The practice of data science is changing with the rise of new deep learning models. 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.
Implementing deep learning models previously took expert knowledge and skills with GPU programming. Now, frameworks provide practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains while providing researchers with low-level components that can be mixed and matched to build new approaches. During this course, we will use fast.ai's deep learning framework. This powerful library will enable you to use deep learning solutions for your problems quickly and easily.
We'll be putting together cohorts of 4-5 learners to complete the fast.ai course together. The group will work together through the course materials and share progress on projects. Participants will meet with our Senior Data Scientist, Dr. Charreau Bell, once each week to ask questions and discuss the content week.
Upon successful completion of this course, you will receive a compute grant the Data Science Institute, either a 6-month to Google Colab Pro, or time on our DGX A100's if your research would benefit from the significant compute. Additionally, you will also be invited to present your work at Applications of Deep Learning showcase.
If you have more limited experience with Python, we suggest that you participate in pre-workshops training. Contact Jesse Spencer-Smith for information (
jesse.spencer-smith@vanderbilt.edu).
