IRAPGOGoogleGO-IRAP1.0<ul> <li>Overview of Responsible AI principles and practices</li><li>Implement processes to check for unfair biases within machine learning models</li><li>Explore techniques to interpret the behavior of machine learning models in a human-understandable manner</li><li>Create processes that enforce the privacy of sensitive data in machine learning applications</li><li>Understand techniques to ensure safety for generative AI-powered applications</li></ul><p>To get the most out of this course, participants should have: </p> <ul> <li>Familiarity with basic concepts of machine learning</li><li>Familiarity with basic concepts of generative AI on Google Cloud in Vertex AI</li></ul><p>Machine learning practitioners and AI application developers wanting to leverage generative AI in a responsible manner.</p><h4>Module 1 - AI Principles and Responsible AI</h4><ul> <li>Google&#039;s AI Principles</li><li>Responsible AI practices</li><li>General best practices</li></ul><h4>Module 2 - Fairness in AI</h4><ul> <li>Overview in Fairness in AI</li><li>Examples of tools to study fairness of datasets and models</li><li>Lab: Using TensorFlow Data Validation and TensorFlow Model Analysis to Ensure Fairness</li></ul><h4>Module 3 - Interpretability of AI</h4><ul> <li>Overview of Interpretability in AI</li><li>Metric selection</li><li>Taxonomy of explainability in ML Models</li><li>Examples of tools to study interpretability</li><li>Lab: Learning Interpretability Tool for Text Summarization</li></ul><h4>Module 4 - Privacy in ML</h4><ul> <li>Overview in Privacy in ML</li><li>Data security</li><li>Model security</li><li>Security for Generative AI on Google Cloud</li></ul><h4>Module 5 - AI Safety</h4><ul> <li>Overview of AI Safety</li><li>Adversarial testing</li><li>Safety in Gen AI Studio</li><li>Lab: Responsible AI with Gen AI Studio</li></ul>- Overview of Responsible AI principles and practices - Implement processes to check for unfair biases within machine learning models - Explore techniques to interpret the behavior of machine learning models in a human-understandable manner - Create processes that enforce the privacy of sensitive data in machine learning applications - Understand techniques to ensure safety for generative AI-powered applicationsTo get the most out of this course, participants should have: - Familiarity with basic concepts of machine learning - Familiarity with basic concepts of generative AI on Google Cloud in Vertex AIMachine learning practitioners and AI application developers wanting to leverage generative AI in a responsible manner.Module 1 - AI Principles and Responsible AI - Google's AI Principles - Responsible AI practices - General best practices Module 2 - Fairness in AI - Overview in Fairness in AI - Examples of tools to study fairness of datasets and models - Lab: Using TensorFlow Data Validation and TensorFlow Model Analysis to Ensure Fairness Module 3 - Interpretability of AI - Overview of Interpretability in AI - Metric selection - Taxonomy of explainability in ML Models - Examples of tools to study interpretability - Lab: Learning Interpretability Tool for Text Summarization Module 4 - Privacy in ML - Overview in Privacy in ML - Data security - Model security - Security for Generative AI on Google Cloud Module 5 - AI Safety - Overview of AI Safety - Adversarial testing - Safety in Gen AI Studio - Lab: Responsible AI with Gen AI Studio1 day650.00695.00695.00850.00950.00950.00950.00790.00