Fast triggering in high-energy physics experiments using hardware neural networks
Bruce Rolstad Denby, Patrick F. Garda, Bertrand Granado, C. Kiesling, Jean-Christophe Prévotet, Andreas Wassatsch · IEEE Transactions on Neural Networks · 2003
High-energy physics experiments require high-speed triggering systems capable of performing complex pattern recognition at rates of Megahertz to Gigahertz. Neural networks implemented in hardware have been the solution of choice for certain experiments. The neural triggering problem is presented here via a detailed look at the H1 level 2 trigger at the HERA accelerator, Hamburg, Germany, followed by a section on the importance of hardware preprocessing for such systems, and finally some new architectural ideas for using field programmable gate arrays in very high-speed neural-network triggers at upcoming experiments.