For our February 2017 Data Science DC (http://www.datacommunitydc.org/sponsorship/data-science-dc-sponsorship) Meetup we are excited to be joined by Jennifer Sleeman, who will give us an introduction to a deep learning generative model, Generative Adversarial Networks (GAN). GANs have been used to generate samples of realistic images and even generate song lyrics! Jennifer is a research scientist for Deep Learning Analytics (http://www.deeplearninganalytics.com/) and a Ph.D. candidate at UMD with research interests in machine learning, data analytics, natural language processing, knowledge representation and the semantic web.
• 6:30pm -- Networking and Refreshments
• 7:00pm -- Introduction, Announcements, GMU Welcome
• 7:30pm -- Presentation and Discussion
• 8:30pm -- Data Drinks (at Liberty Tavern, 3195 Wilson Blvd)
Welcoming Remarks from GMU Staff:
Toni Andrews, Associate Director – Office of Community & Local Government Relations
Paige Wolf, Sr. Assistant Dean, Graduate Programs – School of Business
Tracy Mason, Assistant Dean, Strategic Communications – College of Science
Stephen Nash, Senior Associate Dean, Volgenau School of Engineering
While deep learning has made historic improvements in speech recognition and object recognition in recent years, almost all of these gains have been in supervised learning of now fairly well understood discriminative models. In the larger context of machine learning, less is understood about both unsupervised and generative models, but Generative Adversarial Networks have emerged as a promising approach to making progress in that direction. We are going to introduce Generative Adversarial Networks (GAN), a deep learning generative model. GANs have primarily been used to generate samples of realistic images but other recent uses have included generating song lyrics, images from captions and video. We will begin with a gentle background of the theory of generative models and GANs in particular and show how GANs are being used today. We will then step through the code for training a basic GAN and we will show how to use a pre-trained GAN to generate images. The objective of this talk is to provide a basic introduction to generative models and Generative Adversarial Networks such that you can walk away from this talk with enough understanding to train and test your own GAN.
Speaker Bio: Jennifer Sleeman
Jennifer Sleeman is a research scientist for Deep Learning Analytics (http://www.deeplearninganalytics.com/). She had been a software engineer for over 15 years, working predominantly with start-up companies. Jennifer is also a Ph.D. candidate at the University of Maryland, Baltimore County advised by Tim Finin. Her research interests are machine learning, data analytics, natural language processing, knowledge representation and the semantic web. In her spare time, she volunteers with the FIRST LEGO League to help teach young children how to design, build and program robots.
This event is sponsored by the George Mason University (https://www2.gmu.edu/), Statistics.com (http://bit.ly/12YljkP), Elder Research (http://datamininglab.com/), Novetta (https://www.novetta.com/), Booz Allen Hamilton (https://www.boozallen.com/consulting/strategic-innovation/nextgen-analytics-data-science), and AOL (http://engineering.aol.com/). (Would your organization like to sponsor too? Please get in touch! (http://www.datacommunitydc.org/sponsorship/data-science-dc-sponsorship))
George Mason is easy to get to via metro (Virginia Square - GMU, on the Orange/Silver line), and parking is also available for a fee in the Founder's Hall Garage.
Directions to George Mason University’s Arlington Campus (http://www.gmu.edu/resources/welcome/Directions/Directions-to-Arlington.html)
Metro – Virginia Square (https://www.wmata.com/rider-guide/stations/virginia-sq.cfm)
Campus Map (http://www.gmu.edu/resources/welcome/ArlingtonMap2016.pdf)