Hack the Hackathon Using fastai and IPEX

Your chances of winning a hackathon competition are directly proportional to the number of experiments that you conduct. Learn how the presenters quickly iterated between testing ideas and models, and analyzing errors to win the AI portion of the Social Good Hackathon at Intel Innovation 2022.

The speakers used fastai to quickly build a starting point. Learn how they used Intel AI tools and frameworks optimizations (powered by oneAPI) to accelerate training and inference on the CPU for faster iterations. This approach allowed the speakers to focus on problem-solving instead of software engineering.


Sai Rama Raju Penmatsa is pursuing his master's degree in software engineering with data science as a specialization at San Jose State University (SJSU). He works as a graduate research assistant in computer vision.

Immediately after Ankur Singh finished his undergraduate studies, he started a company in India: AI Adventures. It provided AI and machine learning solutions to businesses. After three years, he joined Zoop.one as the machine learning team lead. He is pursuing a master's degree in software engineering at SJSU.