Speaker : Soumith Chintala
Venue : KD 101
Time : 6:50 PM - 8:00 PM
Day : 27 Jan 2016 (Wednesday)

Title: Generative adversarial networks (GANs) for unsupervised learning
and natural images

Abstract: In this talk, we will discuss recent advances in method of neural network optimization called adversarial networks, and their application to
generative modeling. Specifically, we will look at the domains of image generation/synthesis - where the goal is to generate fake images that are imperceptible
from the real image distribution. We will finally look into using GANs as an unsupervised learning method.

Speaker Bio:

Soumith Chintala is a Researcher at Facebook AI Research, where he works on deep learning, reinforcement learning, generative image models, agents for video games and large-scale high-performance deep learning. Prior to joining Facebook in August 2014, he worked at MuseAmi, where he built deep learning models for music and vision targeted at mobile devices. He holds a Masters in CS from NYU, and spent time in Yann LeCun's lab building deep learning models for pedestrian detection, natural image OCR, depth-images among others.