Synthetic data generation (SDG) is a data augmentation technique necessary for increasing the robustness of models by supplying additional data to train models. We'll explore the use of Transformers for synthetic tabular data generation in the context of credit card transactions. We'll use the Megatron framework, developed by NVIDIA's Applied Deep Learning Research Team, to facilitate training our Transformer SDG model on multi-node, multi-GPU systems and/or supercomputers. We'll work through end-to-end development covering data pre-processing, model pre-training, fine tuning, inference, and evaluation.
Please disregard any reference to "Event Code" for access to training materials. "Event Codes" are only valid during the original live session. Explore more training options offered by the NVIDIA Deep Learning Institute (DLI). Choose from an extensive catalog of self-paced, online courses or instructor-led virtual workshops to help you develop key skills in AI, HPC, graphics & simulation, and more.