Responsible Machine Learning

Responsible Machine Learning

by Patrick Hall, Navdeep Gill, Benjamin Cox
Released October 2020
Publisher(s): O'Reilly Media, Inc.
ISBN: 9781492090861

Explore a preview version of Responsible Machine Learning right now.

O’Reilly members get unlimited access to live online training experiences, plus books, videos, and digital content from 200+ publishers.

Start your free trial

Book description

Like other powerful technologies, AI and machine learning present significant opportunities. To reap the full benefits of ML, organizations must also mitigate the considerable risks it presents. This report outlines a set of actionable best practices for people, processes, and technology that can enable organizations to innovate with ML in a responsible manner.

Authors Patrick Hall, Navdeep Gill, and Ben Cox focus on the technical issues of ML as well as human-centered issues such as security, fairness, and privacy. The goal is to promote human safety in ML practices so that in the near future, there will be no need to differentiate between the general practice and the responsible practice of ML.

This report explores:

  • People: Humans in the Loop--Why an organization's ML culture is an important aspect of responsible ML practice
  • Processes: Taming the Wild West of Machine Learning Workflows--Suggestions for changing or updating your processes to govern ML assets
  • Technology: Engineering ML for Human Trust and Understanding--Tools that can help organizations build human trust and understanding into their ML systems
  • Actionable Responsible ML Guidance--Core considerations for companies that want to drive value from ML

Publisher resources

Download Example Code

Table of contents

  1. Preface
  2. 1. Introduction to Responsible Machine Learning
    1. What Is Responsible Machine Learning?
      1. Responsible Artificial Intelligence
        1. A Responsible Machine Learning Definition
  3. 2. People: Humans in the Loop
    1. Responsible Machine Learning Culture
      1. Accountability
      2. Dogfooding
      3. Demographic and Professional Diversity
      4. Cultural Effective Challenge
      5. Going Fast and Breaking Things
    2. Get in the Loop
      1. Human Audit of Machine Learning Systems
      2. Domain Expertise
      3. User Interactions with Machine Learning
      4. User Appeal and Operator Override
      5. Kill Switches
    3. Going Nuclear: Public Protests, Data Journalism, and White-Hat Hacking
  4. 3. Processes: Taming the Wild West of Machine Learning Workflows
    1. Discrimination In, Discrimination Out
      1. Algorithmic Discrimination and US Regulations
    2. Data Privacy and Security
    3. Machine Learning Security
    4. Legality and Compliance
    5. Model Governance
      1. Model Monitoring
      2. Model Documentation
      3. Hierarchy and Teams for Model Governance
      4. Model Governance for Beginners
    6. AI Incident Response
    7. Organizational Machine Learning Principles
    8. Corporate Social Responsibility and External Risks
      1. Corporate Social Responsibility
      2. Mitigating External Risks
  5. 4. Technology: Engineering Machine Learning for Human Trust and Understanding
    1. Reproducibility
      1. Metadata
      2. Random Seeds
      3. Version Control
      4. Environments
      5. Hardware
    2. Interpretable Machine Learning Models and Explainable AI
      1. Interpretable Models
      2. Post hoc Explanation
    3. Model Debugging and Testing Machine Learning Systems
      1. Software Quality Assurance for Machine Learning
      2. Specialized Debugging Techniques for Machine Learning
    4. Benchmark Models
      1. Model Debugging
      2. Model Monitoring
    5. Discrimination Testing and Remediation
      1. Testing for Discrimination
      2. Remediating Discovered Discrimination
    6. Securing Machine Learning
      1. Machine Learning Attacks
      2. Countermeasures
    7. Privacy-Enhancing Technologies for Machine Learning
      1. Federated Learning
      2. Differential Privacy
      3. Causality
  6. 5. Driving Value with Responsible Machine Learning Innovation
    1. Trust and Risk
    2. Signal and Simplicity
    3. The Future of Responsible Machine Learning
    4. Further Reading
    5. Acknowledgments

Product information

  • Title: Responsible Machine Learning
  • Author(s): Patrick Hall, Navdeep Gill, Benjamin Cox
  • Release date: October 2020
  • Publisher(s): O'Reilly Media, Inc.
  • ISBN: 9781492090861