Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Save more on your purchases! discount-offer-chevron-icon
Savings automatically calculated. No voucher code required.
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletter Hub
Free Learning
Arrow right icon
timer SALE ENDS IN
0 Days
:
00 Hours
:
00 Minutes
:
00 Seconds
Advanced Machine Learning with Python
Advanced Machine Learning with Python

Advanced Machine Learning with Python: Solve challenging data science problems by mastering cutting-edge machine learning techniques in Python

eBook
€26.98 €29.99
Paperback
€36.99
Subscription
Free Trial
Renews at $19.99p/m

What do you get with eBook?

Product feature icon Instant access to your Digital eBook purchase
Product feature icon Download this book in EPUB and PDF formats
Product feature icon Access this title in our online reader with advanced features
Product feature icon DRM FREE - Read whenever, wherever and however you want
OR
Modal Close icon
Payment Processing...
tick Completed

Billing Address

Table of content icon View table of contents Preview book icon Preview Book

Advanced Machine Learning with Python

Chapter 2. Deep Belief Networks

In the preceding chapter, we looked at some widely-used dimensionality reduction techniques, which enable a data scientist to get greater insight into the nature of datasets.

The next few chapters will focus on some more sophisticated techniques, drawing from the area of deep learning. This chapter is dedicated to building an understanding of how to apply the Restricted Boltzmann Machine (RBM) and manage the deep learning architecture one can create by chaining RBMs—the deep belief network (DBN). DBNs are trainable to effectively solve complex problems in text, image, and sound recognition. They are used by leading companies for object recognition, intelligent image search, and robotic spatial recognition.

The first thing that we're going to do is get a solid grounding in the algorithm underlying DBN; unlike clustering or PCA, this code isn't widely-known by data scientists and we're going to review it in some depth to build...

Neural networks – a primer

The RBM is a form of recurrent neural network. In order to understand how the RBM works, it is necessary to have a more general understanding of neural networks. Readers with an understanding of artificial neural network (hereafter neural network, for the sake of simplicity) algorithms will find familiar elements in the following description.

There are many accounts that cover neural networks in great theoretical detail; we won't go into great detail retreading this ground. For the purposes of this chapter, we will first describe the components of a neural network, common architectures, and prevalent learning processes.

The composition of a neural network

For unfamiliar readers, neural networks are a class of mathematical models that train to produce and optimize a definition for a function (or distribution) over a set of input features. The specific objective of a given neural network application can be defined by the operator using a performance measure...

Restricted Boltzmann Machine

The RBM is a fundamental part of this chapter's subject deep learning architecture—the DBN. The following sections will begin by introducing the theory behind an RBM, including the architectural structure and learning processes.

Following that, we'll dive straight into the code for an RBM class, making links between the theoretical elements and functions in code. We'll finish by touching on the applications of RBMs and the practical factors associated with implementing an RBM.

Introducing the RBM

A Boltzmann machine is a particular type of stochastic, recurrent neural network. It is an energy-based model, which means that it uses an energy function to associate an energy value with each configuration of the network.

We briefly discussed the structure of a Boltzmann machine in the previous section. As mentioned, a Boltzmann machine is a directed cyclic graph, where every node is connected to all other nodes. This property enables it to model...

Deep belief networks

A DBN is a graphical model, constructed using multiple stacked RBMs. While the first RBM trains a layer of features based on input from the pixels of the training data, subsequent layers treat the activations of preceding layers as if they were pixels and attempt to learn the features in subsequent hidden layers. This is frequently described as learning the representation of data and is a common theme in deep learning.

How many multiple RBMs there should be depends on what is needed for the problem at hand. From a practical perspective, it's a trade-off between increasing accuracy and increasing computational cost. It is the case that each layer of RBMs will improve the lower bound of the log probability of the training data. In other words; the DBN almost inevitably becomes less bad with each additional layer of features.

As far as layer size is concerned, it is generally advantageous to reduce the number of nodes in the hidden layers of successive RBMs. One should...

Further reading

For a primer on neural networks, it makes sense to read from a range of sources. There are many concerns to be aware of and different authors emphasize on different material. A solid introduction is provided by Kevin Gurney in An Introduction to Neural Networks.

An excellent piece on the intuitions underlying Markov Chain Monte Carlo is available at http://twiecki.github.io/blog/2015/11/10/mcmc-sampling/.

