Book Image

Platform and Model Design for Responsible AI

By : Amita Kapoor, Sharmistha Chatterjee
Book Image

Platform and Model Design for Responsible AI

By: Amita Kapoor, Sharmistha Chatterjee

Overview of this book

AI algorithms are ubiquitous and used for tasks, from recruiting to deciding who will get a loan. With such widespread use of AI in the decision-making process, it’s necessary to build an explainable, responsible, transparent, and trustworthy AI-enabled system. With Platform and Model Design for Responsible AI, you’ll be able to make existing black box models transparent. You’ll be able to identify and eliminate bias in your models, deal with uncertainty arising from both data and model limitations, and provide a responsible AI solution. You’ll start by designing ethical models for traditional and deep learning ML models, as well as deploying them in a sustainable production setup. After that, you’ll learn how to set up data pipelines, validate datasets, and set up component microservices in a secure and private way in any cloud-agnostic framework. You’ll then build a fair and private ML model with proper constraints, tune the hyperparameters, and evaluate the model metrics. By the end of this book, you’ll know the best practices to comply with data privacy and ethics laws, in addition to the techniques needed for data anonymization. You’ll be able to develop models with explainability, store them in feature stores, and handle uncertainty in model predictions.
Table of Contents (21 chapters)
Part 1: Risk Assessment Machine Learning Frameworks in a Global Landscape
Part 2: Building Blocks and Patterns for a Next-Generation AI Ecosystem
Part 3: Design Patterns for Model Optimization and Life Cycle Management
Part 4: Implementing an Organization Strategy, Best Practices, and Use Cases

Part 1: Risk Assessment Machine Learning Frameworks in a Global Landscape

This part provides a detailed introduction to the risks, threats, and challenges that machine learning models in production are vulnerable to. In this part, you will learn about different types of attacks that can be carried out by adversaries and the importance of protecting your models from such attacks. This part also covers the guidelines and standards set by different committees across the world, to facilitate various actions and initiatives at both a national and organizational level.

This part is made up of the following chapters:

  • Chapter 1, Risks and Attacks on ML Models
  • Chapter 2, The Emergence of Risk-Averse Methodologies and Frameworks
  • Chapter 3, Regulations and Policies Surrounding Trustworthy AI