Generative Adversarial Networks (GAN), an introduction by Jennifer Sleeman of Deep Learning Analytics
January 31, 2017
Jennifer Sleeman of Deep Learning Analytics spoke at George Mason University's Founder's Hall on February 1, 2017, introducing Generative Adversarial Networks (GANs), a deep learning generative model. To date, GANs have primarily been used to generate realistic samples of images but other recent uses have included generating images from captions and video. The talk introduced the theory of generative models and GANs in particular and showed how GANs are being used today. The talk provided a basic introduction to generative models and Generative Adversarial Networks with a short example in keras.
Jennifer Sleeman is a research scientist for Deep Learning Analytics. 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.