learning to Learn provides a survey of some of the most exciting new research approaches, written by leading researchers in the field. Its objective is to investigate the utility and feasibility of computer programs that can learn how to learn, both from a practical and a theoretical point of view.

Keywords

algorithms artificial neural network cognition control data mining decision tree knowledge learning machine learning neural networks reinforcement learning

Editors and affiliations

  • Sebastian Thrun
    • 1
  • Lorien Pratt
    • 2
  1. 1.Carnegie Mellon UniversityUSA
  2. 2.Evolving Systems, Inc.USA

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4615-5529-2
  • Copyright Information Kluwer Academic Publishers 1998
  • Publisher Name Springer, Boston, MA
  • eBook Packages Springer Book Archive
  • Print ISBN 978-1-4613-7527-2
  • Online ISBN 978-1-4615-5529-2
  • About this book