Details

Autor(en) / Beteiligte

• Kapoor, Amita
• Chatterjee, Sharmistha

Titel

Platform and model design for responsible AI : design and build resilient, private, fair, and transparent machine learning models

Ort / Verlag

Birmingham ; Mumbai : Packt Publishing Limited

Erscheinungsjahr

2023

Link zu anderen Inhalten

• Cover

Beschreibungen/Notizen

• Table of ContentsRisks and Attacks on ML ModelsThe Emergence of Risk-Averse Methodologies and FrameworksRegulations and Policies Surrounding Trustworthy AIPrivacy Management in Big Data and Model Design PipelinesML Pipeline, Model Evaluation and Handling UncertaintyHyperparameter Tuning, MLOPS, and AutoMLFairness Notions and Fain Data GenerationFairness in Model OptimizationModel ExplainabilityEthics and Model GovernanceThe Ethics of Model AdaptabilityBuilding Sustainable, Enterprise-Grade AI PlatformsSustainable Model Life Cycle Management, Feature Stores, and Model CalibrationIndustry-Wide Use-cases
• 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.Key FeaturesLearn risk assessment for machine learning frameworks in a global landscapeDiscover patterns for next-generation AI ecosystems for successful product designMake explainable predictions for privacy and fairness-enabled ML trainingWhat you will learnUnderstand the threats and risks involved in ML modelsDiscover varying levels of risk mitigation strategies and risk tiering toolsApply traditional and deep learning optimization techniques efficientlyBuild auditable and interpretable ML models and feature storesUnderstand the concept of uncertainty and explore model explainability toolsDevelop models for different clouds including AWS, Azure, and GCPExplore ML orchestration tools such as Kubeflow and Vertex AIIncorporate privacy and fairness in ML models from design to deploymentWho this book is forThis book is for experienced machine learning professionals looking to understand the risks and leakages of ML models and frameworks, and learn to develop and use reusable components to reduce effort and cost in setting up and maintaining the AI ecosystem