Machine Learning: From Theory to Applications

1. Front Matter

   PDF

2. Strategic directions in machine learning

   • Stephen José Hanson, Werner Remmele, Ronald L. Rivest

   Pages 1-4

3. Introduction

   • Ronald L. Rivest

   Pages 5-7

4. Training a 3-node neural network is NP-complete

   • Avrim L. Blum, Ronald L. Rivest

   Pages 9-28

5. Cryptographic limitations on learning Boolean formulae and finite automata

   • Michael J. Kearns, Leslie G. Valiant

   Pages 29-49

6. Inference of finite automata using homing sequences

   • Ronald L. Rivest, Robert E. Schapire

   Pages 51-73

7. Introduction

   • Werner Remmele

   Pages 75-77

8. Adaptive search by learning from incomplete explanations of failures

   • Neeraj Bhatnagar

   Pages 79-92

9. Learning of rules for fault diagnosis in power supply networks

   • R. Meunier, R. Scheiterer, A. Hecht

   Pages 93-105

10. Cross references are features

    • Robert W. Schwanke, Michael A. Platoff

    Pages 107-123

11. The schema mechanism

    • Gary L. Drescher

    Pages 125-138

12. L-ATMS: A tight integration of EBL and the ATMS

    • Kai Zercher

    Pages 139-152

13. Introduction

    • Stephen Josè Hanson

    Pages 153-156

14. Massively parallel symbolic induction of protein structure/function relationships

    • Richard H. Lathrop, Teresa A. Webster, Temple F. Smith, Patrick H. Winston

    Pages 157-173

15. Task decomposition through competition in a modular connectionist architecture: The what and where vision tasks

    • Robert A. Jacobs, Michael I. Jordan, Andrew G. Barto

    Pages 175-202

16. Phoneme discrimination using connectionist networks

    • Raymond L. Watrous

    Pages 203-227

17. Behavior-based learning to control IR oven heating: Preliminary investigations

    • R. Chou, P. Liu, J. Vallino, M. Y. Chiu

    Pages 229-240

18. Trellis codes, receptive fields, and fault tolerant, self-repairing neural networks

    • Thomas Petsche, Bradley W. Dickinson

    Pages 241-268

19. Back Matter

    PDF

This volume includes some of the key research papers in the area of machine learning produced at MIT and Siemens during a three-year joint research effort. It includes papers on many different styles of machine learning, organized into three parts. Part I, theory, includes three papers on theoretical aspects of machine learning. The first two use the theory of computational complexity to derive some fundamental limits on what isefficiently learnable. The third provides an efficient algorithm for identifying finite automata. Part II, artificial intelligence and symbolic learning methods, includes five papers giving an overview of the state of the art and future developments in the field of machine learning, a subfield of artificial intelligence dealing with automated knowledge acquisition and knowledge revision. Part III, neural and collective computation, includes five papers sampling the theoretical diversity and trends in the vigorous new research field of neural networks: massively parallel symbolic induction, task decomposition through competition, phoneme discrimination, behavior-based learning, and self-repairing neural networks.

• Automat
• algorithm
• algorithms
• artificial intelligence
• automata
• complexity
• intelligence
• learning
• machine learning

Policies and ethics