BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Split Learning: Distributed Machine Learning with Sensitive\, Silo
 ed Data
DTSTART:20191114T120000
DTEND:20191114T140000
DTSTAMP:20260407T163401Z
UID:2f2c9fd83853afbb54b35547b2f974b5de9f186517da092ca48c0692
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Dr. Ramesh Raskar \nInstitute of Microengineering - Dist
 inguished Lecture (Bonus Lecture)\n\nAbstract: Friction in data sharing is
  a large challenge for large scale machine learning.  Emerging technologi
 es in domains such as biomedicine\, health and finance benefit from distri
 buted deep learning methods which can allow multiple entities to train a d
 eep neural network without requiring data sharing or resource aggregation 
 at one single place. The talk will explore the main challenges in data fri
 ction that make capture\, analysis and deployment of ML. The challenges in
 clude siloed and unstructured data\, privacy and regulation of data sharin
 g and incentive models for data transparent ecosystems. The talk will comp
 are distributed deep learning methods of federated learning and split lear
 ning. Our team at MIT has pioneered a range of approaches including automa
 ted machine learning (AutoML)\, privacy preserving machine learning (Priva
 teML) and intrinsic as well as extrinsic data valuation (Data Markets). On
 e of the programs at MIT aims to create a standard for data transparent ec
 osystems that can simultaneously address the privacy and utility of data.\
 n\nBio: Ramesh Raskar is an Associate Professor at MIT Media Lab and direc
 ts the Camera Culture research group. His focus is on AI and Imaging for h
 ealth and sustainability. They span research in physical (e.g.\, sensors\,
  health-tech)\, digital (e.g.\, automated and privacy-aware machine learni
 ng) and global (e.g.\, geomaps\, autonomous mobility) domains. He received
  the Lemelson Award (2016)\, ACM SIGGRAPH Achievement Award (2017)\, DARPA
  Young Faculty Award (2009)\, Alfred P. Sloan Research Fellowship (2009)\,
  TR100 Award from MIT Technology Review (2004) and Global Indus Technovato
 r Award (2003). He has worked on special research projects at Google [X]\,
  Apple Privacy Team and Facebook and co-founded/advised several companies.
  Projet page https://splitlearning.github.io/\n\nThis lecture is part of t
 he IMT Distinguished Lecture Series. The lecture is considered as a bonus 
 lecture for the class MICRO-626 (usual attendance requirement does not app
 ly\, but participation is highly encouraged). 
LOCATION:BM 5202 https://plan.epfl.ch/?room==BM%205202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR