and Behavior Modeling

voltaireblingData Management

Nov 20, 2013 (3 years and 9 months ago)

99 views

Breakout Session (B2)

Machine Learning, Data Mining
and Behavior Modeling

Moderators:

Narayanan
C
Krishnan, WSU

and

Qiang Yang, Hong Kong UST

1

B2 Machine learning/behavior
modeling, data mining



Facilitators/Scribes:


Narayanan Krishnan (Washington State University),
Qiang Yang (Hong Kong University of Science and
Technology, Hong Kong)


Attendees:


Du Li, David Chu, Gustavo de
Veciana
,
Dejing

Dou,
Diane Cook,
Farnoush

Banaei
-
Kashani
,
Mirco

Musolesi
, Oliver
Brdiczka
, Wang
-
Chien

Lee,
Tanzeem

Choudhury
, Wendy
Nilsen
, Michael Anderson, James
Landay
, James
Rehg
, Mohan
Trivedi
,
Svetha

Venkatesh
, Andrew Campbell

2

Central Questions


Challenges in


Data


Algorithms


Interdisciplinary

3

Machine Learning and Data Mining,
Behavior Modeling


Grand Challenges


Data


Share the data, annotate the data socially, where the data meet the
objectives,


Longitudinal data set over time


Social media for data collection and annotation


Algorithms


Live with noise, poorly labeled but large quantities of data, but design
algorithms that are distributed, adaptive, capable of online learning (can learn
as the data arrives)


Benchmarking, competition


Multidisciplinary


Better understanding of the application goals and objectives


Understanding taxonomy, temporal, social properties human behavior


Education programs


Funding for Interdisciplinary research for behavior modeling

4