CiML 2015‎ > ‎

Schedule

CiML2015
NIPS 2015 CiML workshop
[new: we have posted the slides below]
Saturday, December 12, 2015
Palais des Congrès de Montréal
Convention and Exhibition Center

Morning session (9:00 am-12:00 pm)
9:00 - Welcome and introduction. Evelyne Viegas [slides]
9:10 - Invited talk,  Challenges in Medical Image Analysis: Comparison, Competition, CollaborationBram van Ginneken [slides]
9:50 - Break 
10:20 - Invited talk, Techniques and Technologies for Efficient and Realistic Benchmarks: Examples from the MediaEval Multimedia Benchmark and CLEF NewsREELMartha Larson [slides]
11:00 - Discussion: Open Innovation, Balazs Kegl and Ben Hamner moderators [Balazs' post][Balazs' slides]
12:00 - Break

Break-out session on AutoML challenge
12:30 - Presentation of the AutoML challenge. Isabelle Guyon -- Announcement of the new GPU track. [slides]
13:00 - Automated Machine Learning: Successes & Challenges. Frank HutterTeam aaad_freiburg. First place AutoML1 phase, second place AutoML2 phase. [paper][supplementary material][slides]
13:30 - Sensible allocation of computation for ensemble construction. James Lloyd. Team jrl44/backstreet.bayes. First place AutoML2 phase, second place AutoML1 phase. [slides]
14:00 - Scalable ensemble learning with stochastic feature boosting. Eugene Tuv. Team ideal.intel.analytics. First place Final0 phase, second place Final1 phase. [slides]
14:30 - Break 

Afternoon session (15:00-18:30)
15:00 - Invited talk, Lessons Learned from the PASCAL VOC Challenges, and Improving the Data Analytics ProcessChris Williams [slides]
15:40 - Discussion: Coopetitions, Evelyne Viegas and Isabelle Guyon moderator 
16:40 - Break 
17:00 - Contributed talk, Academic Torrents: Scalable Data Distribution, Henry Z. Lo and Joseph Paul Cohen [paper][slides]
17:30 -  Open discussion, Michele Sebag modelator 
18:20 - Wrap up
18:30 - Adjourn

CiML dinner

 Eugene Tuv
Eugene Tuv
 James Lloyd
James Lloyd
 
Chris Willians
 
Balazs Kegl
Joseph P. Cohen and Henry Z. Lo
Ben Hamner
 Frank Hutter
Frank Hutter
 Bram van Ginneken
Bram van Ginneken 
 Erick Watson
Erick Watson
Joseph, Henry & Sebastien Treger
 
Jaffray Woodriff & Bram
Balazs, John Platt & Chris

We are connected to the Bayesian Optimization workshop and the Black Box Learning and Inference workshop, because they both treat in some way the "Automatic Machine Learning" problem, which we will discuss during the lunch session.
We are grateful to our Committee for helping put this program together.
Ċ
Isabelle Guyon,
Dec 29, 2015, 8:38 AM
Ċ
Isabelle Guyon,
Dec 29, 2015, 8:39 AM
Ċ
Isabelle Guyon,
Dec 13, 2015, 10:27 AM
Ċ
Isabelle Guyon,
Dec 13, 2015, 10:29 AM
Ċ
Isabelle Guyon,
Dec 13, 2015, 10:27 AM
Ċ
Isabelle Guyon,
Dec 29, 2015, 8:42 AM
Ċ
Isabelle Guyon,
Dec 12, 2015, 10:05 AM
Ċ
Isabelle Guyon,
Dec 12, 2015, 10:09 AM
ą
Level5.png
(106k)
Isabelle Guyon,
Nov 27, 2015, 8:35 AM
ċ
Tuv_CiML_NIPS2015.zip
(13714k)
Isabelle Guyon,
Dec 29, 2015, 8:47 AM
Ċ
Isabelle Guyon,
Dec 13, 2015, 10:27 AM
Ċ
Isabelle Guyon,
Dec 13, 2015, 10:32 AM
Ċ
Isabelle Guyon,
Dec 13, 2015, 9:44 AM