fbpx

Identifying and Mitigating Bias in AI


Date:  Thursday, May 23

Start Time: 12:00 pm

End Time: 12:30 pm

From autonomous driving to immersive shopping, and from enhanced video collaboration to graphic design, AI is placing a wealth of possibilities at our fingertips. However, AI comes with vulnerabilities, which can result in costly mishaps. In this talk, we will explore risks related to bias in AI models. We’ll examine the different types of biases that can arise in defining, training, evaluating and deploying AI models, and illustrate them with examples. We will then introduce practical techniques and tools for detecting and mitigating bias, outlining their capabilities and limitations. We will also touch on fairness metrics that can be useful when developing models.

Track

Session Speakers

  • Nikita Tiwari is an AI Enabling Engineer for the OEM PC ecosystem in Intel’s Client Computing Group, bringing the most compelling video-collaboration experiences to the personal computer, making connectivity possible anywhere you go. Her diverse experience spans silicon debug, validation, artificial intelligence and automotive image processing units. She has received a patent for her work in AI and has authored several publications. She obtained her master’s degree in Electrical and Computer Engineering from Portland State University. As a first-generation university graduate, Nikita strives to pay it forward through volunteerism, and her greatest hope is to be a role model for the next generation to pursue STEM. She was recognized with the 2020 Society of Women Engineers Distinguished New Engineer Award. She is also an IEEE Senior Member and part of the IEEE Ethics/Bias criteria review standards group. Her family of three enjoys hiking and running.


Share

Identifying and Mitigating Bias in AI