For readers with a specific interest in the intuitions supporting Gibbs Sampling, Philip Resnik, and Eric Hardisty's paper, Gibbs Sampling for the Uninitiated, provides a technical, but clear description of how Gibbs works. It's particularly notable to have some really first-rate analogies! Find them at https://www.umiacs.umd.edu/~resnik/pubs/LAMP-TR-153.pdf.

There aren't many good explanations of Contrastive Divergence, one I like is provided by Oliver Woodford at http://www.robots.ox.ac.uk/~ojw/files/NotesOnCD.pdf. If you're a little daunted by the heavy...

Summary

We've covered a lot of ground in this chapter! We began with an overview of Neural Networks, focusing on the general properties of topology and learning method before taking a deep dive into the RBM algorithm and RBM code itself. We took this solid understanding forward to create a DBN. In doing so, we linked the DBN theory and code together, before firing up our DBN to work over the MNIST dataset. We performed image classification in a 10-class problem and achieved an extremely competitive result, with classification error below 2%!

In the next chapter, we'll continue to build on your mastery of deep learning by introducing you to another deep learning architecture—Stacked Denoising Autoencoders (SDA).

Left arrow icon Right arrow icon
Download code icon Download Code

Key benefits

  • Resolve complex machine learning problems and explore deep learning
  • Learn to use Python code for implementing a range of machine learning algorithms and techniques
  • A practical tutorial that tackles real-world computing problems through a rigorous and effective approach

Description

Designed to take you on a guided tour of the most relevant and powerful machine learning techniques in use today by top data scientists, this book is just what you need to push your Python algorithms to maximum potential. Clear examples and detailed code samples demonstrate deep learning techniques, semi-supervised learning, and more - all whilst working with real-world applications that include image, music, text, and financial data. The machine learning techniques covered in this book are at the forefront of commercial practice. They are applicable now for the first time in contexts such as image recognition, NLP and web search, computational creativity, and commercial/financial data modeling. Deep Learning algorithms and ensembles of models are in use by data scientists at top tech and digital companies, but the skills needed to apply them successfully, while in high demand, are still scarce. This book is designed to take the reader on a guided tour of the most relevant and powerful machine learning techniques. Clear descriptions of how techniques work and detailed code examples demonstrate deep learning techniques, semi-supervised learning and more, in real world applications. We will also learn about NumPy and Theano. By this end of this book, you will learn a set of advanced Machine Learning techniques and acquire a broad set of powerful skills in the area of feature selection & feature engineering.

Who is this book for?

This title is for Python developers and analysts or data scientists who are looking to add to their existing skills by accessing some of the most powerful recent trends in data science. If you’ve ever considered building your own image or text-tagging solution, or of entering a Kaggle contest for instance, this book is for you! Prior experience of Python and grounding in some of the core concepts of machine learning would be helpful.

What you will learn

  • Compete with top data scientists by gaining a practical and theoretical understanding of cutting-edge deep learning algorithms
  • Apply your new found skills to solve real problems, through clearly-explained code for every technique and test
  • Automate large sets of complex data and overcome time-consuming practical challenges
  • Improve the accuracy of models and your existing input data using powerful feature engineering techniques
  • Use multiple learning techniques together to improve the consistency of results
  • Understand the hidden structure of datasets using a range of unsupervised techniques
  • Gain insight into how the experts solve challenging data problems with an effective, iterative, and validation-focused approach
  • Improve the effectiveness of your deep learning models further by using powerful ensembling techniques to strap multiple models together

Product Details

Country selected
Publication date, Length, Edition, Language, ISBN-13
Publication date : Jul 28, 2016
Length: 278 pages
Edition : 1st
Language : English
ISBN-13 : 9781784393830
Category :
Languages :

What do you get with eBook?

