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 Print?

Product feature icon Instant access to your digital copy whilst your Print order is Shipped
Product feature icon Paperback book shipped to your preferred address
Product feature icon Redeem a companion digital copy on all Print orders
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

Shipping Address

Billing Address

Shipping Methods
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
Estimated delivery fee Deliver to Hungary

Premium delivery 7 - 10 business days

€25.95
(Includes tracking information)

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 : 9781784398637
Category :
Languages :

What do you get with Print?

Product feature icon Instant access to your digital copy whilst your Print order is Shipped
Product feature icon Paperback book shipped to your preferred address
Product feature icon Redeem a companion digital copy on all Print orders
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

Shipping Address

Billing Address

Shipping Methods
Estimated delivery fee Deliver to Hungary

Premium delivery 7 - 10 business days

€25.95
(Includes tracking information)

Product Details

Publication date : Jul 28, 2016
Length: 278 pages
Edition : 1st
Language : English
ISBN-13 : 9781784398637
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

What is the digital copy I get with my Print order? Chevron down icon Chevron up icon

When you buy any Print edition of our Books, you can redeem (for free) the eBook edition of the Print Book you’ve purchased. This gives you instant access to your book when you make an order via PDF, EPUB or our online Reader experience.

What is the delivery time and cost of print book? Chevron down icon Chevron up icon

Shipping Details

USA:

'

Economy: Delivery to most addresses in the US within 10-15 business days

Premium: Trackable Delivery to most addresses in the US within 3-8 business days

UK:

Economy: Delivery to most addresses in the U.K. within 7-9 business days.
Shipments are not trackable

Premium: Trackable delivery to most addresses in the U.K. within 3-4 business days!
Add one extra business day for deliveries to Northern Ireland and Scottish Highlands and islands

EU:

Premium: Trackable delivery to most EU destinations within 4-9 business days.

Australia:

Economy: Can deliver to P. O. Boxes and private residences.
Trackable service with delivery to addresses in Australia only.
Delivery time ranges from 7-9 business days for VIC and 8-10 business days for Interstate metro
Delivery time is up to 15 business days for remote areas of WA, NT & QLD.

Premium: Delivery to addresses in Australia only
Trackable delivery to most P. O. Boxes and private residences in Australia within 4-5 days based on the distance to a destination following dispatch.

India:

Premium: Delivery to most Indian addresses within 5-6 business days

Rest of the World:

Premium: Countries in the American continent: Trackable delivery to most countries within 4-7 business days

Asia:

Premium: Delivery to most Asian addresses within 5-9 business days

Disclaimer:
All orders received before 5 PM U.K time would start printing from the next business day. So the estimated delivery times start from the next day as well. Orders received after 5 PM U.K time (in our internal systems) on a business day or anytime on the weekend will begin printing the second to next business day. For example, an order placed at 11 AM today will begin printing tomorrow, whereas an order placed at 9 PM tonight will begin printing the day after tomorrow.


Unfortunately, due to several restrictions, we are unable to ship to the following countries:

  1. Afghanistan
  2. American Samoa
  3. Belarus
  4. Brunei Darussalam
  5. Central African Republic
  6. The Democratic Republic of Congo
  7. Eritrea
  8. Guinea-bissau
  9. Iran
  10. Lebanon
  11. Libiya Arab Jamahriya
  12. Somalia
  13. Sudan
  14. Russian Federation
  15. Syrian Arab Republic
  16. Ukraine
  17. Venezuela
What is custom duty/charge? Chevron down icon Chevron up icon

Customs duty are charges levied on goods when they cross international borders. It is a tax that is imposed on imported goods. These duties are charged by special authorities and bodies created by local governments and are meant to protect local industries, economies, and businesses.

Do I have to pay customs charges for the print book order? Chevron down icon Chevron up icon

The orders shipped to the countries that are listed under EU27 will not bear custom charges. They are paid by Packt as part of the order.

List of EU27 countries: www.gov.uk/eu-eea:

A custom duty or localized taxes may be applicable on the shipment and would be charged by the recipient country outside of the EU27 which should be paid by the customer and these duties are not included in the shipping charges been charged on the order.

How do I know my custom duty charges? Chevron down icon Chevron up icon

The amount of duty payable varies greatly depending on the imported goods, the country of origin and several other factors like the total invoice amount or dimensions like weight, and other such criteria applicable in your country.

For example:

  • If you live in Mexico, and the declared value of your ordered items is over $ 50, for you to receive a package, you will have to pay additional import tax of 19% which will be $ 9.50 to the courier service.
  • Whereas if you live in Turkey, and the declared value of your ordered items is over € 22, for you to receive a package, you will have to pay additional import tax of 18% which will be € 3.96 to the courier service.
How can I cancel my order? Chevron down icon Chevron up icon

Cancellation Policy for Published Printed Books:

You can cancel any order within 1 hour of placing the order. Simply contact customercare@packt.com with your order details or payment transaction id. If your order has already started the shipment process, we will do our best to stop it. However, if it is already on the way to you then when you receive it, you can contact us at customercare@packt.com using the returns and refund process.

