Augmenting Knowledge Discovery in PubMed with R

This is a past event

103 people went

Price: $5.00 /per person

: iHeartRadio Theater presented by P.C. Richard & Son

32 Avenue of the Americas · New York, NY

How to find us

When entering the lobby from 6th avenue the theater is on the left

Location image of event venue

Details

This month we have Michael Kane from Yale discussing knowledge discovery in the biomedical sciences.

Thank you again to Misha Lisovich and the iHeartRadio Theater (https://foursquare.com/v/iheartradio-theater-new-york-ny/4b032755f964a5200f4d22e3) for hosting us.

About the talk:

Electronic access to current, scientific literature is essential to continued discovery and progress in the biomedical sciences. The online literature provides for the efficient dissemination of published knowledge and has become ever more convenient, thanks to public databases such as PubMed. However there has been little change in the basic way we electronically search for information, i.e. by keyword-based queries and manual scanning of the returned titles and abstracts. This talk outlines my current efforts for the Bill and Melinda Gates Foundation to integrate higher-level, semantic approaches to understand the relational structure of articles in scientific corpuses. I will place heavy emphasis on computational principles developed to address the challenge of creating an "augmented knowledge discover engine" that allows individual researchers to understand the landscape of relevant data in their subject area. The long-term goal of this project is to provide new perspectives on the current literature and identify new, potentially untapped areas for scientific discovery.

About Michael:

Michael Kane is part of the Biostatistics Faculty at Yale University. His research interests are in the areas of scalable computational learning, augmented knowledge discovery, and stochastic approximation. He is the 2010 winner of the American Statistical Association's Chambers Statistical Software Award for the Bigmemory Project, a set of software libraries that allow the R programming environment to scale to terabyte-scale data. In 2011 he was awarded a grant on DARPA's XDATA project, part of the White House's Big Data Initiative for design and implementation of an elastic, distributed computing framework.

In 2012 he was was the recipient of the Bill and Melinda Gates Foundation’s Grand Challenge Round 11 Award for the semantic clustering of medical and academic literature. He serves as an Editor for the Journal of Statistical Software and is this year's Program Chair for the Graphics Section at the Joint Statistical Meetings.

Pizza starts at 6:15, giveaways and Michael's talk begin at 7 and then after we will head to a local bar.