Python Deep Learning

Book description

Take your machine learning skills to the next level by mastering Deep Learning concepts and algorithms using Python.

About This Book

  • Explore and create intelligent systems using cutting-edge deep learning techniques
  • Implement deep learning algorithms and work with revolutionary libraries in Python
  • Get real-world examples and easy-to-follow tutorials on Theano, TensorFlow, H2O and more

Who This Book Is For

This book is for Data Science practitioners as well as aspirants who have a basic foundational understanding of Machine Learning concepts and some programming experience with Python. A mathematical background with a conceptual understanding of calculus and statistics is also desired.

What You Will Learn

  • Get a practical deep dive into deep learning algorithms
  • Explore deep learning further with Theano, Caffe, Keras, and TensorFlow
  • Learn about two of the most powerful techniques at the core of many practical deep learning implementations: Auto-Encoders and Restricted Boltzmann Machines
  • Dive into Deep Belief Nets and Deep Neural Networks
  • Discover more deep learning algorithms with Dropout and Convolutional Neural Networks
  • Get to know device strategies so you can use deep learning algorithms and libraries in the real world

In Detail

With an increasing interest in AI around the world, deep learning has attracted a great deal of public attention. Every day, deep learning algorithms are used broadly across different industries.

The book will give you all the practical information available on the subject, including the best practices, using real-world use cases. You will learn to recognize and extract information to increase predictive accuracy and optimize results.

Starting with a quick recap of important machine learning concepts, the book will delve straight into deep learning principles using Sci-kit learn. Moving ahead, you will learn to use the latest open source libraries such as Theano, Keras, Google's TensorFlow, and H20. Use this guide to uncover the difficulties of pattern recognition, scaling data with greater accuracy and discussing deep learning algorithms and techniques.

Whether you want to dive deeper into Deep Learning, or want to investigate how to get more out of this powerful technology, you’ll find everything inside.

Style and approach

Python Machine Learning by example follows practical hands on approach. It walks you through the key elements of Python and its powerful machine learning libraries with the help of real world projects.

Downloading the example code for this book. You can download the example code files for all Packt books you have purchased from your account at If you purchased this book elsewhere, you can visit and register to have the code file.

