Track finding with neural networks

Summary, in English

A neural network algorithm for finding tracks in high energy physics experiments is presented. The performance of the algorithm is explored on modest size samples with encouraging results. It is inherently parallel and thus suitable for execution on a conventional SIMD architecture. More important, it naturally lends itself to direct implementations in custom made hardware, which would permit real time operations and hence facilitate fast triggers. Both VLSI and optical technology implementations are briefly discussed.

• Författare: Carsten Peterson
• Avdelning/ar: Department of Astronomy and Theoretical Physics
• Publiceringsår: 1989-07-15
• Språk: Engelska
• Sidor: 537-545
• Publikation/Tidskrift/Serie: Nuclear Instruments & Methods in Physics Research. Section A: Accelerators, Spectrometers, Detectors, and Associated Equipment
• Volym: 279
• Issue: 3
• Länkar: http://dx.doi.org/10.1016/0168-9002(89)91300-4
• Dokumenttyp: Artikel i tidskrift
• Förlag: Elsevier
• Ämne: Other Physics Topics
• Aktiv: Published
• ISBN/ISSN/Övrigt: ISSN: 0168-9002