Advertisement

Learning from Good and Bad Data

  • Philip D. Laird

Table of contents

  1. Front Matter
    Pages i-xviii
  2. Identification in the Limit from Indifferent Teachers

    1. Front Matter
      Pages 1-1
    2. Philip D. Laird
      Pages 3-26
    3. Philip D. Laird
      Pages 27-53
    4. Philip D. Laird
      Pages 55-109
  3. Probabilistic Identification from Random Examples

    1. Front Matter
      Pages 111-111
    2. Philip D. Laird
      Pages 113-134
    3. Philip D. Laird
      Pages 135-195
    4. Philip D. Laird
      Pages 197-200
  4. Back Matter
    Pages 201-211

About this book

Introduction

This monograph is a contribution to the study of the identification problem: the problem of identifying an item from a known class us­ ing positive and negative examples. This problem is considered to be an important component of the process of inductive learning, and as such has been studied extensively. In the overview we shall explain the objectives of this work and its place in the overall fabric of learning research. Context. Learning occurs in many forms; the only form we are treat­ ing here is inductive learning, roughly characterized as the process of forming general concepts from specific examples. Computer Science has found three basic approaches to this problem: • Select a specific learning task, possibly part of a larger task, and construct a computer program to solve that task . • Study cognitive models of learning in humans and extrapolate from them general principles to explain learning behavior. Then construct machine programs to test and illustrate these models. xi Xll PREFACE • Formulate a mathematical theory to capture key features of the induction process. This work belongs to the third category. The various studies of learning utilize training examples (data) in different ways. The three principal ones are: • Similarity-based (or empirical) learning, in which a collection of examples is used to select an explanation from a class of possible rules.

Keywords

algorithms behavior classification inductive bias learning

Authors and affiliations

  • Philip D. Laird
    • 1
  1. 1.NASA Ames Research CenterUSA

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4613-1685-5
  • Copyright Information Springer-Verlag US 1988
  • Publisher Name Springer, Boston, MA
  • eBook Packages Springer Book Archive
  • Print ISBN 978-1-4612-8951-7
  • Online ISBN 978-1-4613-1685-5
  • Series Print ISSN 0893-3405
  • Buy this book on publisher's site
Industry Sectors
Pharma
Automotive
Chemical Manufacturing
Biotechnology
Finance, Business & Banking
Electronics
IT & Software
Telecommunications
Energy, Utilities & Environment
Aerospace
Engineering