Accelerating Topic modeling with RAPIDS and BERT models
This talk covers “Topic modeling” using RAPIDS, Numba, CuPy, HuggingFace, and PyTorch to do text processing, Deep Learning based embedding creation, dimensionality reduction, and clustering all on NVIDIA GPUs in an order of magnitude less time than on CPUs.
About the speaker
Senior Data Scientist / Senior Software Engineer at NVIDIA AI
Vibhu Jawa is a senior software engineer and data scientist on the RAPIDS team at NVIDIA, where his efforts are focused on building GPU-accelerated data science products. Prior to NVIDIA, Vibhu completed his M.S at Johns Hopkins where his research was focused on Natural Language Processing and building interpretable machine learning models for healthcare.