Book DetailAuthor/Editor(s): N.D. Lewis
Publication Date: January 10, 2016
Publisher: CreateSpace Independent Publishing Platform
Size: 4.90 MB
Book DescriptionMaster Deep Learning with this fun, practical, hands on guide.
With the explosion of big data deep learning is now on the radar. Large companies such as Google, Microsoft, and Facebook have taken notice, and are actively growing in-house deep learning teams. Other large corporations are quickly building out their own teams. If you want to join the ranks of today's top data scientists take advantage of this valuable book. It will help you get started. It reveals how deep learning models work, and takes you under the hood with an easy to follow process showing you how to build them faster than you imagined possible using the powerful, free R predictive analytics package.
Bestselling decision scientist Dr. N.D. Lewis shows you the shortcut up the steep steps to the very top. It's easier than you think. Through a simple to follow process you will learn how to build the most successful deep learning models used for learning from data. Once you have mastered the process, it will be easy for you to translate your knowledge into your own powerful applications.
If you want to accelerate your progress, discover the best in deep learning and act on what you have learned, this book is the place to get started.
You'll learn how to:
- Understand Deep Neural Networks
- Use Autoencoders
- Unleash the power of Stacked Autoencoders
- Leverage the Restricted Boltzmann Machine
- Develop Recurrent Neural Networks
- Master Deep Belief Networks
Everything you need to get started is contained within this book. It is your detailed, practical, tactical hands on guide - the ultimate cheat sheet for deep learning mastery. A book for everyone interested in machine learning, predictive analytic techniques, neural networks and decision science. Start building smarter models today using R!
According to the book, you'll learn how to, develop recurrent neural networks, build elman neural networks, deploy jordan neural networks, create cascade correlation neural networks, understand deep neural networks, use autoencoders, unleash the power of stacked autoencoders, leverage the restricted boltzmann machine and master deep belief networks. Now to be candid I wasn't entirely sure what all of those things meant in the first place, so my goal wasn't necessarily to understand how to do them but to appreciate what they are and develop an understanding of how they could be implemented with R if I was so inclined. Based on the text, a whole bunch of illustrations, and snippets of example code, I found this book to be very informative, conversationally written (kind of surprising given the topic) and easy to navigate. I plan on reading a second time through and focusing more on the code examples, but I certainly got what I was hoping for the first time for.
--David S. Saunders, Amazon Customer Reviews