|
||||||||||||||||||||
|
||||||||||||||||||||
|
||||||||||||||||||||
C4.5
und über 1 Million weitere Bücher verfügbar für Amazon Kindle .
Erfahren Sie mehr
| ||||||||||||||||||
|
|
Produktinformation
Möchten Sie die Produktinformationen aktualisieren oder Feedback zu den Produktabbildungen geben?
Ist der Verkauf dieses Produkts für Sie nicht akzeptabel? |
Mehr über den Autor
Entdecken Sie Bücher, lesen Sie über Autoren und mehr
› Besuchen Sie die Seite von J. R. Quinlan auf Amazon
› Besuchen Sie die Seite von J. R. Quinlan auf Amazon
Produktbeschreibungen
Kurzbeschreibung
Classifier systems play a major role in machine learning and knowledge-based systems, and Ross Quinlan's work on ID3 and C4.5 is widely acknowledged to have made some of the most significant contributions to their development. This book is a complete guide to the C4.5 system as implemented in C for the UNIX environment. It contains a comprehensive guide to the system's use , the source code (about 8,800 lines), and implementation notes. The source code and sample datasets are also available on a 3.5-inch floppy diskette for a Sun workstation. C4.5 starts with large sets of cases belonging to known classes. The cases, described by any mixture of nominal and numeric properties, are scrutinized for patterns that allow the classes to be reliably discriminated. These patterns are then expressed as models, in the form of decision trees or sets of if-then rules, that can be used to classify new cases, with emphasis on making the models understandable as well as accurate. The system has been applied successfully to tasks involving tens of thousands of cases described by hundreds of properties. The book starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting. Advantages and disadvantages of the C4.5 approach are discussed and illustrated with several case studies. This book and software should be of interest to developers of classification-based intelligent systems and to students in machine learning and expert systems courses.
Synopsis
Classifier systems play a major role in machine learning and knowledge-based systems, and Ross Quinlan's work on ID3 and C4.5 is widely acknowledged to have made some of the most significant contributions to their development. This book is a complete guide to the C4.5 system as implemented in C for the UNIX environment. It contains a comprehensive guide to the system's use , the source code (about 8,800 lines), and implementation notes. The source code and sample datasets are also available for download (see below). C4.5 starts with large sets of cases belonging to known classes. The cases, described by any mixture of nominal and numeric properties, are scrutinized for patterns that allow the classes to be reliably discriminated. These patterns are then expressed as models, in the form of decision trees or sets of if-then rules, that can be used to classify new cases, with emphasis on making the models understandable as well as accurate. The system has been applied successfully to tasks involving tens of thousands of cases described by hundreds of properties.The book starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting. Advantages and disadvantages of the C4.5 approach are discussed and illustrated with several case studies. This book and software should be of interest to developers of classification-based intelligent systems and to students in machine learning and expert systems courses.
In diesem Buch
(Mehr dazu)
Einleitungssatz
Most applications of artificial intelligence to tasks of practical importance are based on constructing a model of the knowledge used by a human expert. Lesen Sie die erste Seite
Buchdeckel | Copyright | Inhaltsverzeichnis | Auszug | Stichwortverzeichnis | Rückseite
Most applications of artificial intelligence to tasks of practical importance are based on constructing a model of the knowledge used by a human expert. Lesen Sie die erste Seite
Mehr entdecken
Wortanzeiger
Ausgewählte Seiten ansehenWortanzeiger
Buchdeckel | Copyright | Inhaltsverzeichnis | Auszug | Stichwortverzeichnis | Rückseite
Tags(Was ist das?)Bei einem Tag handelt es sich um ein Schlagwort, das zum Produkt passt.
Tags erleichtern allen Kunden die Suche und die Sortierung ihrer Lieblingsprodukte. |
Kundenrezensionen
Die hilfreichsten Kundenrezensionen
1 von 1 Kunden fanden die folgende Rezension hilfreich
Format:Taschenbuch
If you want to get introduced to Decision Trees algorithms, you must read this book. Ross Quinlan is the father of 'C 4.5' the most widely used tree algorithm. Most other algorithms (except for Chaid, which is older) are enhancements to C4.5 If you are from marketing, this is not a book for you. Why didn't you include a disk instead of so much source code pages, Ross ?
