The practice of data science is changing with the rise of powerful, flexible and capable models called transformers. You can solve many different problems using a single pre-trained model, sometimes with no additional training on your data (“zero-shot” solutions). From text, to images, to audio (“textless Natural Language Processing”), you can ask and answer questions, identify objects in images, identify concepts in spoken conversations, ask questions about tables of data, and more, all using the same type of model–transformers. The emphasis for the Intensive will be Transformers–how to use them, how to train them, and how to deploy them to solve a variety of problems. The goal is that participants who come to the workshop with data for a project in-hand will end the workshop with an initial model upon which to build further work.
All sessions will be remote, on Zoom.
The Winter course, while free, has limited capacity. The goal of the workshop is to generate new research on the Vanderbilt University campus using deep learning techniques. Recordings and resources from the workshops will be made available to everyone. Priority for participation in the live workshop will be given to 1) researchers that have a research goal in mind (and, ideally, some preliminary data in hand) and 2) students who are interested in joining the researchers on projects that arise from these workshops, then 3) all others interested in deep learning. Even if you don’t have a particular project defined, but are interested in using the techniques, please do apply. Feel free to reach out to discuss possible projects if you don’t already have one in mind! (https://calendly.com/dsi-data-science-team/student-participation)
Register for the workshop at https://bit.ly/dsi-ai-winter!