Schedule & Organization

Go to URL tiny.cc/nipsnotes to Open the Gdoc tiny.cc/nipsnotes – Shared Notes, Questions, Discussion.

View the workshop live by going to the URL tiny.cc/nipshangout.

Link to screencasted recording will be added here afterwards: [      ] Location: **CHANGED** Room 514a, Montreal Convention Centre. Map.

Schedule

8:50 - 9:00 Introductions

Interactive Machine Learning


9:00 - 10:00: "Reinforcement Learning from users: New algorithms and frameworks." Michael Littman, Brown University.



10-10:30: Coffee Break

Machine Teaching

10:30 - 11:45: "Machine Teaching for Personalized Education, Security, Interactive Machine Learning" Jerry Zhu, University of Wisconsin Madison.

[Slides]


"Smooth Imitation Learning". Hoang M. Le, Yisong Yue, & Peter Carr. [PDF]

11:45-1:30: Lunch

Embedding Online Learning Algorithms in Adaptive User Technologies

1:30 - 2:15:  "Enabling real-time evaluation of crowdsourced machine learning algorithms: Experimentation and Personalization in math problems on ASSISTments.org" Neil Heffernan, Worcester Polytechnic Institute.

2:15 - 3:00 Spotlights & Posters    List of Extended Abstracts


Personalization & Contextualization

3:00 - 4:00: From Ads to Interventions: Contextual Bandit Algorithms for Mobile Health". Ambuj Tewari, Huitian Lei, & Susan Murphy. University of Michigan. " (NIH application to "Heartsteps")


4:00 - 4:30: Coffee Break


4:30 - 5:30: "An Interactive Learning Platform for Making Decisions." John Langford, Microsoft Research. Multi-World Testing Intro. Website

Conclusion

5:30-6:30: Panel & Group Discussion on Conclusions, Next Steps, Future Directions. Joseph Jay Williams, Finale Doshi-Velez, Michael Littman, John Langford, Jerry Zhu.


Accepted Presentations – Posters & Spotlights

Bei Peng, James MacGlashan, Robert Loftin, Michael L. Littman, David L. Roberts, & Matthew E. Taylor. "A Need for Speed: Adapting Agent Action Speed to Improve Performance of Task Learning from Turkers." [PDF]

Wei Sun, Anshul Sheopuri, Ying Li, & Thales S. Teixeira. "Cognitive Advertisement Design via Dynamic Bayesian Network." [PDF]

Stefanos Poulis & Sanjoy Dasgupta. "Interactive annotation with feature feedback: from theory to practice." [PDF]

Jens Schreiter, Mona Eberts, Duy Nguyen-Tuong, & Marc Toussaint. "Safe Exploration for Active Learning with Gaussian Process Models." [PDF].

Hoang M. Le, Yisong Yue, & Peter Carr. "Smooth Imitation Learning." [PDF]

Bo Zhang. "Machine Teaching via Simulation Optimization." [PDF]

He He, Paul Mineiro, & Nikos Karampatziakis. "Active Information Acquisition." [PDF]

Adish Singla, Sebastian Tschiatschek, & Andreas Krause. "Adaptive Sampling for Noisy Submodular Maximization with Applications to Crowdsourced Image Collection Summarization." [PDF]

Theja Tulabandhula. "Learning Personalized Optimal Control for Repeatedly Operated Systems." [PDF]

Harold Soh, Scott Sanner and Greg Jamieson. "A Decision-Theoretic Approach for Adaptive User Interfaces in Interactive Learning Systems." [PDF]


Ċ
Joseph Jay Williams,
Nov 15, 2015, 11:04 AM
Ċ
Joseph Jay Williams,
Nov 15, 2015, 11:04 AM
Ċ
FBAL.pdf
(1717k)
Joseph Jay Williams,
Nov 15, 2015, 11:04 AM
Ċ
Joseph Jay Williams,
Nov 15, 2015, 11:04 AM
Ċ
MT.pdf
(1087k)
Joseph Jay Williams,
Dec 12, 2015, 7:35 AM
Ċ
Joseph Jay Williams,
Nov 15, 2015, 11:05 AM
Ċ
Joseph Jay Williams,
Nov 15, 2015, 11:05 AM
Ċ
Harold Soh,
Jan 11, 2016, 7:54 AM
Ċ
Joseph Jay Williams,
Nov 15, 2015, 11:05 AM
Ċ
aia.pdf
(243k)
Joseph Jay Williams,
Nov 15, 2015, 11:04 AM
Ċ
Joseph Jay Williams,
Nov 15, 2015, 11:04 AM
Ċ
Theja Tulabandhula,
Dec 4, 2015, 12:30 PM
Comments