Visual data (images/videos) is rich in valuable insights. Data science and ML techniques can help understand visual content and enable better customer experience across application domains, in turn driving its exponential growth. A key factor for success in visual ML is to get the foundational data infrastructure right, which can be extremely challenging and time consuming due to a lack of data management solutions designed with visual data or data science in mind.
In this talk, I will start by briefly highlighting why visual data today needs special treatment and how this can be achieved. I will also dive deeper into certain architecture and design decisions that have worked well so far as we build such a database ourselves, and give you a quick preview of our product, ApertureDB, and where we are going next.
Vishakha Gupta-Cledat is Co-founder and CEO of ApertureData. Prior to that, she worked at Intel Labs for over 7 years where she led the design and development of VDMS (the Visual Data Management System) which forms the core of ApertureData’s product, ApertureDB. Vishakha holds a Ph.D in Computer Science from the Georgia Institute of Technology and a M.S. in Information Networking from Carnegie Mellon University. She has worked on scheduling in heterogeneous multi-core environments, graph based storage and applications on non volatile memory systems, and visual data management challenges for analytics use cases.