Deep Learning

Deep learning is making waves. At the time of this writing (March 2016), Google’s AlghaGo program just beat 9-dan professional Go player Lee Sedol at the game of Go, a Chinese board game.

Experts in the field of Artificial Intelligence thought we were 10 years away from achieving a victory against a top professional Go player, but progress seems to have accelerated!

While deep learning is a complex subject, it is not any more difficult to learn than any other machine learning algorithm. I wrote this book to introduce you to the basics of neural networks. You will get along fine with undergraduate-level math and programming skill.

All the materials in this book can be downloaded and installed for free. We will use the Python programming language, along with the numerical computing library Numpy. I will also show you in the later chapters how to build a deep network using Theano and TensorFlow, which are libraries built specifically for deep learning and can accelerate computation by taking advantage of the GPU.

Unlike other machine learning algorithms, deep learning is particularly powerful because it automatically learns features. That means you don’t need to spend your time trying to come up with and test “kernels” or “interaction effects” - something only statisticians love to do. Instead, we will let the neural network learn these things for us. Each layer of the neural network learns a different abstraction than the previous layers. For example, in image classification, the first layer might learn different strokes, and in the next layer put the strokes together to learn shapes, and in the next layer put the shapes together to form facial features, and in the next layer have a high level representation of faces.

On top of all this, deep learning is known for winning its fair share Kaggle contests. These are machine learning contests that are open to anyone in the world who are allowed to use any machine learning technique they want. Deep learning is that powerful.

Do you want a gentle introduction to this “dark art”, with practical code examples that you can try right away and apply to your own data? Then this book is for you.

Who is this book NOT for?

Deep Learning and Neural Networks are usually taught at the upper-year undergraduate level. That should give you some idea of the type of knowledge you need to understand this kind of material.

You absolutely need exposure to calculus to understand deep learning, no matter how simple the instructor makes things. Linear algebra would help. I will assume familiarity with Python (although it is an easy language to pick up). You will need to have some concept of machine learning. If you know about algorithms like logistic regression already, this book is perfect for you. If not, you might want to check out my “prerequisites” book, at: http://amzn.com/B01D7GDRQ2

On the other hand, this book is more like a casual primer than a dry textbook. If you are looking for material on more advanced topics, like LSTMs, convolutional neural networks, or reinforcement learning, I have online courses that teach this material, for example: https://www.udemy.com/deep-learning-c...

New libraries like TensorFlow are being updated constantly. This is not an encyclopedia for these libraries (as such a thing would be impossible to keep up to date). In the one (1!!!) month since the book was first published, no less than THREE new wrapper libraries for TensorFlow have been released to make coding deep networks easier.

50 Basic & Intermediate Tips & Tricks

Zed Shaw has perfected the world's best system for learning Python. Follow it and you will succeed-just like the hundreds of thousands of beginners Zed has taught to date! You bring the discipline, commitment, and persistence; the author supplies everything else.

In *Learn Python the Hard Way, Third Edition,* you'll learn Python by working through 52 brilliantly crafted exercises. Read them. Type their code precisely. (No copying and pasting!) Fix your mistakes. Watch the programs run. As you do, you'll learn how software works; what good programs look like; how to read, write, and think about code; and how to find and fix your mistakes using tricks professional programmers use. Most importantly, you'll learn the following, which you need to start writing excellent Python software of your own:

This latest edition of The Definitive Guide to Django is updated for Django 1.1, and, with the forward–compatibility guarantee that Django now provides, should serve as the ultimate tutorial and reference for this popular framework for years to come.

Django, the Python–based equivalent to Ruby’s Rails web development framework, is one of the hottest topics in web development today. Lead developer Jacob Kaplan–Moss and Django creator Adrian Holovaty show you how they use this framework to create award–winning web sites by guiding you through the creation of a web application reminiscent of ChicagoCrime.org.

