Jeff Smith builds large-scale machine learning systems using Scala and Spark. For the past decade, he has been working on data science applications at various startups in New York, San Francisco, and Hong Kong. He blogs and speaks about various aspects of building real world machine learning systems.. Machine learning applications autonomously reason about data at massive scale. It's important that they remain responsive in the face of failure and changes in load. But machine learning systems are different than other applications when it comes to testing, building, deploying, and monitoring. Reactive Machine Learning Systems teaches readers how to implement reactive design solutions in their machine learning systems to make them as reliable as a well-built web app. Using Scala and powerful frameworks such as Spark, MLlib, and Akka, they'll learn to quickly and reliably move from a single machine to a massive cluster. Key Features: * Example-rich guide * Step-by-step guide * Move from single-machine to massive cluster Readers should have intermediate skills in Java or Scala. No previous machine learning experience is required. About the Technology: Machine learning systems are different than other applications when it comes to testing, building, deploying, and monitoring. To make machine learning systems reactive, you need to understand both reactive design patterns and modern data architecture patterns.
Walkthrough of the Scala, Akka, Spark, MLib approach At first I thought this book might cover a broad range of machine learning systems, but actually it is pretty specialized in the platform technique. This book is focused on the author's expertise in production-grade systems using Scala, Akka, Spark, and MLib. So don't expect anything about TensorFlow, PyTorch, Keras, MXNet, The Microsoft Cognitive Toolkit, Caffe, Deeplearning4j, or Chainer. The book doesn't get into these neural network platforms, these are not within the book's specialty area. This book reads like a tutorial, and that's the best way to make sense of the content. It is hard to read it like a reference book and skip around because the explanations are formed around the stories of real-world problems that build up from previous chapters. Overall this is an excellent book for understanding one specific set of technologies via real-world examples.
Provide a good insight on the topic Overall I have been enjoying this book. It is short, concise and well written and provide a first level insight on how to build reactive ML systems. The book doesn't require any prior knowledge on the topic but require some Java and Scala expertise (at least be able to read code). Some of the example picked are not of the best taste. I understand trying to add some humor to some dry topics but in this case I don't think it added much.
A tutorial for scaling Scala/Spark/MLib applications in production environments This book barely lives upto its potential - while the technical content is sufficient for anyone looking to build a production grade learning system (especially if you have decided on your tech stack), it could have focused more on real world examples and toned down the forced sense of humor. The narrative style is a bit too informal to use as a supplement for a course, but may be fine for someone looking to broaden their skills in Scala/Spark. The author has organized the material well and progressively conveys the key features for a learning system. Domains where such systems are in great demand include finance and healthcare, but this does not address unique challenges related to either. A good starting point for building learning systems , especially for Scala/Spark.
Decent book, but not for everyone I read this book after having a few other ML books, so while I wasn't as familiar with Deep Learning, it wasn't my first introduction. Unfortunately, this book focuses on a lot of languages that I don't use in my day-to-day. I use primarily Python, and know a bit of TensorFlow and Keras. I've dabbled a bit with AWS and Spark/PySpark, and even just a vague recognition was enough for me to understand this book, but ultimately this book is aimed at someone who isn't me. That said, I still think it's a pretty good book -- the platforms the book covers are quite popular, so I was glad to learn a bit more about them, even if I don't have any way to apply them at the moment.
Rating : 3.3 of 411 Reviewers
Rating : 3.5 of 404 Reviewers
Rating : 3.5 of 112 Reviewers