Product feature icon Instant access to your Digital eBook purchase
Product feature icon Download this book in EPUB and PDF formats
Product feature icon Access this title in our online reader with advanced features
Product feature icon DRM FREE - Read whenever, wherever and however you want
OR
Modal Close icon
Payment Processing...
tick Completed

Billing Address

Product Details

Publication date : Jul 28, 2016
Length: 278 pages
Edition : 1st
Language : English
ISBN-13 : 9781784393830
Category :
Languages :

Packt Subscriptions

See our plans and pricing
Modal Close icon
$19.99 billed monthly
Feature tick icon Unlimited access to Packt's library of 7,000+ practical books and videos
Feature tick icon Constantly refreshed with 50+ new titles a month
Feature tick icon Exclusive Early access to books as they're written
Feature tick icon Solve problems while you work with advanced search and reference features
Feature tick icon Offline reading on the mobile app
Feature tick icon Simple pricing, no contract
$199.99 billed annually
Feature tick icon Unlimited access to Packt's library of 7,000+ practical books and videos
Feature tick icon Constantly refreshed with 50+ new titles a month
Feature tick icon Exclusive Early access to books as they're written
Feature tick icon Solve problems while you work with advanced search and reference features
Feature tick icon Offline reading on the mobile app
Feature tick icon Choose a DRM-free eBook or Video every month to keep
Feature tick icon PLUS own as many other DRM-free eBooks or Videos as you like for just €5 each
Feature tick icon Exclusive print discounts
$279.99 billed in 18 months
Feature tick icon Unlimited access to Packt's library of 7,000+ practical books and videos
Feature tick icon Constantly refreshed with 50+ new titles a month
Feature tick icon Exclusive Early access to books as they're written
Feature tick icon Solve problems while you work with advanced search and reference features
Feature tick icon Offline reading on the mobile app
Feature tick icon Choose a DRM-free eBook or Video every month to keep
Feature tick icon PLUS own as many other DRM-free eBooks or Videos as you like for just €5 each
Feature tick icon Exclusive print discounts

Frequently bought together


Stars icon
Total 128.97
Python Machine Learning Cookbook
€49.99
Mastering Data Mining with Python ??? Find patterns hidden in your data
€41.99
Advanced Machine Learning with Python
€36.99
Total 128.97 Stars icon

Table of Contents

11 Chapters
1. Unsupervised Machine Learning Chevron down icon Chevron up icon
2. Deep Belief Networks Chevron down icon Chevron up icon
3. Stacked Denoising Autoencoders Chevron down icon Chevron up icon
4. Convolutional Neural Networks Chevron down icon Chevron up icon
5. Semi-Supervised Learning Chevron down icon Chevron up icon
6. Text Feature Engineering Chevron down icon Chevron up icon
7. Feature Engineering Part II Chevron down icon Chevron up icon
8. Ensemble Methods Chevron down icon Chevron up icon
9. Additional Python Machine Learning Tools Chevron down icon Chevron up icon
A. Chapter Code Requirements Chevron down icon Chevron up icon
Index Chevron down icon Chevron up icon

Customer reviews

Top Reviews
Rating distribution
Full star icon Full star icon Full star icon Half star icon Empty star icon 3.1
(7 Ratings)
5 star 28.6%
4 star 28.6%
3 star 0%
2 star 14.3%
1 star 28.6%
Filter icon Filter
Top Reviews

Filter reviews by




Nasser Albalkhi Jul 16, 2023
Full star icon Full star icon Full star icon Full star icon Full star icon 5
It is very good book and cover the information that we looking for
Amazon Verified review Amazon
Amazon Customer Mar 27, 2017
Full star icon Full star icon Full star icon Full star icon Full star icon 5
Great product!
Amazon Verified review Amazon
braxen Sep 09, 2016
Full star icon Full star icon Full star icon Full star icon Empty star icon 4
A few word about myself:I am a Analyst, I have a MSc. in Mathematics and Statistics and do analytics for a living. While I have studied about neural networks and machine learning a while ago, only past year have I (re)-discovered the power of neural nets and Deep Learning.In my quest to improve my knowledge, I have taken many certificates in ML and have bought a few books about Machine Learning. Among these are:-Python Machine Learning by Sebastian Raschka (recommended)-Building Machine Learning Systems with Python by by Luis Pedro Coelho and Willi Richert (nice to have for additional perspective)However, I wanted to go beyond what one can find in those two books. The topics I was specifically interested in were:-Deep Belief Networks (inc. Restricted Boltzmann Machine)-Autoencoders-Convolutional Neural NetworksSo where does Advanced Machine Learning rank among these?I must say, and that will be my main criticism of the book that it is not for the faint of heart. It is fast, sometimes too fast... I suppose there is so much you can put in 250 pages to explain about these topics, and it is easy to become lost.However, do not get me wrong. This book is a small gem in itself.Why? Because while I have found online many tutorials or courses about the topics I was interested, the book gives you additional information and explanations that I haven't found anywhere else. How do you set your hyper-parameters in a CNN? What is the depth exactly representing, what are the current architectures, are they really all that good? Why?It is the difference between the how and the more precise what and why. Tutorials online are great but many people just do things without clearly showing why. This books gives you the clues.In conclusion, for me currently (after having bought 8 books):The book is difficult but not super difficult. It gives more understanding and depth than I could ever obtain with all the material available online currently (including the very good Stanford courses). So, yes, I feel I am making progress.-Python Machine Learning by Sebastian Raschka is the way to go for Machine Learning foundations-Advanced Machine Learning with Python by John Hearty is a super helpful complement to what one can already find online dispersed all over the place, it just make sense with better hindsight.
Amazon Verified review Amazon
Ankit Feb 09, 2024
Full star icon Full star icon Full star icon Full star icon Empty star icon 4
Worth it
Amazon Verified review Amazon
Anshuman Gaurav Sep 09, 2016
Full star icon Full star icon Empty star icon Empty star icon Empty star icon 2
This book has so many printing errors in its code that it is impossible to follow. They claim to teach ML using python but least care has been taken to verify the printed contents.
Amazon Verified review Amazon
Get free access to Packt library with over 7500+ books and video courses for 7 days!
Start Free Trial