The Definitive Guide to Django is broken into three parts, with the first introducing Django fundamentals such as installation and configuration, and creating the components that together power a Django–driven web site. The second part delves into the more sophisticated features of Django, including outputting non–HTML content such as RSS feeds and PDFs, caching, and user management. The appendixes serve as a detailed reference to Django’s many configuration options and commands.

What you’ll learn

The first half of this book explains in depth how to build web applications using Django including the basics of dynamic web pages, the Django templating system interacting with databases, and web forms.

The second half of this book discusses higher-level concepts such as caching, security, and how to deploy Django.

The appendixes form a reference for the commands and configurations available in Django.

Who this book is for

Anyone who wants to use the powerful Django framework to build dynamic web sites quickly and easily.

Table of Contents

Introduction to Django

Getting Started

Views and URLconfs

Templates

Models

The Django Admin Site

Forms

Advanced Views and URLconfs

Advanced Templates

Advanced Models

Generic Views

Deploying Django

Generating Non-HTML Content

Sessions, Users, and Registration

Caching

django.contrib

Middleware

Integrating with Legacy Databases and Applications

Internationalization

Security

About the Author

Adrian Holovaty , a web developer and journalist, is one of the creators and core developers of Django. He works at WashingtonPost.com, where he builds database web applications and does "journalism as computer programming." Previously, he was lead developer for World Online in Lawrence, Kansas, where Django was created. When not working on Django improvements, Adrian hacks on side projects for the public good, such as ChicagoCrime.org, which won the 2005 Batten Award for Innovations in Journalism. He lives in Chicago and maintains a weblog at www.Holovaty.com.

Jacob Kaplan-Moss is one of the lead developers of Django. At his day job, he's the lead developer for the Lawrence Journal-World, a locally owned newspaper in Lawrence, Kansas, where Django was developed. At the Journal-World, Jacob hacks on a number of sites including lawrence.com, LJWorld.com, and KUsports.com, and he is continually embarrassed by the multitude of media awards those sites win. In his spare time—what little of it there is—he fancies himself a chef.

Zed Shaw has perfected the world’s best system for learning Python 3. Follow it and you will succeed—just like the millions of beginners Zed has taught to date! You bring the discipline, commitment, and persistence; the author supplies everything else.

In Learn Python 3 the Hard Way, you’ll learn Python by working through 52 brilliantly crafted exercises. Read them. Type their code precisely. (No copying and pasting!) Fix your mistakes. Watch the programs run. As you do, you’ll learn how a computer works; what good programs look like; and how to read, write, and think about code. Zed then teaches you even more in 5+ hours of video where he shows you how to break, fix, and debug your code—live, as he’s doing the exercises.

Two Scoops of Django 1.11 Now Available!

Search for Two Scoops of Django 1.11 to find and purchase the latest edition.

Two Scoops of Django: Best Practices For Django 1.8 is full of more material that will help you with your Django projects.

We'll introduce you to various tips, tricks, patterns, code snippets, and techniques that we've picked up over the years.

We have put thousands of hours into the third edition of the book, writing and revising its material to include significant improvements and new material based on feedback from previous editions.

If you want to learn how to program, working with Python is an excellent way to start. This hands-on guide takes you through the language a step at a time, beginning with basic programming concepts before moving on to functions, recursion, data structures, and object-oriented design. This second edition and its supporting code have been updated for Python 3.

Through exercises in each chapter, you’ll try out programming concepts as you learn them. Think Python is ideal for students at the high school or college level, as well as self-learners, home-schooled students, and professionals who need to learn programming basics. Beginners just getting their feet wet will learn how to start with Python in a browser.

Start with the basics, including language syntax and semantics

Get a clear definition of each programming concept

Learn about values, variables, statements, functions, and data structures in a logical progression

Discover how to work with files and databases

Understand objects, methods, and object-oriented programming

Use debugging techniques to fix syntax, runtime, and semantic errors

Explore interface design, data structures, and GUI-based programs through case studies

Available from www.tangowithdjango.com