DFW Data Science - April 4 2016
Dallas, TX
Monday, April 4, 2016
The DFW Data Science Meetup is a community where you can discuss Data Science techniques such as Apache Spark, Apache Drill, Apache Parquet, share a cool Scala idea, spread the love to Dabble or Enhance Systems with Mahout, or you want to learn about Hadoop or NoSQL (SOLR, MongoDB, Casandra), Column DB (Apache Parquet). Veteran or novice - the DFW Data Science Meetup welcomes all. Everything and anything used as a tool by an experimenter is fair game in this community.


Intro workshop in Deep Learning: Everything you always wanted to know about Deep Learning (but were afraid to ask)

Joseph Blue View Bio

According to rumor & innuendo, deep learning is the hottest thing to come out of data science since the first fair coin was struck in Asia Minor. The goals of this high-to-medium-level discussion are to de-mystify deep learning and help machine learning enthusiasts understand how it works, what it can do (and what it cannot), where to get it and what the future might hold. During this workshop, we will expose how deep learning evolved from neural networks, walk through the architecture and training of convolutional & recurrent neural networks (CNN & RNN, respectively) and review practical examples of real-life use cases from the field. We will also touch on current developments (both advancements and challenges) and speculate on how businesses are beginning to adopt these models. Note: experience with Neural Networks isn’t a prerequisite for participation in this discussion, but we assume the attendees are aware of model-building essentials (e.g supervised vs. unsupervised, major categories of algorithms, over-fitting, etc.).


Joseph Blue

In his role as Data Scientist at MapR, Joe assists customers in solving their big data problems, making efficient use of the Hadoop ecosystem to generate tangible results. Recent projects include debit card fraud & breach detection, lead generation from social data, customer matching through record linkage, lookalike modeling using browser history and real-time product recommendations.

Prior to MapR, Joe was the Chief Scientist for Optum (a division of UnitedHealth) and the principal innovator in analytics for healthcare. As a Sr. Fellow with OptumLabs, he applied machine learning concepts to healthcare issues such as disease prediction from co-morbidities, estimation of PMPY (member cost), physician scoring and treatment pathways. As a leader in the Payment Integrity business, he built anomaly detection engines responsible for saving $100M annually in claim overpayments.