Enabling Data-driven Innovation in Product Lifecycles with Synthetic Data
About this Session
Conversations with leading enterprise AI vendors across market verticals indicate that a lack of access to realistic and diverse data from multiple deployments hampers innovation. For instance, when products trained on data are not representative of customer environments, there is no way to quantitatively assess products; or when machine learning workflows experience data drift, the product audit/feedback is not quantitative. The result today is lower quality products, a lack of transparency, lots of effort in debugging/reproduction/resolution, and the inability to share insights across customers.
Hear from Vyas Sekar, Professor at Carnegie Mellon University who is leading research on the feasibility of using synthetic data using Generative Adversarial Networks (GANs) to address these challenges. Vyas and team have identified and addressed key fidelity, scalability, and privacy challenges and tradeoffs in existing GAN-based approaches. By synthesizing domain-specific insights with recent advances in machine learning and privacy, we identify design choices to tackle these challenges.
Vyas is the Tan Family Professor of Electrical and Computer Engineering in the ECE Department at CMU with a courtesy appointment in the Computer Science Department. He is also affiliated with Cylab and co-direct the Future of Enterprise Security initiative @Cylab. He works broadly at the intersection of networks, systems, and security.
About Tech Talks
A regular series by Soroco, Tech Talks are expert-led technical sessions that deep dive into a specific area of technology and provide engineers valuable insights and tools. It also examines fascinating research, use cases and facilitates larger conversations around cutting-edge tech.