Session: Federated Learning and Differential Privacy: Privacy Preserving Machine Learning on User’s Data
Federated Learning challenges the standard approaches in Machine Learning that require centralised training of the data. In this session, Sunitha Narayan will explore the key concepts in Federated Learning with an emphasis on User Privacy. You would also learn how various industries and business functions are deploying this privacy-preserving technology, and explore the current open problems in this research area.
- Decentralized and privacy-preserving machine learning, Differential privacy,
Sunitha Narayan is a former entrepreneur with a deep passion for technology products. She is set to graduate from Johns Hopkins University, MS in Computer Science with a minor in Cryptography, and holds a certificate in Product Strategy from Kellogg. She has experience building and scaling innovative products. She was featured widely on national media including The Hindu, (leading national daily in India) for building an electric vehicle prototype that was immediately adopted by the State Government of India. Sunitha was also among the few women selected for a prominent national initiative that involved a nation-wide odyssey to work with technology and social entrepreneurs to drive change. She has founded several chapters for women - professionals, teachers, students & researchers - to support mentorship, allyship & career development. She is passionate about women in the STEM field and the Tech industry.