Loading...
Please wait, while we are loading the content...
Similar Documents
A Neural Network for Global Second Level Trigger - A Real-time Implementation on DecPeRLe-1 (1995)
| Content Provider | CiteSeerX |
|---|---|
| Author | Lundheim, L. Legrand, I. C. Moll, L. |
| Description | In the second level triggering for ATLAS "Regions of Interest" (RoIs) are defined in (etha, phi) corresponding to possibly interesting particles. For every RoI physically meaningful parameters are extracted for each subdetector. Based on these parameters a classification of the particle type is made. A feed-forward neural net with 12 input variables, a 6-node intermediate layer, and 4 output nodes has earlier been suggested for this classification task. The reported work consists of an implementation of this neural net using a DECPeRLe-1, a Programmable Active Memory (PAM). This is a reconfigurable processor based on Field Programmable Gate Arrays (FPGAs), which has also been used for real-time implementation of feature extraction algorithms for second level triggering. The implementation is pipelined, runs with a clock of 25 MHz, and uses 0.64 microseconds for one particle classification. Integer arithmetic is used, and the performance is comparable to a floating point version. 1 Intr... |
| File Format | |
| Language | English |
| Publisher Date | 1995-01-01 |
| Publisher Institution | Real Time Implementation on DecPeRLe-1, CERN/EAST note |
| Access Restriction | Open |
| Subject Keyword | Feature Extraction Algorithm Reported Work Feed-forward Neural Net Second Level Meaningful Parameter Atlas Region Classification Task Neural Net Reconfigurable Processor Input Variable Programmable Active Memory Neural Network 6-node Intermediate Layer Field Programmable Gate Array Interesting Particle Output Node Floating Point Version Real-time Implementation Particle Classification Particle Type |
| Content Type | Text |
| Resource Type | Article |
