Adam, AdaGrad & AdaDelta - EXPLAINED!

Sdílet
Vložit
  • čas přidán 7. 09. 2024

Komentáře • 12

  • @Firestorm-tq7fy
    @Firestorm-tq7fy Před rokem +3

    Very very good explaination! Besides your little accent, it’s top quality.
    I have been searching for a decent explain-video for a long time. U nailed it! Strongly underrated video 👌🏼

  • @hreedishkakoty6771
    @hreedishkakoty6771 Před 4 měsíci

    I have tried your python notebook for this video from Github. Excellent work. Thanks for making it available. However, I can see that adam is not really working best for the linear function you have created. I was wondering, at what point of non-linear complexity does adam start showing better results over other optimizers. Would be great to have this discussion.

  • @raghavendra6978
    @raghavendra6978 Před rokem +2

    superb explaination :)

  • @yameenvinchu6255
    @yameenvinchu6255 Před rokem +3

    Keep going quality content

  • @georgeli4538
    @georgeli4538 Před rokem +1

    Excellent video

  • @dhiraj223
    @dhiraj223 Před 2 lety +2

    Awesome 😎 Will try 🤘🤘

  • @user-hn3pu2ci5f
    @user-hn3pu2ci5f Před rokem +1

    Great explanation bro😊

  • @crusadermic-41
    @crusadermic-41 Před 10 měsíci

    superb content buddy... keep on uploading

  • @aftermancz
    @aftermancz Před 2 měsíci

    Nice, thx :D

  • @tollsimyfpv
    @tollsimyfpv Před 9 měsíci

    Awesome content!

  • @sumeetmishra9115
    @sumeetmishra9115 Před 2 lety +1

    Good content

  • @pnachtwey
    @pnachtwey Před 3 měsíci

    I have found that alpha_t gets too big too quickly so that learning slows to a crawl. A simple line search works better.