Site Tools


Hotfix release available: 2025-05-14b "Librarian". upgrade now! [56.2] (what's this?)
Hotfix release available: 2025-05-14a "Librarian". upgrade now! [56.1] (what's this?)
New release available: 2025-05-14 "Librarian". upgrade now! [56] (what's this?)
Hotfix release available: 2024-02-06b "Kaos". upgrade now! [55.2] (what's this?)
Hotfix release available: 2024-02-06a "Kaos". upgrade now! [55.1] (what's this?)
New release available: 2024-02-06 "Kaos". upgrade now! [55] (what's this?)
Hotfix release available: 2023-04-04b "Jack Jackrum". upgrade now! [54.2] (what's this?)
Hotfix release available: 2023-04-04a "Jack Jackrum". upgrade now! [54.1] (what's this?)
New release available: 2023-04-04 "Jack Jackrum". upgrade now! [54] (what's this?)
Hotfix release available: 2022-07-31b "Igor". upgrade now! [53.1] (what's this?)
Hotfix release available: 2022-07-31a "Igor". upgrade now! [53] (what's this?)
New release available: 2022-07-31 "Igor". upgrade now! [52.2] (what's this?)
New release candidate 2 available: rc2022-06-26 "Igor". upgrade now! [52.1] (what's this?)
New release candidate available: 2022-06-26 "Igor". upgrade now! [52] (what's this?)
Hotfix release available: 2020-07-29a "Hogfather". upgrade now! [51.4] (what's this?)
realisation_som

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
realisation_som [2025/12/18 17:46]
47.128.30.165 old revision restored (2025/11/27 23:35)
realisation_som [2026/01/05 00:30] (current)
177.42.97.180 old revision restored (2025/10/22 16:41)
Line 32: Line 32:
 Avec Θ(t) la fonction de voisinage et L(t) le taux d'apprentissage : Avec Θ(t) la fonction de voisinage et L(t) le taux d'apprentissage :
  
-Θ(t) = exp( -dist² / 2σ²(t)) \\+Θ(t) = exp( -dist / 2σ²(t)) \\
 et \\ et \\
 L(t) = L0 * exp(-t / λ) \\ L(t) = L0 * exp(-t / λ) \\
 +
 +<note important>Certains articles parlaient d'une fonction de voisinage telle que ci-dessous : \\
 +Θ(t) = exp( -dist² / 2σ²(t)) \\
 +Mettre dist au carré a -dans mon cas- détruit le maillage, les neurones voisins du neurone gagnant se déplacaient trop à chaque itération ne permettant pas de converger vers une position correcte.</note>
 +
  
 ==== Expérience ==== ==== Expérience ====
realisation_som.1766076408.txt.gz · Last modified: 2025/12/18 17:46 by 47.128.30.165