What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

Key benefits

Skill up and implement tricky neural networks using Google's TensorFlow 1.x

An easy-to-follow guide that lets you explore reinforcement learning, GANs, autoencoders, multilayer perceptrons and more.

Hands-on recipes to work with Tensorflow on desktop, mobile, and cloud environment

Description

Deep neural networks (DNNs) have achieved a lot of success in the field of computer vision, speech recognition, and natural language processing. This exciting recipe-based guide will take you from the realm of DNN theory to implementing them practically to solve real-life problems in the artificial intelligence domain. In this book, you will learn how to efficiently use TensorFlow, Google’s open source framework for deep learning. You will implement different deep learning networks, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Deep Q-learning Networks (DQNs), and Generative Adversarial Networks (GANs), with easy-to-follow standalone recipes. You will learn how to use TensorFlow with Keras as the backend. You will learn how different DNNs perform on some popularly used datasets, such as MNIST, CIFAR-10, and Youtube8m. You will not only learn about the different mobile and embedded platforms supported by TensorFlow, but also how to set up cloud platforms for deep learning applications. You will also get a sneak peek at TPU architecture and how it will affect the future of DNNs. By using crisp, no-nonsense recipes, you will become an expert in implementing deep learning techniques in growing real-world applications and research areas such as reinforcement learning, GANs, and autoencoders.

Who is this book for?

This book is intended for data analysts, data scientists, machine learning practitioners and deep learning enthusiasts who want to perform deep learning tasks on a regular basis and are looking for a handy guide they can refer to. People who are slightly familiar with neural networks, and now want to gain expertise in working with different types of neural networks and datasets, will find this book quite useful.

What you will learn

• Leverage different data sets such as MNIST, CIFAR-10, and Youtube8m with TensorFlow and learn how to access and use them in your code

• Use TensorBoard to understand neural network architectures, optimize the learning process, and peek inside the neural network black box

• Use different regression techniques for prediction and classifi cation problems

• Build single and multilayer perceptrons in TensorFlow

• Implement a CNN and a RNN in TensorFlow, and use them to solve real-world problems

• Learn how Restricted Boltzmann Machines can be used to recommend movies

• Understand the implementation of autoencoders and deep belief networks, and use them for emotion detection

• Master the different reinforcement learning methods in order to implement game playing agents

What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

Frequently bought together

Neural Network Programming with TensorFlow

£32.99

£29.99

£36.99

Total £ 99.97

Kishore A Feb 16, 2018

This book gives a very good overview of the various algorithms to get one started in deep learning. I have especially liked the fact that it walks the reader through multiple use cases across all the algorithms. Additionally, it has a broad coverage including CNN, RNN, RL, Auto encoders, Capsule networks and even the implementation of tensorflow on mobile devices.Definitely a great buy!

Amazon Verified review

Juan Lopez Feb 05, 2018

Even for a good chef a recipe book always come handy, and thanks to the authors all Deep Learning professionals, enthusiasts, or beginners will have this Cookbook for consulting. From simple Linear Regressions to Generative Adversarial Networks you will find easy recipes to follow and learn how to implement all these kind of networks.

Amazon Verified review

A. Jaokar Jan 11, 2018

I bought this book (physical copy) from the Packt based on reading the author's previous book(on Keras). I have enjoyed the previous book and use it extensively because of its practical implementation approach. The same is followed here (but for core tensorflow instead of Keras). The cookbook approach helps a lot for tensorflow. Apart from CNNs, RNNS etc the book also covers Tensorflow mobile (which is of interest for me personally). The section on distributed tensorflow(Chapter 12) was new and interesting for me. Like in the first book, I referred to the author's git repo which I found useful. I used this book mainly to get a deeper understanding of tensorflow(I was starting from keras). It is also a good approach to learning tensorflow itself because of the cookbook approach. It even talks of Capsule networks. Hence, at the time of review(Jan 18) - its as current as Tensorflow can be. The distributed tensorflow also covers Azure and Amazon in addition to Google cloud(was nice to see the open approach). finally, I suggest that future versions of the book could expand on TPUs(also an interest for me based on my work)

Amazon Verified review

Sujit Pal Feb 18, 2018

I thought this was an awesome book that tries to teach a fairly complex framework like Tensorflow (TF) in a very accessible way. While the TF project does provide very good tutorials, the learning curve is quite steep. This book does require some familiarity with Python, but I think the learning curve to master TF using this book is considerably less steep than using the TF tutorials. In addition, it covers an incredible number of network architectures in quite a lot of depth. As expected from the Cookbook format, it also provides code that implements many of these architectures that you could use to jump start your own project. Overall, I think it is a very useful book that has enhanced my own understanding of many TF features and opened up the possibility to build some networks I wouldn't have thought to do before this.Disclaimer: I am a co-author on another book with one of the authors of this book, and reviewed some of the chapters as they were written. However, I did pay for the book (even though it was only $5 during the PackT Christmas sale) and I did go through the post-publication version of the book, and my review is based on this version.

Amazon Verified review

Non-expert Casual User Mar 01, 2018

I bought the book on Packt. But their review system is surely confusing. So leaving a review here.This book has been an absolutely a great investment of both time and money. Money of course was the trivial part here.As a matter of specialization, I have chosen to focus on vision based technologies but I was finding it difficult to resist the temptation of delving into the broader subject of deep learning across the spectrum.With not such a great hold of Mathematics, I had been reluctant, until now.The book simplifies working across platform. Apart from the regular Ubuntu based instructions, it comes with excellent documentation for Windows users too.While most DL enthusiasts are working with GPUs, the book also covers (and accurately) the CPU platforms. Both for Ubuntu and Windows.I covered the book across a long and busy schedule of project deadlines and travel. I had my lazy moments where I stuck to completing the rituals of the recipe and not go into conceptual depths. It didn't hamper my progress in the next chapters though.Apart from well laid out recipes, the interested learners can delve into the complex Mathematics too at their discretion.I will highly recommend the book for busy executives and engineers who want to have a smooth preview and a handheld tour of the potential of Deep Learning in their respective domains.

Amazon Verified review

TensorFlow 1.x Deep Learning Cookbook: Over 90 unique recipes to solve artificial-intelligence driven problems with Python

What do you get with eBook?

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with eBook?

Product Details

Frequently bought together

Recommendations for you

Customer reviews

Filter reviews by

People who bought this also bought

FAQs

TensorFlow 1.x Deep Learning Cookbook: Over 90 unique recipes to solve artificial-intelligence driven problems with Python

What do you get with eBook?

Contact Details

Billing Address

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with eBook?

Contact Details

Billing Address

Product Details

Packt Subscriptions

Frequently bought together

Recommendations for you

Customer reviews

Filter reviews by

People who bought this also bought

FAQs