Introduction to Learning Classifier Systems | springerprofessional.de

Springer Professional

nach oben

2017 | Buch

Kapitel lesen Erstes Kapitel lesen

Introduction to Learning Classifier Systems

verfasst von: Dr. Ryan J. Urbanowicz, Dr. Will N. Browne

Verlag: Springer Berlin Heidelberg

Buchreihe : SpringerBriefs in Intelligent Systems

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This accessible introduction shows the reader how to understand, implement, adapt, and apply Learning Classifier Systems (LCSs) to interesting and difficult problems. The text builds an understanding from basic ideas and concepts. The authors first explore learning through environment interaction, and then walk through the components of LCS that form this rule-based evolutionary algorithm. The applicability and adaptability of these methods is highlighted by providing descriptions of common methodological alternatives for different components that are suited to different types of problems from data mining to autonomous robotics.

The authors have also paired exercises and a simple educational LCS (eLCS) algorithm (implemented in Python) with this book. It is suitable for courses or self-study by advanced undergraduate and postgraduate students in subjects such as Computer Science, Engineering, Bioinformatics, and Cybernetics, and by researchers, data analysts, and machine learning practitioners.

Anzeige

Inhaltsverzeichnis

Frontmatter

Chapter 1. LCSs in a Nutshell

Abstract

This chapter aims to introduce readers to Learning Classifier Systems (LCSs) through the lens of an accessible but non-trivial classification problem. It offers a brief summary of the basic concepts and components of an LCS algorithm, concluding with code exercises that pair with this textbook to offer hands-on experience.

Ryan J. Urbanowicz, Will N. Browne

Chapter 2. LCS Concepts

Abstract

This chapter aims to provide an appreciation for core concepts that separate LCSs from other techniques. In particular, we provide insight into why they work, and how they are conceptually unique. It is hoped that the reader will appreciate that LCSs represent a machine learning concept, rather than a single technique. We consider the answers to questions such as (1) Rules/classifiers - What are they? Plus, how can they be represented and evaluated? (2) Why do we evolve a population of rules rather than a single rule as a solution? (3) What is the importance of cooperation and competition among classifiers? (4) How does an LCS interact with problems to find and generalise useful patterns? (5) What problem properties should be considered when deciding whether to apply an LCS? and (6) What are the general advantages and disadvantages of LCSs? The functional cycle and how to begin implementing an LCS are covered in the next chapter.

Ryan J. Urbanowicz, Will N. Browne

Chapter 3. Functional Cycle Components

Abstract

This chapter aims to build upon the brief, simplified description of an LCS functional cycle outlined in Section 1.3. Previously, we discussed how all LCSs include a form of discovery and learning components, and Figure 1.3 specifically illustrated many of the common LCS algorithm components in step-wise order. Here we will discuss these algorithmic components in greater detail, introduce some new ones, consider key adaptations to problem domains beyond the multiplexer example, and begin to discuss methodological differences between supervised and reinforcement learning, all within the purview of Michigan-style LCS architectures (see Section 4.3.3). This chapter will emphasise how the functional cycle seeks to learn useful state-action mappings by (1) matching the input state to classifiers (and triggering covering if needed), (2) determining whether these classifiers are correct or incorrect (or returning reward if the exact output is unknown), (3) updating the associated classifiers so their worth may be evaluated, (4) discovering potentially better rules when appropriate, and finally (5) deleting the least-contributing classifiers if necessary.

Ryan J. Urbanowicz, Will N. Browne

Chapter 4. LCS Adaptability

Abstract

This chapter aims to demonstrate how LCS algorithms have been adapted to different problem domains. This will be accomplished by differentiating major LCS algorithm subtypes, describing specific LCS implementations, and introducing additional variations of LCS components. An understanding of the different options and insight into the performance trade-offs is provided.

Ryan J. Urbanowicz, Will N. Browne

Chapter 5. Applying LCSs

Abstract

LCSs as a concept and framework are suited to a wide range of applications. This chapter describes how the various LCS methods can be chosen and adapted for certain types of problems, such as data mining or robot control. Specifically, this chapter offers a basic setup guide discussing logistics, design considerations, setting run parameters, tuning for performance, and troubleshooting. This book concludes with a summary of useful LCS resources beyond this introductory textbook.

Ryan J. Urbanowicz, Will N. Browne

Titel: Introduction to Learning Classifier Systems
verfasst von: Dr. Ryan J. Urbanowicz
Dr. Will N. Browne
Copyright-Jahr: 2017
Verlag: Springer Berlin Heidelberg
Electronic ISBN: 978-3-662-55007-6
Print ISBN: 978-3-662-55006-9
DOI: https://doi.org/10.1007/978-3-662-55007-6

Weitere Formate
Fachgebiete
Bücher
Zeitschriften
Themenseiten
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024