SPEAKER: Dr. Stephen G. Odaibo
ABSTRACT: Generative models attempt to infer the native probability distribution of a data type, and to generate samples from that distribution. Following the work of Goodfellow et al (2014), Generative Adversarial Networks (GANs), an adversarial type of generative model, has gained popularity based on the increasingly realistic datasets it can generate. Interesting applications have included "deep fakes" of human faces, and more recently, of medical data.
Some theory of adversarial training algorithms has been in existence for at least 3 decades (Schmidhuber, 1992). However, practical feasibility, awareness, traction, and performance are only now notably rising.
In this talk I will discuss the theory behind GANs, implementation in Keras, some interesting applications, and some likely theoretical limits on their performance for certain tasks such as data augmentation.