Abstract:
A short overview of existing neuromorphic hardware is given as well as the physics
projects making use of them. As a concrete example we describe an innovative
project within the H1-Experiment at the electron-proton collider HERA is
described, instrumenting hardwired neural networks as pattern recognition
machines to disciminate between wanted physics and uninteresting background at
the trigger level. The decision time of the system is less than 20
microseconds, typical for a modern second level trigger. The neural trigger has
been successfully running for the past four years and has turned out new
physics results from H1 unobtainable so far with other triggering schemes. We
describe the concepts and the technical realization of the neural network
trigger system, present the status and the most important physical results, and
motivate an upgrade of the system for the future high luminosity running at
HERA. The upgrade concentrates on intelligent pre-processing of the neural
inputs. We present the physical principles and the underlying algorithms of the
pre-processing step, which is required to be executed in less than 8 microseconds.
Back to Program
Back to ACAT Web page