We encourage everyone interested in this topic to register for the live stream and ask their questions via audio or in the chat. If you cannot attend the live stream, feel free to send us your questions in advance via email or on Twitter. A recording of the talk will be made available on our YouTube channel later on.
Abstract: In this talk I introduce Generative Adversarial Networks (GANs) for Social Scientists. GANs are an innovative neural network architecture where two neural networks adversarially learn arbitrary target distributions. A Generator network learns to produce simulated samples that mimic real data. At the same time, a Discriminator network learns to distinguish between real and simulated data. A GAN is successful in producing simulated data if a Discriminator is maximally uncertain about the origins of the data (real or simulated). GANs achieve impressive results in producing synthetic samples from complex data like images (e.g. cats, faces) or audio data (e.g. voices, songs). In this talk, I introduce current applications of GANs and present my work on their use for Social Science research. In particular, I will cover applications to Multiple Imputation, Small Area Estimation and the Generation of fully Synthetic Data. All applications will be accompanied by hands-on code examples.
Click here to import this event into your calendar. Visit our blog, follow us on Twitter, or check out our YouTube channel for recordings of our past events! As always, feel free to forward this email to other interested members of the local academic community and to subscribe to our SSDL mailing list.
„Generative Adversarial Nets for Social Scientists“ by Marcel Neunhoeffer
