BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : DeepDive: A Data Management System for Machine Lea
 rning Workloads
DTSTART:20160310T101500
DTEND:20160310T113000
DTSTAMP:20260407T184001Z
UID:68a3cf96feaf99e829f5a1656e23e94cc26144c50d247e575b4b16d9
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Ce Zhang - Stanford University\nIC Faculty candidate\nAbs
 tract :\nMany pressing questions in science are macroscopic: they require 
 scientists to consult information expressed in a wide range of resources\,
  many of which are not organized in a structured relational form. Knowledg
 e base construction (KBC) is the process of populating a knowledge base\, 
 i.e.\, a relational database storing\nfactual information\, from unstructu
 red inputs. KBC holds the promise of facilitating a range of macroscopic s
 ciences by making information accessible to scientists. One key challenge 
 in building a high-quality KBC system is that developers must often deal w
 ith data that are both diverse in type and large in size. Further complica
 ting the scenario is that these data need to be manipulated by both relati
 onal operations and state-of-the-art machine-learning techniques.\nMy rese
 arch focuses on building a data management system for machine learning wor
 kloads with the goal to help this complex process of building KBC systems.
  The system I build is called DeepDive\, whose ultimate goal is to allow s
 cientists to build a KBC system\, and machine learning systems in general\
 , by declaratively specifying domain knowledge without worrying about any 
 algorithmic\, performance\, or scalability issues. DeepDive has been used 
 by users without machine learning expertise in a number of domains from pa
 leobiology to genomics to anti-human trafficking. In this talk\, I will de
 scribe the DeepDive framework\, its applications\, and underlying techniqu
 es we developed to speed up a range of machine learning workloads by up to
  two orders of magnitude.Bio :\nCe is a postdoctoral researcher in Compute
 r Science at Stanford University. He is working with Christopher Ré on da
 ta management and database systems. With the indispensable help of many co
 llaborators\, his PhD work produced the system DeepDive\, a trained data s
 ystem for automatic knowledge-base construction. As part of his PhD thesis
 \, he led the research efforts that won the 2014 SIGMOD Best Paper Award a
 nd was invited to the “Best of VLDB 2015” special issue\; PaleoDeepDiv
 e\, a machine-reading system for paleontologists\, was featured in Nature 
 magazine\, and he also led the Stanford team that produced the top-perform
 ing machine-reading system for TAC-KBP 2014 slot-filling evaluations using
  DeepDive. Ce obtained his PhD from the University of Wisconsin-Madison\, 
 advised by Christopher Ré\, and his Bachelor of Science degree from Pekin
 g University\, advised by Bin Cui.More information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR