Target Audience

Who should attend?
Machine learning practitioners and AI application developers looking to leverage generative AI responsibly, with a focus on fairness, transparency, and ethics in AI development

COURSE AGENDA

AI Principles & Responsible AI

  • Overview of Fairness in AI: Understand the foundational principles of fairness in AI and its importance in machine learning.
  • Tools for Fairness: Learn about various tools used to study the fairness of datasets and models.
  • Lab: Use TensorFlow Data Validation and TensorFlow Model Analysis to ensure fairness in your models.

Fairness in AI

  • Overview of Fairness in AI: A deeper dive into the challenges of ensuring fairness in AI and model training.
  • Fairness Tools: Explore additional tools and techniques to assess and improve the fairness of datasets and models.
  • Lab: Apply TensorFlow Data Validation and TensorFlow Model Analysis to evaluate and ensure fairness in your models.

Interpretability of AI

  • Overview of Interpretability in AI: Understand the importance of interpreting AI models and their decisions.
  • Metric Selection: Learn how to select the right metrics to evaluate the performance and explainability of models.
  • Taxonomy of Explainability: Explore the different approaches to explainability in machine learning models.
  • Tools for Interpretability: Examine various tools used to study and improve the interpretability of AI models.
  • Lab: Use the Learning Interpretability Tool for text summarization to understand model behavior.

Privacy in ML

  • Overview of Privacy in ML: Gain insight into the privacy considerations in machine learning workflows.
  • Data Security: Learn about the importance of data security and techniques for securing sensitive data used in machine learning.
  • Model Security: Explore how to ensure security at the model level and prevent vulnerabilities.
  • Generative AI Security: Understand how to secure generative AI models and applications running on Google Cloud.

AI Safety

  • Overview of AI Safety: Learn about the key principles and practices for ensuring safety in AI models.
  • Adversarial Testing: Understand how to conduct adversarial testing to evaluate the robustness and safety of AI models.
  • Safety in Gen AI Studio: Discover how to apply safety practices within Gen AI Studio for responsible AI model development.
  • Lab: Apply Responsible AI practices in Gen AI Studio to ensure ethical, safe AI deployments.

CONTACT US TO START YOUR GOOGLE CLOUD JOURNEY

Contact Us Now

Fill out the form to download the file