يعرض 1 - 20 نتائج من 2,885 نتيجة بحث عن '(( making task decrease ) OR ( a ((larger decrease) OR (marked decrease)) ))', وقت الاستعلام: 0.40s تنقيح النتائج
  1. 1
  2. 2
  3. 3
  4. 4
  5. 5

    ROC analysis to mark selectivity results in mostly mixed-selective units. حسب Thomas S. Wierda (22404198)

    منشور في 2025
    "…The large number of mixed selective units also results in a significant decrease in accuracy when these neurons are targeted as compared to <a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1013559#pcbi.1013559.g006" target="_blank">Fig 6c</a> where there was no significant effect visible after targeting mixed selective units, likely because there were less mixed selective units present. …"
  6. 6
  7. 7
  8. 8
  9. 9
  10. 10
  11. 11

    Biases in larger populations. حسب Sander W. Keemink (21253563)

    منشور في 2025
    "…<p>(<b>A</b>) Maximum absolute bias vs the number of neurons in the population for the Bayesian decoder. …"
  12. 12
  13. 13
  14. 14

    Network architectures for multi-agents task. حسب Hongjie Zhang (136127)

    منشور في 2025
    "…<div><p>Deep reinforcement learning has achieved significant success in complex decision-making tasks. However, the high computational cost of policies based on deep neural networks restricts their practical application. …"
  15. 15
  16. 16
  17. 17

    Time(s) and GFLOPs savings of single-agent tasks. حسب Hongjie Zhang (136127)

    منشور في 2025
    "…<div><p>Deep reinforcement learning has achieved significant success in complex decision-making tasks. However, the high computational cost of policies based on deep neural networks restricts their practical application. …"
  18. 18

    Scores vs Skip ratios on single-agent task. حسب Hongjie Zhang (136127)

    منشور في 2025
    "…<div><p>Deep reinforcement learning has achieved significant success in complex decision-making tasks. However, the high computational cost of policies based on deep neural networks restricts their practical application. …"
  19. 19
  20. 20