Artificial Intelligence Now

Book description

The past year or so has seen a true explosion in both the capabilities and adoption of artificial intelligence technologies. Today’s generalized AI tools can solve specific problems more powerfully than the complex rule-based tools that preceded them. And, because these new AI tools can be deployed in many contexts, more and more applications and industries are ripe for transformation with AI technologies.

By drawing from the best posts on the O’Reilly AI blog, this in-depth report summarizes the current state of AI technologies and applications, and provides useful guides to help you get started with deep learning and other AI tools.

In six distinct parts, this report covers:

  • The AI landscape: the platforms, businesses, and business models shaping AI growth; plus a look at the emerging AI stack
  • Technology: AI’s technical underpinnings and deep learning capabilities, tools, and tutorials
  • Homebuilt autonomous systems: "hobbyist" applications that showcase AI tools, libraries, cloud processing, and mobile computing
  • Natural language: strategies for scoping and tackling NLP projects
  • Use cases: an analysis of two of the leading-edge use cases for artificial intelligence—chat bots and autonomous vehicles
  • Integrating human and machine intelligence: development of human-AI hybrid applications and workflows; using AI to map and access large-scale knowledge databases

Table of contents

  1. Introduction
  2. I. The AI Landscape
  3. 1. The State of Machine Intelligence 3.0
    1. Ready Player World
    2. Why Even Bot-Her?
    3. On to 11111000001
    4. Peter Pan’s Never-Never Land
    5. Inspirational Machine Intelligence
    6. Looking Forward
  4. 2. The Four Dynamic Forces Shaping AI
    1. Abundance and Scarcity of Ingredients
    2. Forces Driving Abundance and Scarcity of Ingredients
    3. Possible Scenarios for the Future of AI
    4. Broadening the Discussion
  5. II. Technology
  6. 3. To Supervise or Not to Supervise in AI?
  7. 4. Compressed Representations in the Age of Big Data
    1. Deep Neural Networks and Intelligent Mobile Applications
    2. Succinct: Search and Point Queries on Compressed Data Over Apache Spark
    3. Related Resources
  8. 5. Compressing and Regularizing Deep Neural Networks
    1. Current Training Methods Are Inadequate
    2. Deep Compression
    3. DSD Training
    4. Generating Image Descriptions
    5. Advantages of Sparsity
  9. 6. Reinforcement Learning Explained
    1. Q-Learning: A Commonly Used Reinforcement Learning Method
    2. Common Techniques of Reinforcement Learning
    3. What Is Reinforcement Learning Good For?
    4. Recent Applications
    5. Getting Started with Reinforcement Learning
  10. 7. Hello, TensorFlow!
    1. Names and Execution in Python and TensorFlow
    2. The Simplest TensorFlow Graph
    3. The Simplest TensorFlow Neuron
    4. See Your Graph in TensorBoard
    5. Making the Neuron Learn
      1. Training Diagnostics in TensorBoard
    6. Flowing Onward
  11. 8. Dive into TensorFlow with Linux
    1. Collecting Training Images
    2. Training the Model
    3. Build the Classifier
    4. Test the Classifier
  12. 9. A Poet Does TensorFlow
  13. 10. Complex Neural Networks Made Easy by Chainer
    1. Chainer Basics
    2. Chainer’s Design: Define-by-Run
    3. Implementing Complex Neural Networks
    4. Stochastically Changing Neural Networks
    5. Conclusion
  14. 11. Building Intelligent Applications with Deep Learning and TensorFlow
    1. Deep Learning at Google
    2. TensorFlow Makes Deep Learning More Accessible
    3. Synchronous and Asynchronous Methods for Training Deep Neural Networks
    4. Related Resources
  15. III. Homebuilt Autonomous Systems
  16. 12. How to Build a Robot That “Sees” with $100 and TensorFlow
    1. Building My Robot
    2. Programming My Robot
    3. Final Thoughts
  17. 13. How to Build an Autonomous, Voice-Controlled, Face-Recognizing Drone for $200
    1. Choosing a Prebuilt Drone
    2. Programming My Drone
    3. Architecture
    4. Getting Started
    5. Flying from the Command Line
    6. Flying from a Web Page
    7. Streaming Video from the Drone
    8. Running Face Recognition on the Drone Images
    9. Running Speech Recognition to Drive the Drone
    10. Autonomous Search Paths
    11. Conclusion
  18. IV. Natural Language
  19. 14. Three Three Tips for Getting Started with NLU
    1. Examples of Natural Language Understanding
    2. Begin Using NLU—Here’s Why and How
    3. Judging the Accuracy of an Algorithm
  20. 15. Training and Serving NLP Models Using Spark
    1. Constructing Predictive Models with Spark
    2. The Process of Building a Machine Learning Product
      1. Prediction
      2. Data Set
      3. Model Training
    3. Operationalization
    4. Spark’s Role
      1. What Are We Using Spark For?
      2. Feature Extraction
      3. Training
      4. Prediction
      5. Prediction Data Types
    5. Fitting It into Our Existing Platform with IdiML
      1. Why a Persistence Layer?
    6. Faster, Flexible Performant Systems
  21. 16. Capturing Semantic Meanings Using Deep Learning
    1. Word2Vec
      1. The CBOW Model
      2. The Continuous Skip-Gram Model
    2. Coding an Example
      1. Looking to Wikipedia for a Big Data Set
    3. Training the Model
    4. fastText
    5. Evaluating Embeddings: Analogies
    6. Results
  22. V. Use Cases
  23. 17. Bot Thots
    1. Text Isn’t the Final Form
    2. Discovery Hasn’t Been Solved Yet
    3. Platforms, Services, Commercial Incentives, and Transparency
    4. How Important Is Flawless Natural Language Processing?
    5. What Should We Call Them?
  24. 18. Infographic: The Bot Platforms Ecosystem
  25. 19. Creating Autonomous Vehicle Systems
    1. An Introduction to Autonomous Driving Technologies
    2. Autonomous Driving Algorithms
      1. Sensing
      2. Perception
      3. Decision
    3. The Client System
      1. Robotics Operating System
      2. Hardware Platform
    4. Cloud Platform
      1. Simulation
      2. HD Map Production
      3. Deep Learning Model Training
    5. Just the Beginning
  26. VI. Integrating Human and Machine Intelligence
  27. 20. Building Human-Assisted AI Applications
    1. Orchestra: A Platform for Building Human-Assisted AI Applications
    2. Bots and Data Flow Programming for Human-in-the-Loop Projects
    3. Related Resources
  28. 21. Using AI to Build a Comprehensive Database of Knowledge
    1. Building the Largest Structured Database of Knowledge
    2. Knowledge Component of an AI System
    3. Leveraging Open Source Projects: WebKit and Gigablast
    4. Related Resources

Product information

  • Title: Artificial Intelligence Now
  • Author(s): O'Reilly Media, Inc.
  • Release date: February 2017
  • Publisher(s): O'Reilly Media, Inc.
  • ISBN: 9781491977620