Twitter Science Tech Talk
Date and time
Location
@TwitterBoston
141 Portland Street, 6th Floor Cambridge, Ma 02139Description
Twitter makes extensive use of data to continuously improve its offerings. Our data is wide ranging from Tweets, photos, videos, Vines and Periscope streams to social graph changes and app interactions. So is the number of ways we use the data which includes content classification, a/b testing, ad targeting, recommendations, and many other applications. The Twitter Science group brings together experienced data engineers, statisticians, deep learning pioneers, and machine learning practitioners to tackle these challenges.
Join us for an evening of food, drinks, and talks that offer a peek into the systems and problems we are working on right here in Boston!
Agenda:
6:00 PM // Doors Open
6:00 PM - 7:00 PM // Networking and Appetizers
7:00 PM // Doors Close
7:00 PM - 7:05 PM // Welcome by Tom Woolway
7:05 PM - 7:15 PM // Overview of Twitter Science by Jeremy Rishel, VP of Engineering
7:15 PM - 7:30 PM // A/B Testing at Twitter by Dmitriy Ryaboy
7:30 PM - 7:45 PM // Twitter Semantic Core: In-flight Entity and Topic Classification by Patrick Maguire
7:45 PM - 8:00 PM // From lab to revenue: Deep Learning in the Industry by Naz Erkan
8:00 PM - 8:15 PM // Scalable Bayesian Optimization Using Deep Neural Networks by Jasper Snoek
8:15 PM - 9:00 PM // Networking
9:00 PM // End of Event
Speakers:
Jeremy Rishel (@jdrishel) is Twitter's deputy head of engineering and leads Twitter Science, a group that includes machine learning (Cortex), product data science, and experimentation efforts. Prior to this role he has done extensive work on Twitter's media, video, and TV related products, as well as leading the advertising, publishers, and exchange engineering organization. Previously, he served as senior vice president of engineering for products and data at Bluefin Labs, and earlier he was the CTO at aPriori, a cost management software solution.
Jeremy earned an MBA from the MIT Sloan School of Management and B.S. degrees in Computer Science and Philosophy, also from MIT. He is @jdrishel on Twitter.
Dmitriy Ryaboy (@squarecog) manages Twitter’s Product Instrumentation and Experimentation team. Previously, he created and led Twitter's Data Platform group, responsible for many "big data" technologies like Parquet, Scalding, Summingbird, Heron, and others. He is a committer to several Apache Foundation projects. Dmitriy holds a Master’s degree in "Very Large Information Systems" from CMU and a Bachelor’s in EECS from UC Berkeley.
Naz Ekran (@naz_ekran) is a senior data scientist at Twitter Cortex, NYC. She has been responsible for user location modeling and relevance problems in recommended content quality, with a focus on machine learning methodologies. Formerly she was at Julpan, a start up acquired by Twitter back in 2011, where she worked on real time search and discovery algorithms and developed an evaluation framework for search quality. She holds a Ph.D. in computer science from NYU’s Courant Institute, supervised by Prof. Yann LeCun. Naz is originally from Istanbul, Turkey.
Patrick Maguire (@maguir_e) is the technical lead for Twitter's entity and topic classification system, Semantic Core. Before joining Twitter, he worked at Amazon, where he led the engineering effort to produce natural language understanding models for the Echo device. Patrick holds a Bachelor's degree in Computer Science from Northeastern University.
Jasper Snoek (@latentjasper) completed his PhD in the machine learning group at the University of Toronto. He subsequently held postdoctoral fellowships at the University of Toronto, supervised by Geoffrey Hinton, and at the Harvard Center for Research on Computation and Society. Jasper co-founded the machine learning startup Whetlab, which was recently acquired by Twitter.