The future of computing is visual. With everything from smartphones to Spectacles, we are about to see more digital imagery and associated processing than ever before.
In conjunction, 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.
This session will examine the image recognition techniques available with Apache Spark, and how to put those techniques into production. It will further explore algebraic operations on tensors, and how that can assist in large-scale, high-throughput, highly-parallel image recognition. In particular, this session will showcase the use of Spark in conjunction with a high-performance database to operationalize these workflows.
Learn about a combination 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
You’ll also see a live demonstration on constructing and executing a real-time image recognition pipeline.to persist data from Spark.
Session hashtag: #SFml8
Nikita Shamgunov co-founded MemSQL and has served as CTO since inception. Prior to co-founding the company, Nikita worked on core infrastructure systems at Facebook. He served as a senior database engineer at Microsoft SQL Server for more than half a decade. Nikita holds a bachelor’s, master’s and doctorate in computer science, has been awarded several patents and was a world medalist in ACM programming contests.