The application of AI algorithms in domains such as criminal justice, credit scoring, and hiring holds unlimited promise. At the same time, it raises legitimate concerns about algorithmic fairness. There’s a growing demand for fairness, accountability, and transparency from ML systems. And we need to remember that training data isn’t the only source of possible bias and adversarial contamination. It can also be introduced through inappropriate data handling, inappropriate model selection, or incorrect algorithm design. We need a pipeline that’s open, transparent, secure, and fair and that fully integrates into the AI lifecycle.
Animesh Singh examines how to build such a pipeline while leveraging open source projects. Such a pipeline requires a robust set of bias and adversarial checkers, debiasing, and more.
This session is sponsored by IBM.
Animesh Singh is a senior technical staff member (STSM) and program director for IBM Watson and Cloud Platform, where he leads machine learning and deep learning initiatives on IBM Cloud and works with communities and customers to design and implement deep learning, machine learning, and cloud computing frameworks. He has a proven track record of driving design and implementation of private and public cloud solutions from concept to production. Animesh has worked on cutting-edge projects for IBM enterprise customers in the telco, banking, and healthcare industries, particularly focusing on cloud and virtualization technologies, and led the design and development first IBM public cloud offering.
©2019, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org