For the last meetup, Graham Ganssle gave a talk on Generative Adversarial Networks (GANs) with remarkable real life use cases. Due to the high interest surrounding the topic, we will be following the same theme for the next Journal Club.
The paper we will be discussing this time is Ian Goodfellow's original
"Generative Adversarial Networks": https://arxiv.org/abs/1406.2661
As described by the paper, GANs is a framework for estimating generative models via an adversarial process. Some exciting topics that the paper covers are game theory, generative modeling, and gradient based optimization in adversarial settings.
The journal club is for more advanced Deep Learning practitioners and researchers. Attendees are expected to read the paper at least once and to contribute to the discussion.
Food and drinks will not be provided. If you are interested in sponsoring the journal club meetings, please contact the organizers of the group.
What to bring: a copy of the paper (either digital or hardcopy)