California Institute of Technology
Speaker: Jennifer Ngadiuba, Caltech
Deep learning (DL) algorithms are widely used in various fields, e.g., computer vision, speech recognition, or natural language processing, and are becoming ubiquitous across particle physics. As the amount of data collected by next-generation particle physics experiments is about to explode, the physics reach will be limited by the accuracy of algorithms and computational resources. Modern DL algorithms promises to provide improvements in both of these areas. While offering enhanced physics performance, they also lead to increased parallelization and faster computational times on dedicated hardware, here specifically Field Programmable Gate Arrays (FPGAs). This talk will present the ongoing efforts to execute deep learning inference on FPGAs for the real-time analysis of sensor data in particle physics experiments.
You can also watch the conference live through YouTube. The links are available in the community board (WebApp Link).