Format:Taschenbuch|Von Amazon bestätigter Kauf
Dieses Buch enthält im ersten Teil eine sehr gute Beschreibung der C4.5 Klassifier Methoden. Was einem immer wieder auffällt: Das Hauptargument des Autors sind nicht theoretische Überlegungen. So schreibt er z.B. Wahrscheinlichkeit an mehreren Stellen unter Anführungszeichen, weil es es sich im streng mathematischen Sinn um keine Wahrscheinlichkeiten handelt. Letztendlich läuft die Argumentation immer darauf hinaus: Auch wenn es theoretisch nicht sauber ist, aber durch jahrelanges Ausprobieren habe ich herausgefunden, dass dies und das am besten funktioniert. Das ist bei allen praktisch erfolgreichen Systemen die ich kenne der Fall. Z.B. sind die theoretisch optimalen Lernraten viel zu gering. Theoretisch geht es um die sichere Konvergenz im Unendlichen. Real hat man aber nie soviel Zeit. Das System soll schon nach 1000 Schritten brauchbare Ergebnisse liefern. Meines Erachtens ist dieser Fakt ein Armutszeugnis für die moderne Theorieproduktion. L.Breiman hat dies auch in einem vielbeachteten Artikel schön auf den Punkt gebracht (siehe [1]). Es hat allerdings nichts geholfen.
Im zweiten Teil des Buches ist der vollständige C4.5 Kode abgedruckt. Das ist sehr mutig. Kode ist etwas sehr Intimes und jeder Programmierer hat Angst dass die Welt quasi auch seine angeschissenen Programmierunterhosen sieht. Es ist aber ein sehr schöner, guter alter K&R-C Kode. Wobei ich nicht nur den eigentlichen Machine-Learning Kode, sondern auch die vielen Support-Routinen, interessant gefunden habe. Z.B. ist ein häufiges Problem: Man mische den Input gut durch (shuffle). Der Kode enthält eine sehr nette shuffle-Routine.
Man kann sich - eine etwas neuere Version - des Kodes auch auf der Homepage des Authors herunterladen (der im Buch angegebene Verlag-Link ist obsolet). Ich habe es aber trotzdem sinnvoll gefunden, dass der Kode auch im Buch abgedruckt war. Es liest sich ein Buch einfach besser.
[1] L.Breiman, Statistical Modeling: The Two Cultures
Im zweiten Teil des Buches ist der vollständige C4.5 Kode abgedruckt. Das ist sehr mutig. Kode ist etwas sehr Intimes und jeder Programmierer hat Angst dass die Welt quasi auch seine angeschissenen Programmierunterhosen sieht. Es ist aber ein sehr schöner, guter alter K&R-C Kode. Wobei ich nicht nur den eigentlichen Machine-Learning Kode, sondern auch die vielen Support-Routinen, interessant gefunden habe. Z.B. ist ein häufiges Problem: Man mische den Input gut durch (shuffle). Der Kode enthält eine sehr nette shuffle-Routine.
Man kann sich - eine etwas neuere Version - des Kodes auch auf der Homepage des Authors herunterladen (der im Buch angegebene Verlag-Link ist obsolet). Ich habe es aber trotzdem sinnvoll gefunden, dass der Kode auch im Buch abgedruckt war. Es liest sich ein Buch einfach besser.
[1] L.Breiman, Statistical Modeling: The Two Cultures
Die hilfreichsten Kundenrezensionen auf Amazon.com (beta)
Amazon.com:
4 Rezensionen
15 von 16 Kunden fanden die folgende Rezension hilfreich
Invaluable for serious users of See5 or C5.0
15. April 2008
Format:Taschenbuch
Despite its age this classic is invaluable to any serious user of See5 (Windows) or C5.0 (UNIX). C4.5 (See5/C5) is a linear classifier system that is often used for machine learning, or as a data mining tool for discovering patterns in databases. The classifiers can be in the form of either decision trees or rule sets. Just like ID3 it employs a "divide and conquer" strategy and uses entropy (information content) to compute its gain ratio (the split criteria).
