Scala for Machine Learning
By Patrick R. Nicolas
Publisher: Packt Publishing
Final Release Date: December 2014
Pages: 520

The discovery of information through data clustering and classification is becoming a key differentiator for competitive organizations. Machine learning applications are everywhere, from self-driving cars, engineering designs, biometrics, and trading strategies, to detection of genetic anomalies.

The book begins with an introduction to the functional capabilities of the Scala programming language that are critical to the creation of machine learning algorithms such as dependency injection and implicits.

Next, you'll learn about data preprocessing and filtering techniques. Following this, you'll move on to clustering and dimension reduction, Naive Bayes, regression models, sequential data, regularization and kernelization, support vector machines, neural networks, generic algorithms, and re-enforcement learning. A review of the Akka framework and Apache Spark clusters concludes the tutorial.

Product Details
Recommended for You
Customer Reviews

REVIEW SNAPSHOT®

by PowerReviews
oreillyScala for Machine Learning
 
5.0

(based on 2 reviews)

Ratings Distribution

  • 5 Stars

     

    (2)

  • 4 Stars

     

    (0)

  • 3 Stars

     

    (0)

  • 2 Stars

     

    (0)

  • 1 Stars

     

    (0)

Reviewed by 2 customers

Displaying reviews 1-2

Back to top

 
5.0

Practical, informative, insightful

By Matthew

from Helsinki, Finland

About Me Developer

Pros

  • Accurate
  • Detailed
  • Focused
  • Helpful examples
  • Practical

Cons

  • Dense

Best Uses

  • Expert
  • Intermediate
  • Student

Comments about oreilly Scala for Machine Learning:

Some technical books are heavy on theory, some are heavy on practicality. There are books that describe 'why' and others that show you 'how'. Personally, I have always tended towards the 'how' side of things - the 'cookbook' approach is one I have always liked. The more practical the better.

Scala For Machine Learning (full disclosure, I received an unpaid review copy) is as about as practical as it gets. Loaded with code examples, this book leaves you in no doubt that it will help you construct your own code, against your own data in the fastest time possible. But it does not take any short-cuts.

Machine Learning and Scala is a broad subject to cover and SFML does an admirable job of taking you from the first steps of data preparation, right the way through to a artificial neural networks and genetic algorithms.

I work with data - it has been my day-to-day working life for over twenty years, and there is never any shortage of new territory to cover. I am predominately data engineering focused, and whilst the data content is the most important thing, it is the technology that keeps me engaged. In the final chapter of SFML Nicolas covers a nice selection of frameworks for concurrent processing. This really piqued my interest - Apache Spark is a hot topic at the moment and is given a good few pages here, reviewing its Scala and Akka heritage and demonstrating its core design principles of in-memory persistence, scheduling laziness, distributed dataset actions and shared variables. Better yet Nicolas shows you how to get Spark up and running and executing your first K-means tasks.

The bulk of the book is made up with detailed reviews, explanations and implementation guides for different machine learning algorithms and methodologies. Each section is made up of a wealth of detailed explanation, detailed implementation instructions and guidelines, honestly - at times - the information density can be a little overwhelming, but it is all hugely valuable, and much appreciated.

Running through the whole book is, of course, an appreciation of Scala and its abilities to perform in a distributed manner, at scale. This is the sort work that Scala, in all of its object-functional glory, was designed to address. I have read other Scala books and the programming language has always been presented in a "you may be used to, but Scala…" fashion. I am happy to say that is not the case here, with solid examples, proper real world code and thorough debriefs - Scala is presented as it should be, a language in its own right, being dealt with on its own terms.

If your work or study includes components of machine learning and / or data processing - and you are looking for a modern take on some time-honoured methods, this book is work picking up and consuming, avidly.

(1 of 1 customers found this review helpful)

 
5.0

Worth reading

By mmatej

from bratislava

About Me Developer

Pros

  • Deep
  • Helpful examples
  • State Of The Art
  • Well-written

Cons

    Best Uses

    • Intermediate
    • Student

    Comments about oreilly Scala for Machine Learning:

    Studying machine learning during my university times and being an aspiring scala developer I picked this book up as an opportunity to learn scala while reading about what interests me the most in the field of computer science. This wont be an easy read for people not familiar with scala at all, but if you have some experience with the language and are interested in machine learning, I definitely recommend the book. It is a nice and quite deep dive into the topic. What I found very interesting was the optional math part available in each section. This book is also showing me where my understanding of scala is still superficial, the code is written a very good way.

    Displaying reviews 1-2

    Back to top

     
    Buy 2 Get 1 Free Free Shipping Guarantee
    Buying Options
    Immediate Access - Go Digital what's this?
    Ebook:  $35.99
    Formats:  ePub, Mobi, PDF