MSST 2015 Keynote
Ron Bekkerman, University of Haifa, Israel
Can Smart Storage be the Future of Machine Learning?
The field of Machine Learning is currently undergoing a significant transformation. From a niche methodology comprehensible to experts, it is becoming the main stream tool available for masses. From modeling thousands of data instances, it now needs to make sense of billions. From extending sophisticated intractable models, it now has to focus on parallelizing conceptually simple optimization procedures. From prototyping in Matlab, Machine Learning practitioners are now moving to programming GPUs and FPGAs—but they still use generic storage. In this talk, I will outline requirements to designing the smart storage systems of the future—to build the foundation for the next-generation intelligent data processing.
Dr. Ron Bekkerman is an Assistant Professor of Data Science at the University of Haifa, Israel, and the CTO of a stealth mode startup. Before becoming an academic in 2013, Ron was the Chief Data Officer of Carmel Ventures, a leading Israeli VC fund. Prior to that, Ron was a Senior Research Scientist at LinkedIn, and a Research Scientist at HP Labs in the Bay Area. Ron holds a PhD in Machine Learning from UMass Amherst, and MSc/BSc in CS from the Technion. Ron serves on the Organizing Committee of SIGKDD, the top-tier Data Mining conference. He is the corresponding editor of "Scaling up Machine Learning", and the creator of a series of popular Machine Learning lectures on YouTube.