Neural feature extraction for calorimeters based on optimum weighting procedures

Seixas, J. M.; Calôba, L. P.; Linhares, Rodrigo T. F.; Kastrup, Bernardo

doi:10.1016/s0168-9002(97)00066-1

Cited by 1 publication

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the outermost cells sample low energy levels but perform eficient discrimination, grouping cells by means of a weighting Combination help to boost the contribution of such cells in the ROI based discrimination, The determination of the weighting factor of each grouped sum is integrated to the training phase of the network, so that optimum normalization factors for the grouped sums can be obtained altogether with the network's weighting vectors that minimize the desired cost function (mean squared error) [7]. Figure 1 shows such a possible ROI mapping.…”

Section: Neural Processingmentioning

confidence: 99%

A neural online triggering system based on parallel processing

Seixas

Calôba

Anjos

et al. 1998

IEEE Trans. Nucl. Sci.

View full text Add to dashboard Cite

The study of a prototype of the second-level triggering system for operation at LHC conditions is addressed by means of a parallel machine implementation. The 16 node transputer based machine uses a fast digital signal processor acting as a coprocessor for optimizing signal processing applications. A C-language development environment is used for running all applications at ultimate speed.The implementation is based on information supplied by four detectors and includes two phases of system operation: feature extraction and global decision. Feature extraction for calorimeters and global decision processing are performed by means of neural networks. Preprocessing and neural network parameters rest in memory and the activation function is implemented using a look up table. Simulated data for the second-level trigger operation are used for performance evaluation.

show abstract

Section: Neural Processingmentioning

confidence: 99%