Abstract: 

Despite its transformative potential, the accelerated adoption of AI/ML technologies over the past decade has also led to several avoidable incidents due to insufficient oversight. Based on my recent book, this talk proposes a comprehensive framework for implementing responsible AI. This talk delves into my recently published book, which encapsulates comprehensive methodologies for creating responsible AI. The discussion is based on a multifaceted framework designed to ameliorate AI/ML technology, business protocols, and cultural competencies.

The talk will explore technical approaches for responsible AI, including explainability, model validation, bias management, data privacy, and ML security. Additionally, we'll discuss the formation of an impactful AI risk management practice.

Moreover, the presentation will provide an introductory guide to existing standards, laws, and assessments for AI technology adoption, including the newly released NIST AI Risk Management Framework. Audiences will also be introduced to the available resources on GitHub and Colab, serving as valuable tools for the audience to continue learning, post the presentation.

Session Outline:

Attendees will gain valuable insights into the following areas post-session:

- Understanding the technical aspects of responsible AI, including explainability, model validation, bias management, data privacy, and ML security.
- Formation and implementation of an effective AI risk management practice.
- Knowledge of existing standards, laws, and assessments for AI technology adoption, specifically the new NIST AI Risk Management Framework.
- Appreciation of the importance of responsible AI/ML implementation in ensuring accountability, transparency, and equity.

We won't go into the implementation or demonstrate any code. However, all the tools that we have used in the book are open source.

Background Knowledge:

This presentation is best suited for those with a basic understanding of artificial intelligence and machine learning concepts

Bio: 

Parul Pandey has a background in Electrical Engineering and currently works as a Principal Data Scientist at H2O.ai. Prior to this, she was working as a Machine Learning Engineer at Weights & Biases. Parul is one of the co-authors of Machine Learning for High-Risk Applications book, which focuses on the responsible implementation of AI. She is also a Kaggle Grandmaster in the notebooks category and was one of Linkedin’s Top Voices in the Software Development category in 2019. Parul has written multiple articles focused on Data Science and Software development for various publications and mentors, speaks, and delivers workshops on topics related to Responsible AI.