FAQs

How do I buy and download an eBook? Chevron down icon Chevron up icon

Where there is an eBook version of a title available, you can buy it from the book details for that title. Add either the standalone eBook or the eBook and print book bundle to your shopping cart. Your eBook will show in your cart as a product on its own. After completing checkout and payment in the normal way, you will receive your receipt on the screen containing a link to a personalised PDF download file. This link will remain active for 30 days. You can download backup copies of the file by logging in to your account at any time.

If you already have Adobe reader installed, then clicking on the link will download and open the PDF file directly. If you don't, then save the PDF file on your machine and download the Reader to view it.

Please Note: Packt eBooks are non-returnable and non-refundable.

Packt eBook and Licensing When you buy an eBook from Packt Publishing, completing your purchase means you accept the terms of our licence agreement. Please read the full text of the agreement. In it we have tried to balance the need for the ebook to be usable for you the reader with our needs to protect the rights of us as Publishers and of our authors. In summary, the agreement says:

  • You may make copies of your eBook for your own use onto any machine
  • You may not pass copies of the eBook on to anyone else
How can I make a purchase on your website? Chevron down icon Chevron up icon

If you want to purchase a video course, eBook or Bundle (Print+eBook) please follow below steps:

  1. Register on our website using your email address and the password.
  2. Search for the title by name or ISBN using the search option.
  3. Select the title you want to purchase.
  4. Choose the format you wish to purchase the title in; if you order the Print Book, you get a free eBook copy of the same title. 
  5. Proceed with the checkout process (payment to be made using Credit Card, Debit Cart, or PayPal)
Where can I access support around an eBook? Chevron down icon Chevron up icon
  • If you experience a problem with using or installing Adobe Reader, the contact Adobe directly.
  • To view the errata for the book, see www.packtpub.com/support and view the pages for the title you have.
  • To view your account details or to download a new copy of the book go to www.packtpub.com/account
  • To contact us directly if a problem is not resolved, use www.packtpub.com/contact-us
What eBook formats do Packt support? Chevron down icon Chevron up icon

Our eBooks are currently available in a variety of formats such as PDF and ePubs. In the future, this may well change with trends and development in technology, but please note that our PDFs are not Adobe eBook Reader format, which has greater restrictions on security.

You will need to use Adobe Reader v9 or later in order to read Packt's PDF eBooks.

What are the benefits of eBooks? Chevron down icon Chevron up icon
  • You can get the information you need immediately
  • You can easily take them with you on a laptop
  • You can download them an unlimited number of times
  • You can print them out
  • They are copy-paste enabled
  • They are searchable
  • There is no password protection
  • They are lower price than print
  • They save resources and space
What is an eBook? Chevron down icon Chevron up icon

Packt eBooks are a complete electronic version of the print edition, available in PDF and ePub formats. Every piece of content down to the page numbering is the same. Because we save the costs of printing and shipping the book to you, we are able to offer eBooks at a lower cost than print editions.

When you have purchased an eBook, simply login to your account and click on the link in Your Download Area. We recommend you saving the file to your hard drive before opening it.

For optimal viewing of our eBooks, we recommend you download and install the free Adobe Reader version 9.