Showing 1 - 20 results of 3,785 for search '(((( learning using decrease ) OR ( _ linear decrease ))) OR ( a larger decrease ))', query time: 0.54s Refine Results
  1. 1

    A Locally Linear Dynamic Strategy for Manifold Learning. by Weifan Wang (4669081)

    Published 2025
    “…For 10-30% noise, where the Hebbian network employs a local linear transform, learning selectively increases signal direction alignment (blue) while simultaneously decreasing noise direction alignment (orange). …”
  2. 2
  3. 3
  4. 4

    Based on our time series data(first from the left), the visualizations of linear residual predictions under different decimation rates (next three) show that as the decimation rate decreases, the range of residual variations also becomes smaller. by Hua Huo (1818133)

    Published 2025
    “…<p>Based on our time series data(first from the left), the visualizations of linear residual predictions under different decimation rates (next three) show that as the decimation rate decreases, the range of residual variations also becomes smaller.…”
  5. 5
  6. 6
  7. 7
  8. 8
  9. 9

    STL Linear Combination Forecast Graph. by Xiangjuan Liu (618000)

    Published 2025
    “…<div><p>This study constructs a multi-stage hybrid forecasting model using hog price time series data and its influencing factors to improve prediction accuracy. …”
  10. 10
  11. 11
  12. 12
  13. 13
  14. 14

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

    Published 2025
    “…(<b>B</b>) Minimum and maximum bias in a long 1D array with rectified cosine tuning. Bias expressed in terms of the distance between neurons in a linear population of equally spaced neurons. …”
  15. 15
  16. 16
  17. 17

    <b>Supporting data for manuscript</b> "<b>Voluntary locomotion induces an early and remote hemodynamic decrease in the large cerebral veins</b>" by Kira Shaw (18796168)

    Published 2025
    “…The locomotion values (traces and metrics) are in arbitrary units with larger integers representing a greater displacement of the spherical treadmill, the hemodynamic (Hbt) values (traces and metrics) are a percentage change from the normalised baseline (prior to stimulus presentation), and the corresponding time series vector is presented in seconds. …”
  18. 18
  19. 19
  20. 20