Please understand that Packt Publishing cannot provide refunds or cancel any order except for the cases described in our Return Policy (i.e. Packt Publishing agrees to replace your printed book because it arrives damaged or material defect in book), Packt Publishing will not accept returns.

What is your returns and refunds policy? Chevron down icon Chevron up icon

Return Policy:

We want you to be happy with your purchase from Packtpub.com. We will not hassle you with returning print books to us. If the print book you receive from us is incorrect, damaged, doesn't work or is unacceptably late, please contact Customer Relations Team on customercare@packt.com with the order number and issue details as explained below:

  1. If you ordered (eBook, Video or Print Book) incorrectly or accidentally, please contact Customer Relations Team on customercare@packt.com within one hour of placing the order and we will replace/refund you the item cost.
  2. Sadly, if your eBook or Video file is faulty or a fault occurs during the eBook or Video being made available to you, i.e. during download then you should contact Customer Relations Team within 14 days of purchase on customercare@packt.com who will be able to resolve this issue for you.
  3. You will have a choice of replacement or refund of the problem items.(damaged, defective or incorrect)
  4. Once Customer Care Team confirms that you will be refunded, you should receive the refund within 10 to 12 working days.
  5. If you are only requesting a refund of one book from a multiple order, then we will refund you the appropriate single item.
  6. Where the items were shipped under a free shipping offer, there will be no shipping costs to refund.

On the off chance your printed book arrives damaged, with book material defect, contact our Customer Relation Team on customercare@packt.com within 14 days of receipt of the book with appropriate evidence of damage and we will work with you to secure a replacement copy, if necessary. Please note that each printed book you order from us is individually made by Packt's professional book-printing partner which is on a print-on-demand basis.

What tax is charged? Chevron down icon Chevron up icon

Currently, no tax is charged on the purchase of any print book (subject to change based on the laws and regulations). A localized VAT fee is charged only to our European and UK customers on eBooks, Video and subscriptions that they buy. GST is charged to Indian customers for eBooks and video purchases.

What payment methods can I use? Chevron down icon Chevron up icon

You can pay with the following card types:

  1. Visa Debit
  2. Visa Credit
  3. MasterCard
  4. PayPal
What is the delivery time and cost of print books? Chevron down icon Chevron up icon

Shipping Details

USA:

'

Economy: Delivery to most addresses in the US within 10-15 business days

Premium: Trackable Delivery to most addresses in the US within 3-8 business days

UK:

Economy: Delivery to most addresses in the U.K. within 7-9 business days.
Shipments are not trackable

Premium: Trackable delivery to most addresses in the U.K. within 3-4 business days!
Add one extra business day for deliveries to Northern Ireland and Scottish Highlands and islands

EU:

Premium: Trackable delivery to most EU destinations within 4-9 business days.

Australia:

Economy: Can deliver to P. O. Boxes and private residences.
Trackable service with delivery to addresses in Australia only.
Delivery time ranges from 7-9 business days for VIC and 8-10 business days for Interstate metro
Delivery time is up to 15 business days for remote areas of WA, NT & QLD.

Premium: Delivery to addresses in Australia only
Trackable delivery to most P. O. Boxes and private residences in Australia within 4-5 days based on the distance to a destination following dispatch.

India:

Premium: Delivery to most Indian addresses within 5-6 business days

Rest of the World:

Premium: Countries in the American continent: Trackable delivery to most countries within 4-7 business days

Asia:

Premium: Delivery to most Asian addresses within 5-9 business days

Disclaimer:
All orders received before 5 PM U.K time would start printing from the next business day. So the estimated delivery times start from the next day as well. Orders received after 5 PM U.K time (in our internal systems) on a business day or anytime on the weekend will begin printing the second to next business day. For example, an order placed at 11 AM today will begin printing tomorrow, whereas an order placed at 9 PM tonight will begin printing the day after tomorrow.


Unfortunately, due to several restrictions, we are unable to ship to the following countries:

  1. Afghanistan
  2. American Samoa
  3. Belarus
  4. Brunei Darussalam
  5. Central African Republic
  6. The Democratic Republic of Congo
  7. Eritrea
  8. Guinea-bissau
  9. Iran
  10. Lebanon
  11. Libiya Arab Jamahriya
  12. Somalia
  13. Sudan
  14. Russian Federation
  15. Syrian Arab Republic
  16. Ukraine
  17. Venezuela