Abstract: In this talk, you will get an exposure to the various types of deep learning frameworks – declarative and imperative frameworks such as TensorFlow and PyTorch. After a broad overview of frameworks, you will be introduced to the PyTorch framework in more detail. We will discuss your perspective as a researcher and a user, formalizing the needs of research workflows (covering data pre-processing and loading, model building, etc.). Then, we shall see how the different features of PyTorch map to helping you with these workflows.
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. With over 500 commits, Soumith is also one of the primary developers of the popular open-source PyTorch framework for 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 NYU lab building deep learning models for pedestrian detection, natural image OCR, and depth-images among others.