Deep Learning For Dummies

Table of contents

1. Cover
2. Introduction
   1. About This Book
   2. Foolish Assumptions
   3. Icons Used in This Book
   4. Beyond the Book
   5. Where to Go from Here
3. Part 1: Discovering Deep Learning
   1. Chapter 1: Introducing Deep Learning
      1. Defining What Deep Learning Means
      2. Using Deep Learning in the Real World
      3. Considering the Deep Learning Programming Environment
      4. Overcoming Deep Learning Hype
   2. Chapter 2: Introducing the Machine Learning Principles
      1. Defining Machine Learning
      2. Considering the Many Different Roads to Learning
      3. Pondering the True Uses of Machine Learning
   3. Chapter 3: Getting and Using Python
      1. Working with Python in this Book
      2. Obtaining Your Copy of Anaconda
      3. Downloading the Datasets and Example Code
      4. Creating the Application
      5. Understanding the Use of Indentation
      6. Adding Comments
      7. Getting Help with the Python Language
      8. Working in the Cloud
   4. Chapter 4: Leveraging a Deep Learning Framework
      1. Presenting Frameworks
      2. Working with Low-End Frameworks
      3. Understanding TensorFlow
4. Part 2: Considering Deep Learning Basics
   1. Chapter 5: Reviewing Matrix Math and Optimization
      1. Revealing the Math You Really Need
      2. Understanding Scalar, Vector, and Matrix Operations
      3. Interpreting Learning as Optimization
   2. Chapter 6: Laying Linear Regression Foundations
      1. Combining Variables
      2. Mixing Variable Types
      3. Switching to Probabilities
      4. Guessing the Right Features
      5. Learning One Example at a Time
   3. Chapter 7: Introducing Neural Networks
      1. Discovering the Incredible Perceptron
      2. Hitting Complexity with Neural Networks
      3. Struggling with Overfitting
   4. Chapter 8: Building a Basic Neural Network
      1. Understanding Neural Networks
      2. Looking Under the Hood of Neural Networks
   5. Chapter 9: Moving to Deep Learning
      1. Seeing Data Everywhere
      2. Discovering the Benefits of Additional Data
      3. Improving Processing Speed
      4. Explaining Deep Learning Differences from Other Forms of AI
      5. Finding Even Smarter Solutions
   6. Chapter 10: Explaining Convolutional Neural Networks
      1. Beginning the CNN Tour with Character Recognition
      2. Explaining How Convolutions Work
      3. Detecting Edges and Shapes from Images
   7. Chapter 11: Introducing Recurrent Neural Networks
      1. Introducing Recurrent Networks
      2. Explaining Long Short-Term Memory
5. Part 3: Interacting with Deep Learning
   1. Chapter 12: Performing Image Classification
      1. Using Image Classification Challenges
      2. Distinguishing Traffic Signs
   2. Chapter 13: Learning Advanced CNNs
      1. Distinguishing Classification Tasks
      2. Perceiving Objects in Their Surroundings
      3. Overcoming Adversarial Attacks on Deep Learning Applications
   3. Chapter 14: Working on Language Processing
      1. Processing Language
      2. Memorizing Sequences that Matter
      3. Using AI for Sentiment Analysis
   4. Chapter 15: Generating Music and Visual Art
      1. Learning to Imitate Art and Life
      2. Mimicking an Artist
   5. Chapter 16: Building Generative Adversarial Networks
      1. Making Networks Compete
      2. Considering a Growing Field
   6. Chapter 17: Playing with Deep Reinforcement Learning
      1. Playing a Game with Neural Networks
      2. Explaining Alpha-Go
6. Part 4: The Part of Tens
   1. Chapter 18: Ten Applications that Require Deep Learning
      1. Restoring Color to Black-and-White Videos and Pictures
      2. Approximating Person Poses in Real Time
      3. Performing Real-Time Behavior Analysis
      4. Translating Languages
      5. Estimating Solar Savings Potential
      6. Beating People at Computer Games
      7. Generating Voices
      8. Predicting Demographics
      9. Creating Art from Real-World Pictures
      10. Forecasting Natural Catastrophes
   2. Chapter 19: Ten Must-Have Deep Learning Tools
      1. Compiling Math Expressions Using Theano
      2. Augmenting TensorFlow Using Keras
      3. Dynamically Computing Graphs with Chainer
      4. Creating a MATLAB-Like Environment with Torch
      5. Performing Tasks Dynamically with PyTorch
      6. Accelerating Deep Learning Research Using CUDA
      7. Supporting Business Needs with Deeplearning4j
      8. Mining Data Using Neural Designer
      9. Training Algorithms Using Microsoft Cognitive Toolkit (CNTK)
      10. Exploiting Full GPU Capability Using MXNet
   3. Chapter 20: Ten Types of Occupations that Use Deep Learning
      1. Managing People
      2. Improving Medicine
      3. Developing New Devices
      4. Providing Customer Support
      5. Seeing Data in New Ways
      6. Performing Analysis Faster
      7. Creating a Better Work Environment
      8. Researching Obscure or Detailed Information
      9. Designing Buildings
      10. Enhancing Safety
7. Index
8. About the Authors
9. Advertisement Page
10. Connect with Dummies
11. End User License Agreement