IoT Predictive Maintenance using Deep Learning

Please join us for an exciting evening to learn more about Deep Learning with TensorFlow through a real-world IoT predictive maintenance scenario from Justin Brandenburg (https://www.linkedin.com/in/justin-brandenburg-86422b2/), Data Scientist at MapR Technologies (https://mapr.com).

Parking:

• RBC Plaza offers $6 valet after 4pm at the main entrance.

• Street parking available on Marquette Ave.

• Gavidae Commons lot, directly across 6th St. from the RBC Plaza main entrance, also offers $6 self-park after 4pm.

Schedule:

5:30 pm - 6:00 pm: Networking, pizza and drinks

6:00 pm - 6:05 pm: Welcome by the organizers: Sam & Slim

6:05 pm - 7:00 pm: Talk by Justin Brandenburg from MapR

Sponsors:

• Bright Hat (http://brighthat.io/) is hosting the event

• HEXstream (http://www.hexstream.com) is offering pizza and drinks

Description:

As MapR continues to innovate its Converged Data Platform and how it integrates a globally distributed elastic data plane that not only supports distributed file processing but also strongly consistent geo-distributed database applications with high performance NoSQL document DB, and real-time event streaming capabilities in a single cluster, MapR will provide a technical deep dive into these innovations.

In this talk, we'll look at how organizations can leverage IoT and bring compelling insight into their operations to optimize efficiencies or predict behavior with actionable results with MapR Converged Platform and Deep Learning Models.

We will evaluate and demonstrate a workflow for an IoT predictive maintenance scenario that leverages real-time streaming events and predict behavior using TensorFlow, Spark and Python. We will showcase an entire data pipeline build for data transformation, model training/testing, and data visualization of results.

Bio:

Justin Brandenburg ( https://www.linkedin.com/in/justin-brandenburg-86422b2/ ) is a Data Scientist at MapR Technologies. He has experience in a number of data analytics verticals ranging from counter narcotics to cyber analytics where he has leveraged machine learning, graph theory and dynamic programming to pull value from data.

He has a undergraduate degree in Economics from VA Tech, a Masters in Economics from Johns Hopkins University and a Masters in Computational Social Science from George Mason University.