The future of computing is visual. With everything from smartphone to Spectacles, we are about to see more digital imagery and associated processing than ever before. In conjuction, new computing models are rapidly appearing to help data engineers harness the power of this imagery. Vast resources with cloud platforms, and the sharing of processing algorithms are moving the industry forward quickly. The models are readily available as well. We’ll examine the image recognition techniques available with Apache Spark, and how to put those techniques into production. We will further explore algebraic operations on tensors and examine how that can assist in large scale, high-throughput, highly parallel image recognition. In particular, we’ll showcase the use of Spark in conjunction with a high performance database to operationalize these workflows. This presentation will feature a combinations of _Architectural considerations in building and image recognition pipeline _Advantages and pitfalls of specific approaches _Real-time capabilities for instant matches _Use of a fast relational datastore to persist data from Spark This talk features a live demonstration of constructing and executing a real-time image recognition pipeline.
Session hashtag: #EUai0
Gary is the SVP of Product at MemSQL, where he's responsible for product marketing, technical marketing, and customer engagement. Prior to MemSQL, Gary was the SVP of Product at Fusion-io where he helped expand the product portfolio from one to three product lines. Earlier in his career, Gary worked at infrastructure companies across file systems, caching, and high-speed networking. Gary has written several industry books for O'Reilly Media, including the recently released Data Warehousing in the Age of Artificial Intelligence. Gary holds a bachelor’s degree from Dartmouth College and a master's in business administration from The Wharton School at the University of Pennsylvania.