Envío gratis siempre a todo México.
Haz clic para hacer zoom
Not Available
Sharmistha Chatterjee
Platform and Model Design for Responsible AI
Cargando comentarios…
Comparte
$985
$886
Envío gratis siempre
Comentarios
Cargando el resumen…
Cargando comentarios…
product
1696393Platform and Model Design for Responsible AIhttps://www.gandhi.com.mx/platform-and-model-design-for-responsible-ai/phttps://gandhi.vtexassets.com/arquivos/ids/1290032/df7cca47-82a6-4328-b5ee-d69fbb69bae4.jpg?v=638337796550600000886985MXNPackt PublishingInStock/Ebooks/1673092Platform and Model Design for Responsible AI886985https://www.gandhi.com.mx/platform-and-model-design-for-responsible-ai/phttps://gandhi.vtexassets.com/arquivos/ids/1290032/df7cca47-82a6-4328-b5ee-d69fbb69bae4.jpg?v=638337796550600000InStockMXN99999DIEbook20239781803249773_W3siaWQiOiI0NjkyMTc0My0xYjkzLTQ3NTUtYjViOS1mOWEyYzNhN2Y4ZGUiLCJsaXN0UHJpY2UiOjk4NSwiZGlzY291bnQiOjk5LCJzZWxsaW5nUHJpY2UiOjg4NiwiaW5jbHVkZXNUYXgiOnRydWUsInByaWNlVHlwZSI6Ildob2xlc2FsZSIsImN1cnJlbmN5IjoiTVhOIiwiZnJvbSI6IjIwMjQtMDQtMDhUMTY6MDA6MDBaIiwicmVnaW9uIjoiTVgiLCJpc1ByZW9yZGVyIjpmYWxzZX1d9781803249773_<p><strong>Develop the skills to design responsible AI projects, including model privacy, fairness, and risk assessment methodologies for scalable distributed systems. Explainability features and sustainable model practices are also covered.</strong></p><h4>Key Features</h4><ul><li>Learn risk assessment for machine learning frameworks for use in a global landscape</li><li>Discover patterns for next generation AI ecosystems for successful product design</li><li>Make explainable predictions for privacy and fairness enabled ML training</li></ul><h4>Book Description</h4><p>AI algorithms are ubiquitous, used for everything from recruiting to deciding who will get a loan. With such widespread use of AI in the decision-making process, it is essential that we build an explainable, responsible, and trustworthy AI enabled systems.</p><p>Using this book, you will be able to make existing black box models transparent. Youll 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.</p><p>Complete with step-by-step explanations of essential concepts, practical examples, and self-assessment questions, you will begin to master designing ethical models for traditional and deep learning ML models as well as deploying them in a sustainable production setup.</p><p>Youll learn how to set up data pipelines, validate datasets, and set up component microservices in a secured, private fashion in any cloud agnostic framework. Youll then build a fair and private ML model with proper constraints, tune the hyperparameters, and evaluate the model metrics.</p><p>By the end of the book, you will know how the best practices comply with laws regarding data privacy and ethics, plus the techniques needed for data anonymization. You will be able to develop models with explainability features, store them in feature stores and handle uncertainty in the model predictions.</p><h4>What you will learn</h4><ul><li>Understand the threats and risks involved in machine learning models</li><li>Discover varying levels of risk mitigation strategies and risk tiering tools</li><li>Apply traditional and deep learning optimization techniques efficiently</li><li>Build auditable, interpretable ML models and feature stores.</li><li>Develop models for different clouds including AWS, Azure and GCP</li><li>Incorporate privacy and fairness in ML models from design to deployment</li><li>Industry wide use-cases centered around Finance, Retail, and Healthcare</li><li>Organizational strategies for leadership across domain use-cases</li></ul><h4>Who This Book Is For</h4><p>This book is primarily intended for those who have previous machine learning experience and would like to know about the risks and leakages of ML models and frameworks, and how to develop and use reusable components to reduce effort and cost in setting up and maintaining the AI ecosystem.</p><h4>Table of Contents</h4><ol><li>Risks and Attacks on ML Models</li><li>Emergence of risk-averse methodologies and frameworks</li><li>Nationwide laws and policies surrounding Trustworthy AI</li><li>Privacy management in Big Data Pipelines and Model Design</li><li>Machine Learning Pipeline, Model Evaluation and Handling Uncertainty</li><li>Hyperparameter Tuning, MLOPS, and AutoML options</li><li>Fairness in Data Collection</li><li>Fairness in Model Optimization</li><li>Model Explainability</li><li>Ethics and Model Governance</li><li>Model Adaptability under Ethics</li><li>Building Scalable Enterprise-grade Trustworthy AI platforms</li><li>Sustainable Feature Stores and Model calibration</li><li>Industry-wide Ethical AI Use-cases</li></ol>...(*_*)9781803249773_<p><b>Craft ethical AI projects with privacy, fairness, and risk assessment features for scalable and distributed systems while maintaining explainability and sustainability Purchase of the print or Kindle book includes a free PDF eBook</b></p><h2>Key Features</h2><ul><li>Learn risk assessment for machine learning frameworks in a global landscape</li><li>Discover patterns for next-generation AI ecosystems for successful product design</li><li>Make explainable predictions for privacy and fairness-enabled ML training</li></ul><h2>Book Description</h2>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, its necessary to build an explainable, responsible, transparent, and trustworthy AI-enabled system. With Platform and Model Design for Responsible AI, youll be able to make existing black box models transparent. Youll 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. Youll start by designing ethical models for traditional and deep learning ML models, as well as deploying them in a sustainable production setup. After that, youll 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. Youll 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, youll know the best practices to comply with data privacy and ethics laws, in addition to the techniques needed for data anonymization. Youll be able to develop models with explainability, store them in feature stores, and handle uncertainty in model predictions.<h2>What you will learn</h2><ul><li>Understand the threats and risks involved in ML models</li><li>Discover varying levels of risk mitigation strategies and risk tiering tools</li><li>Apply traditional and deep learning optimization techniques efficiently</li><li>Build auditable and interpretable ML models and feature stores</li><li>Understand the concept of uncertainty and explore model explainability tools</li><li>Develop models for different clouds including AWS, Azure, and GCP</li><li>Explore ML orchestration tools such as Kubeflow and Vertex AI</li><li>Incorporate privacy and fairness in ML models from design to deployment</li></ul><h2>Who this book is for</h2><p>This 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.</p>...9781803249773_Packt Publishinglibro_electonico_edfa7b33-9353-31ed-a4b3-85983fa5726f_9781803249773;9781803249773_9781803249773Sharmistha ChatterjeeInglésMéxicohttps://getbook.kobo.com/koboid-prod-public/packt-epub-a0c5eac1-2d13-47f6-826a-bb861042fc73.epub2023-04-28T00:00:00+00:00Packt Publishing