Attendees should be able to connect to the DLI / GTC Platform Site from their personal laptop. Our training Jupyter notebook illustrates the code along with the steps mentioned for the dataset, driven by Docker so that you don't have to install everything from scratch. An understanding of data science will be needed to gain the most out of the lab.
In addition, it will be helpful but not required to have some prior knowledge of Jupyter notebooks, and it will be a plus if they have knowledge of the GOAi platform to perform analysis and data extraction from MapD/OmniSci, understand preprocessing it in Pygdf/Pandas, analyze nodes in Graphistry, train the model to make clusters with H2O's KMeans, and store the results back in MapD/OmniSci Core.
How To Prepare: All attendees must bring their own laptop and charger. We recommend using a current version of Chrome, Firefox, or Safari for an optimal experience. Create an account at http://courses.nvidia.com/join before you arrive.
Learn how we accelerated the NASA GeneLab dataset in the Kansas University/Loma Linda projects. The dataset, available at NASA Genelab Data Repository, contains current research on mice subjected to a physiological model of spaceflight. You’ll learn how to load, analyze, pre-process, and visualize data, as well as how to do predictive modeling. By accelerating machine learning and deep learning research for NASA and KSU, GOAi provides an open source alternative that reduces research clock time and computational cost. Utilizing a GPU-Accelerated pipeline, scientists can focus on reviewing more data from the research. We’ll explain why we believe that combining different datasets in one analytics platform shifts the focus towards further analysis and deeper insights. We prepared a blog and Jupyter notebook (tested by NVIDIA’s DLI) for this lab.