IPM Data Science Meetup #10
▪️Generative Adversarial Network
▫️By: Dr. Mahdieh Soleymani, Sharif University of Technology
🕙 Thursday 20 Ordibehesht 1397, 10:00 AM
Generative Adversarial Network
Generative adversarial network (GAN) is a class of learning algorithms consisting of a generator and a discriminator network contesting with each other to improve the quality of generated samples. In fact, the generator network creates candidates and the discriminator evaluates them. GAN has shown some successful results in image generation, and a large amount of research have been developed in the last three years and a wide variety of new ideas, techniques, and applications based on GAN have been introduced. According to the recent successes, it seems that GAN has great potential to be applied to synthetic data generations. We will introduce GAN and describe some of its applications in generating images and sequences.
Mahdieh Soleymani received the BS, MSc, and PhD degrees from the Department of Computer Engineering, Sharif University of Technology in 2003, 2005, and 2010. She is an assistant professor of Computer Engineering in Sharif University of Technology since April 2012. She established the Machine Learning Lab in the Computer Engineering Department of this university in 2013. Her research interests include machine learning, deep learning, probabilistic modeling, and intelligent systems.