1. Forward Tracking in the ILD Detector

2. ILC

6. the goal Standalone track search for the FTDs (Forward Tracking Disks)

8. Digitizer Vertextion Reconstruction Track Reconstruction

9. Why not combine with TPC tracking?

10. TPC

11. FTDs

12. Methods Cellular Automaton Kalman Filter Hopfield Neural Network

13. The Cellular Automaton

15. It's about rules

16. IP

17. cell ( segment)

18. state 0

23. On the FTDs

24. The Hits

25. The Segments

26. Cellular Automaton

27. Clean Up

28. Longer Segments

29. Cellular Automaton

30. Clean Up

31. Track Candidates

32. Kalman Filter Prediction → Filtering (Updating) → Smoothing Superior to simple helix fitter Quality Indicator: χ ² probability

34. Kalman Filter Prediction → Filtering (Updating) → Smoothing Superior to simple helix fitter Quality Indicator: χ ² probability

37. Track Candidates

38. Kalman Filter

39. p > 0.005

41. The Hopfield Neural Network Track ↔ Neuron Goal: the global minimum

44. T=2 T=1 T=0

46. Background Inner 2 disks are pixel detectors How many bunch crossings? 100 BX * hit density ≈ 900 hits / pixel disk

47. Ghost hits Outer 5 disks are strip detectors Solution: shallow angle

48. At the moment Conversion to new geometry (staggered petals) Debugging and efficiency Seperating core form implementation Sensible use of Hopfield Neural Network Robustification Picking up hits from other places More analysis Individual steering for pattern recognition → xml file Measure the improvement (old vs. new software)

49. Thanks to Rudi Frühwirth and Winfried Mitaroff Steve Aplin, Frank Gaede and Jan Engels And Jakob Lettenbichler (Belle 2)

50. Thank you!

51. Back Up

52. Dependencies FTD drivers and gear → at the moment in between solution The real background Bad χ ² probability distribution Number of integrated bunchcrossings

56. Before Hopfiel Neural Network

57. After Hopfield Neural Network

58. tracks will Skip a layer Connect directly to the IP

59. regions