Machine Learning: An Algorithmic Perspective

by Stephen Marsland

Traditional books on machine learning can be divided into two groups — those aimed at advanced undergraduates or early postgraduates with reasonable mathematical knowledge and those that are primers on how to code algorithms. The field is ready for a text that not only demonstrates how to use the algorithms that make up machine learning methods, but also provides the background needed to understand how and why these algorithms work. Machine An Algorithmic Perspective is that text.Theory Backed up by Practical ExamplesThe book covers neural networks, graphical models, reinforcement learning, evolutionary algorithms, dimensionality reduction methods, and the important area of optimization. It treads the fine line between adequate academic rigor and overwhelming students with equations and mathematical concepts. The author addresses the topics in a practical way while providing complete information and references where other expositions can be found. He includes examples based on widely available datasets and practical and theoretical problems to test understanding and application of the material. The book describes algorithms with code examples backed up by a website that provides working implementations in Python. The author uses data from a variety of applications to demonstrate the methods and includes practical problems for students to solve.Highlights a Range of Disciplines and ApplicationsDrawing from computer science, statistics, mathematics, and engineering, the multidisciplinary nature of machine learning is underscored by its applicability to areas ranging from finance to biology and medicine to physics and chemistry. Written in an easily accessible style, this book bridges the gaps between disciplines, providing the ideal blend of theory and practical, applicable knowledge.

Genres: Computer Science, Artificial Intelligence, Mathematics, Programming, Education, Technology, Nonfiction

406 pages, Kindle Edition

First published January 1, 2009

Reviews

[Simon Meißner · Rating 4 out of 5]

Dieses Buch war Basis einer einführenden Veranstaltung an meiner Uni.

Das Buch vermittelt die Grundlagen von künstlichen neuronalen Netzen und maschinellen Lernen.
Dabei werden vor allem das single-, und multilayered Perceptron betrachtet. Zu Beginn gibt es ein paar einführende Kapitel, die einen guten Einstieg in das Thema verschaffen.

Leider wird das Buch nach kurzer Zeit relativ komplex, behandelt ausführlich mathematische Zusammenhänge und geht über das Grundlagenwissen weit hinaus. Was durchaus nicht schlecht ist aber für meinen individuellen Zeit- und Standpunkt zu tiefgreifend ist/war.

Mir hat sehr gefallen, dass der Autor begleitend zu dem Buch eine Website betreibt, die Testcode in python enthält, um die Theorie direkt in der Praxis umzusetzen. Außerdem werden am Ende jedes Kapitels, Fragen/Aufgaben gestellt um das Gelernte zu überprüfen.

[Kai Wolf · Rating 4 out of 5]

Wonderful introduction to Machine Learning basics using Python (and numpy). Doesn't touch Deep Learning concepts as this book came out before the current AI hype really started to kick off.

[YOUSSEF AIDANI · Rating 1 out of 5]

Even though it's so wordy the explanation are unclear and sometimes missing. Some concepts we superficially explained. Chapters are missing summaries. There are also frequent errors in formulas example the variance-bias error decomposition equation has clear problems in it in page 36

[zedoul · Rating 2 out of 5]

So so, and Python codes was nice.

[Adri Molina · Rating 3 out of 5]

A great book for starting digging into neural networks. The explanations are quite clear and straightforwardly written but kind of outdated as well.
I'd recommend it as a first step into machine learning algorithms before taking some hands-on approaches.

[Jessada Karnjana · Rating 5 out of 5]

เป็นอีกเล่มหนึ่ง (ฉบับ second edition) ที่ใช้ประกอบการสอน ML ซึ่งในมุมของ algorithm ถือว่าชัดเจนดีทีเดียว มีข้ามรายละเอียด math บ้าง และหาเติมเต็มได้ด้วยเล่มอื่น ๆ สำหรับ algorithmic perspective ดีงาม

[Nick · Rating 2 out of 5]

Some of the many text errors are kind of unforgivable.

[Rick Sam · Rating 2 out of 5]

Look at this,



Would you read this, Giant Blog of Text?

[Brett Dargan · Rating 4 out of 5]

I read this while I was reading Data Mining (weka one). Explanations in here are terse and in python, which helped me skip over some of the wordy explanations in Data Mining book.

[Alon Gutman · Rating 2 out of 5]

Nice, but too mathematical, and go too deep on unimportant stuff on the one hand, and is missing some ML fundamentals on the other hand.

[Rishabh · Rating 4 out of 5]

variable description missing in equations, everything else is lucid and very clear