Publisher resources

Download Example Code

Table of contents

  1. Python Deep Learning
    1. Table of Contents
    2. Python Deep Learning
    3. Credits
    4. About the Authors
    5. About the Reviewer
      1. eBooks, discount offers, and more
        1. Why subscribe?
    7. Customer Feedback
    8. Preface
      1. What this book covers
      2. What you need for this book
      3. Who this book is for
      4. Conventions
      5. Reader feedback
      6. Customer support
        1. Downloading the example code
        2. Downloading the color images of this book
      7. Errata
        1. Piracy
        2. Questions
    9. 1. Machine Learning – An Introduction
      1. What is machine learning?
      2. Different machine learning approaches
        1. Supervised learning
        2. Unsupervised learning
        3. Reinforcement learning
        4. Steps Involved in machine learning systems
        5. Brief description of popular techniques/algorithms
          1. Linear regression
          2. Decision trees
          3. K-means
          4. Naïve Bayes
          5. Support vector machines
          6. The cross-entropy method
          7. Neural networks
          8. Deep learning
        6. Applications in real life
        7. A popular open source package
      3. Summary
    10. 2. Neural Networks
      1. Why neural networks?
      2. Fundamentals
        1. Neurons and layers
        2. Different types of activation function
        3. The back-propagation algorithm
          1. Linear regression
          2. Logistic regression
          3. Back-propagation
        4. Applications in industry
          1. Signal processing
          2. Medical
          3. Autonomous car driving
          4. Business
          5. Pattern recognition
          6. Speech production
        5. Code example of a neural network for the function xor
      3. Summary
    11. 3. Deep Learning Fundamentals
      1. What is deep learning?
        1. Fundamental concepts
        2. Feature learning
        3. Deep learning algorithms
      2. Deep learning applications
        1. Speech recognition
        2. Object recognition and classification
      3. GPU versus CPU
      4. Popular open source libraries – an introduction
        1. Theano
        2. TensorFlow
        3. Keras
        4. Sample deep neural net code using Keras
      5. Summary
    12. 4. Unsupervised Feature Learning
      1. Autoencoders
        1. Network design
        2. Regularization techniques for autoencoders
          1. Denoising autoencoders
          2. Contractive autoencoders
          3. Sparse autoencoders
        3. Summary of autoencoders
      2. Restricted Boltzmann machines
        1. Hopfield networks and Boltzmann machines
        2. Boltzmann machine
        3. Restricted Boltzmann machine
        4. Implementation in TensorFlow
        5. Deep belief networks
      3. Summary
    13. 5. Image Recognition
      1. Similarities between artificial and biological models
      2. Intuition and justification
      3. Convolutional layers
        1. Stride and padding in convolutional layers
      4. Pooling layers
      5. Dropout
      6. Convolutional layers in deep learning
      7. Convolutional layers in Theano
      8. A convolutional layer example with Keras to recognize digits
      9. A convolutional layer example with Keras for cifar10
      10. Pre-training
      11. Summary
    14. 6. Recurrent Neural Networks and Language Models
      1. Recurrent neural networks
        1. RNN — how to implement and train
          1. Backpropagation through time
          2. Vanishing and exploding gradients
        2. Long short term memory
      2. Language modeling
        1. Word-based models
          1. N-grams
          2. Neural language models
        2. Character-based model
          1. Preprocessing and reading data
          2. LSTM network
          3. Training
          4. Sampling
          5. Example training
      3. Speech recognition
        1. Speech recognition pipeline
        2. Speech as input data
        3. Preprocessing
        4. Acoustic model
          1. Deep belief networks
          2. Recurrent neural networks
          3. CTC
          4. Attention-based models
        5. Decoding
        6. End-to-end models
      4. Summary
      5. Bibliography
    15. 7. Deep Learning for Board Games
      1. Early game playing AI
      2. Using the min-max algorithm to value game states
      3. Implementing a Python Tic-Tac-Toe game
      4. Learning a value function
      5. Training AI to master Go
      6. Upper confidence bounds applied to trees
      7. Deep learning in Monte Carlo Tree Search
      8. Quick recap on reinforcement learning
      9. Policy gradients for learning policy functions
      10. Policy gradients in AlphaGo
      11. Summary
    16. 8. Deep Learning for Computer Games
      1. A supervised learning approach to games
      2. Applying genetic algorithms to playing games
      3. Q-Learning
        1. Q-function
      4. Q-learning in action
      5. Dynamic games
        1. Experience replay
        2. Epsilon greedy
      6. Atari Breakout
        1. Atari Breakout random benchmark
        2. Preprocessing the screen
        3. Creating a deep convolutional network
        4. Convergence issues in Q-learning
        5. Policy gradients versus Q-learning
      7. Actor-critic methods
        1. Baseline for variance reduction
        2. Generalized advantage estimator
      8. Asynchronous methods
      9. Model-based approaches
      10. Summary
    17. 9. Anomaly Detection
      1. What is anomaly and outlier detection?
      2. Real-world applications of anomaly detection
      3. Popular shallow machine learning techniques
        1. Data modeling
        2. Detection modeling
      4. Anomaly detection using deep auto-encoders
      5. H2O
        1. Getting started with H2O
      6. Examples
        1. MNIST digit anomaly recognition
          1. Electrocardiogram pulse detection
      7. Summary
    18. 10. Building a Production-Ready Intrusion Detection System
      1. What is a data product?
      2. Training
        1. Weights initialization
        2. Parallel SGD using HOGWILD!
        3. Adaptive learning
          1. Rate annealing
          2. Momentum
          3. Nesterov's acceleration
          4. Newton's method
          5. Adagrad
          6. Adadelta
        4. Distributed learning via Map/Reduce
        5. Sparkling Water
      3. Testing
      4. Model validation
        1. Labeled Data
        2. Unlabeled Data
        3. Summary of validation
      5. Hyper-parameters tuning
      6. End-to-end evaluation
        1. A/B Testing
        2. A summary of testing
      7. Deployment
        1. POJO model export
        2. Anomaly score APIs
        3. A summary of deployment
      8. Summary
    19. Index

Product information

  • Title: Python Deep Learning
  • Author(s): Valentino Zocca, Gianmario Spacagna, Daniel Slater, Peter Roelants
  • Release date: April 2017
  • Publisher(s): Packt Publishing
  • ISBN: 9781786464453