C5.0 and See5 are built on C4.5, which is open source and free. However, since C5.0 and See5 are commercial products the code and the internals of the See5/C5 algorithms are not public. This is why this book is still so valuable. The first half of the book explains how C4.5 works, and describes its features, for example, partitioning, pruning, and windowing in detail. The book also discusses how C4.5 should be used, and potential problems with over-fit and non-representative data. The second half of the book gives a complete listing of the source code; 8,800 lines of C-code.
C5.0 is faster and more accurate than C4.5 and has features like cross validation, variable misclassification costs, and boost, which are features that C4.5 does not have. However, since minor misuse of See5 could have cost our company tens of millions of dollars it was important that we knew as much as possible about what we were doing, which is why this book was so valuable.
The reasons we did not use, for example, neural networks were:
(1) We had a lot of nominal data (in addition to numeric data)
(2) We had unknown attributes
(3) Our data sets were typically not very large and still we had a lot of attributes
(4) Unlike neural networks, decision trees and rule sets are human readable, possible to comprehend, and can be modified manually if necessary. Since we had problems with non-representative data but understood these problems as well as our system quite well, it was sometimes advantageous for us to modify the decision trees.
If you are in a similar situation I recommend See5/C5 as well as this book.
C5.0 and See5 are built on C4.5, which is open source and free. However, since C5.0 and See5 are commercial products the code and the internals of the See5/C5 algorithms are not public. This is why this book is still so valuable. The first half of the book explains how C4.5 works, and describes its features, for example, partitioning, pruning, and windowing in detail. The book also discusses how C4.5 should be used, and potential problems with over-fit and non-representative data. The second half of the book gives a complete listing of the source code; 8,800 lines of C-code.
C5.0 is faster and more accurate than C4.5 and has features like cross validation, variable misclassification costs, and boost, which are features that C4.5 does not have. However, since minor misuse of See5 could have cost our company tens of millions of dollars it was important that we knew as much as possible about what we were doing, which is why this book was so valuable.
The reasons we did not use, for example, neural networks were:
(1) We had a lot of nominal data (in addition to numeric data)
(2) We had unknown attributes
(3) Our data sets were typically not very large and still we had a lot of attributes
(4) Unlike neural networks, decision trees and rule sets are human readable, possible to comprehend, and can be modified manually if necessary. Since we had problems with non-representative data but understood these problems as well as our system quite well, it was sometimes advantageous for us to modify the decision trees.
If you are in a similar situation I recommend See5/C5 as well as this book.
12 von 13 Kunden fanden die folgende Rezension hilfreich
The most clear work on Decision Trees available !
4. Mai 1999
Format:Taschenbuch
If you want to get introduced to Decision Trees algorithms, you must read this book. Ross Quinlan is the father of 'C 4.5' the most widely used tree algorithm. Most other algorithms (except for Chaid, which is older) are enhancements to C4.5 If you are from marketing, this is not a book for you. Why didn't you include a disk instead of so much source code pages, Ross ?
2 von 2 Kunden fanden die folgende Rezension hilfreich
Classical book - a bit pricy
27. Februar 2006
Format:Taschenbuch
This a very classical macihne learning book. The presentation of the material is very lucid. Dr. Quinlan is a great writer. However I would say that the book is a bit pricy. More than half of the book is C4.5 code. I personally would have liked more of the theory part. Also an updated edition with C5.0 algorithm will be very much welcome from the readers. I am not sure whether Dr. Quinlan has a book on C5.0 or is the enhancements over C4.5 are completely proprietory.
Overall, it is a good book to learn about the C4.5 algorithm.
Overall, it is a good book to learn about the C4.5 algorithm.
Waren diese Rezensionen hilfreich?
Wir wollen von Ihnen hören.
Kunden diskutieren
|
Das Forum zu diesem Produkt
Fragen stellen, Meinungen austauschen, Einblicke gewinnen Aktive Diskussionen in ähnlichen Foren
Kundendiskussionen durchsuchen
|
Ähnliche Foren
|
||||||||||||||||||||||||||||||||||
Lieblingslisten
Ähnliche Artikel finden
Anhand des Sachgebietes nach ähnlichen Produkten suchen:
Ihr Kommentar
Möchten Sie die Produktinformationen aktualisieren oder Feedback zu den Produktabbildungen geben?
|
