Everyone is invited to the monthly virtual seminar on artificial intelligence and machine learning (AI-ML) hosted by the Exobiology Branch at NASA Ames Research Center.

The speaker for this event will be Dr. Aastha Acharya, from the Aviation Systems Division at NASA ARC, discussing the types of uncertainty that arise in machine learning applications, especially within deep learning. Dr. Acharya will help the community better understand these uncertainties and provide ways to work with them through uncertainty quantification techniques.

Talk will be recorded and posted to the AI/ML portal and YouTube channel.

APRIL 17^TH at 10AM PT/1PM ET

Speaker:

Dr. Aastha Acharya

NASA Ames Research Center, Aviation Systems Division

Title:

Understanding and Leveraging Uncertainty Quantification in Deep Learning Systems

Abstract:

As artificial intelligence and machine learning (AI/ML) methods are increasingly adopted into high-stakes applications, concerns about their reliability, robustness, and trustworthiness are also growing. This talk explores the critical role of uncertainty quantification (UQ) in addressing these skepticisms by distinguishing and analyzing two sources of uncertainties in deep learning systems: aleatoric and epistemic. Aleatoric uncertainty is an irreducible form of uncertainty, emerging from sources such as inherent data noise and randomness. Epistemic uncertainty is a reducible form of uncertainty, arising from limited knowledge of model parameters. We will present UQ techniques such as Bayesian Neural Networks, Monte Carlo dropout, and ensemble methods, and demonstrate how they can be integrated into deep learning pipelines. This will result in robust models that provide a measure of confidence in model predictions, thus improving their interpretability, reliability, and trustworthiness.