يعرض 1 - 20 نتائج من 53 نتيجة بحث عن '(( game ((nn decrease) OR (mean decrease)) ) OR ( ai ((larger decrease) OR (marked decrease)) ))', وقت الاستعلام: 0.34s تنقيح النتائج
  1. 1
  2. 2
  3. 3

    K-means results. حسب Fei Zhang (85787)

    منشور في 2025
    "…By employing K-means clustering on possession duration, we categorized possessions from 1,141 NBA games in the 2019–2020 season into high-frequency (HFS), low-frequency (LFS), and normal-frequency segments (NFS). …"
  4. 4
  5. 5

    Feature importance result of SHAP. حسب Fei Zhang (85787)

    منشور في 2025
    "…By employing K-means clustering on possession duration, we categorized possessions from 1,141 NBA games in the 2019–2020 season into high-frequency (HFS), low-frequency (LFS), and normal-frequency segments (NFS). …"
  6. 6

    Definition of variables. حسب Fei Zhang (85787)

    منشور في 2025
    "…By employing K-means clustering on possession duration, we categorized possessions from 1,141 NBA games in the 2019–2020 season into high-frequency (HFS), low-frequency (LFS), and normal-frequency segments (NFS). …"
  7. 7

    Result of random forest. حسب Fei Zhang (85787)

    منشور في 2025
    "…By employing K-means clustering on possession duration, we categorized possessions from 1,141 NBA games in the 2019–2020 season into high-frequency (HFS), low-frequency (LFS), and normal-frequency segments (NFS). …"
  8. 8
  9. 9
  10. 10
  11. 11
  12. 12
  13. 13
  14. 14

    Tree cover limits occupancy of a declining game bird حسب Bradley Kubecka (7387181)

    منشور في 2025
    "…Probability of bobwhite occupancy decreased as canopy cover increased (β<em><sub>Tree</sub></em> = -0.74, 95% CrI: -1.29 – -0.28); occupancy was over 19 times higher when canopy cover was 44% versus the mean observed value of 80.8% (range: 38–96%). …"
  15. 15
  16. 16
  17. 17
  18. 18
  19. 19
  20. 20

    A novel RNN architecture to improve the precision of ship trajectory predictions حسب Martha Dais Ferreira (18704596)

    منشور في 2025
    "…To solve these challenges, Recurrent Neural Network (RNN) models have been applied to STP to allow scalability for large data sets and to capture larger regions or anomalous vessels behavior. This research proposes a new RNN architecture that decreases the prediction error up to 50% for cargo vessels when compared to the OU model. …"