Speaker
Description
Artificial Intelligence (AI) has dramatically transformed the landscape of computing and data processing, marking a paradigm shift in how machines interact with data and perform complex tasks. By leveraging algorithms that can learn from and adapt to data, AI has enabled computers to process and analyze vast amounts of information at speeds and accuracies that were previously unimaginable.
In this talk the developments in CLAS12 tracking are presented leveraging machine learning techniques to achieve increased tracking efficiency, resulting in a 50%-75% increase in statistics in different physics reactions. The novel methods in track parameter reconstruction using artificial intelligence in CLAS12 allow physics reaction identification in real-time, leading to a significant reduction in data processing times (3 to 6 times) for experiments. The methods discussed can be applicable for future experiments running in streaming mode for data reduction and partial data processing in real time.
