Learning Analytics Workshop - Participants: Difference between revisions
From Santa Fe Institute Events Wiki
No edit summary |
|||
Line 9: | Line 9: | ||
[[image:sficdebacco.jpg|150px|{border}]] <br> | [[image:sficdebacco.jpg|150px|{border}]] <br> | ||
'''Caterina De Bacco''', Postdoctoral Fellow, Santa Fe Institute <br> | '''[http://www.santafe.edu/about/people/profile/Caterina%20De%20Bacco Caterina De Bacco]''', Postdoctoral Fellow, Santa Fe Institute <br> | ||
Caterina works with Professor Cris Moore on problems at the interface between computer science and statistical physics. Her research interests range from combinatorial optimization, inference, message passing and random walks on networks. She is interested in developing novel models and deriving fundamental limits to finding hidden structures behind noisy and incomplete datasets. Her approach combines Bayesian likelihood maximization with techniques borrowed from linear algebra such as low rank matrix approximation and non-negative tensor factorization. Applications range from clustering of sparse high dimensional data to community detection in networks with multiple types of edges. Starting from the theoretical findings, part of the challenge will be to develop efficient algorithmic ideas that are applicable to a broader range of problems and in different settings. | |||
[[image:sfigabby.jpg|150px|{border}]] <br> | [[image:sfigabby.jpg|150px|{border}]] <br> |
Revision as of 16:56, 6 September 2016
Working Group Navigation |
Microsoft Participants
TBA
Santa Fe Institute Participants
Caterina De Bacco, Postdoctoral Fellow, Santa Fe Institute
Caterina works with Professor Cris Moore on problems at the interface between computer science and statistical physics. Her research interests range from combinatorial optimization, inference, message passing and random walks on networks. She is interested in developing novel models and deriving fundamental limits to finding hidden structures behind noisy and incomplete datasets. Her approach combines Bayesian likelihood maximization with techniques borrowed from linear algebra such as low rank matrix approximation and non-negative tensor factorization. Applications range from clustering of sparse high dimensional data to community detection in networks with multiple types of edges. Starting from the theoretical findings, part of the challenge will be to develop efficient algorithmic ideas that are applicable to a broader range of problems and in different settings.
Gabby Beans, Manager of Online Education, Santa Fe Institute
Gwen Warniment, Inquiry Science Education Consortium Program Director, Los Alamos National Laboratory Foundation
Juniper Lovato, Director of Education, Santa Fe Institute
Nikki Pfarr, Design Researcher
Nikki Pfarr is a design researcher who specializes in helping product development teams combine insights from behavioral science with design thinking, to develop innovative products and services. She's supported innovation centers in companies like Google, Samsung, Microsoft, and T-Mobile, with an emphasis on projects related to education, healthcare, and productivity. Recent work has focused on the role of play in learning, incentive strategies to promote engagement in online programs, and how new technologies can enable social and emotional learning. Nikki received an SB in Comparative Media Studies from MIT, and an MDes from the IIT Institute of Design.
Boeing Participants
TBA