MIT 6.S191: Deep Generative Modeling

Поділитися
Вставка
  • Опубліковано 22 гру 2024

КОМЕНТАРІ • 50

  • @ML-DS-AI-Projects
    @ML-DS-AI-Projects 7 місяців тому +19

    First thank you Alexander and Ava for sharing the knowledge
    After watching these videos, I realized that learning machine learning is not just a skill; teaching is a much bigger skill.

  • @lucawahl8078
    @lucawahl8078 5 місяців тому +10

    I would love to see Lecture 6 on Diffusion Models!

  • @sammyfrancisco9966
    @sammyfrancisco9966 Місяць тому

    Briliant Ava. Explained one of the most complex concept GAN, cycle GAN brilliantly.

  • @ssrwarrior7978
    @ssrwarrior7978 3 місяці тому +5

    I lost from 32:00 onwards about different terms phi, qphi etc meant ...

    • @erdinn
      @erdinn 19 днів тому +1

      i think she meant that if we mix the stochasticity with the latent variables in z we can not backpropagate the weights as the added stochasticity makes the weights untracable. if however you detach the stochasticity from the variables in the latent space you can trace it back because latent varibales and stochasticity is clearly separated.
      its like warming up pasta and the carbonara sauce in separate containers instead of first mixing it and then warming it up

  • @freddybrou405
    @freddybrou405 7 місяців тому +12

    Thank you so much for the course. So much interesting.

  • @Radosteven
    @Radosteven 29 днів тому +1

    Thanks for your course, what I want to ask is whether you can upload the pratice course file or related document to website etc. It maybe help for all of those who want to follow the course and do some practices. Many thanks!

  • @pradyumnanimbkar8011
    @pradyumnanimbkar8011 7 місяців тому +4

    Cool and well-sorted.

  • @erikkim4739
    @erikkim4739 7 місяців тому +4

    so excited for this!

  • @shakshamkarki7061
    @shakshamkarki7061 7 місяців тому +11

    Not a MITian but learning in MIT

  • @akshatchouhan5199
    @akshatchouhan5199 4 місяці тому +1

    What an amazing lecture it was. Really enjoyed it tbh.

  • @anantsinha9637
    @anantsinha9637 3 місяці тому +2

    Does anyone know if we can actually expect Lab 3 to be released or if there's a way to access it?

  • @JCasaraconn
    @JCasaraconn 6 місяців тому +1

    I am curious, regarding the CycleGANs with respect to audio generation, would the output from the model be better if the person creating the input audio were to try and mimic the person the model was trained on as closely as possible? For example, if an Obama impersonator were to supply the input audio, would the output even more closely resemble that of Obama's true voice? The same question would also apply to the video content. If body-language were more closely mimicking the target, does the model generate an output that more closely resembles the target? My hunch is that it would indeed improve the prediction.

  • @ssrwarrior7978
    @ssrwarrior7978 3 місяці тому

    Thank you for the video .. what is Deterministic and Stochastic node?

  • @acya05
    @acya05 5 місяців тому +1

    Brilliant ❤

  • @catalinmanea1560
    @catalinmanea1560 7 місяців тому +3

    awesome, many thanks for your initiative !
    keep up the great work

  • @civilengineeringonlinecour7143
    @civilengineeringonlinecour7143 7 місяців тому +2

    Awesome lecture. 🎉

  • @ahmedelsafty6654
    @ahmedelsafty6654 6 місяців тому

    First thank you Ava for sharing the knowledge.
    I'm not able to understand, why the standard auto-encoder does a deterministic operation?

    • @akshay5011
      @akshay5011 6 місяців тому

      I guess its because once the training is done and as the neural network weights are fixed , as there is no backpropogation etcc.., involved after training , the weights couldn't change and thus for every input you would get the same output as learnt function doesnt involve any probabilistic element.

  • @miroslavdyer-wd1ei
    @miroslavdyer-wd1ei 5 місяців тому

    Couldn't bear to live without tech and AGI.

  • @ssrwarrior7978
    @ssrwarrior7978 3 місяці тому

    what is qphi?

  • @ssrwarrior7978
    @ssrwarrior7978 3 місяці тому

    what is phi?

  • @arpandas2758
    @arpandas2758 7 місяців тому

    thank you for the amazing content, please add the slides for this lecture in the website, its still not there, cheers :)

  • @geoffreyporto
    @geoffreyporto 7 місяців тому

    I have a dataset of 120 images of cell phone photographs of the skin of dogs sick with 12 types of skin diseases, with a distribution of 10 images for each dog.
    What type of Generative Adversarial Network (GAN) is most suitable to increase my dataset with quality and be able to train my DL model? DcGAN, ACGAN, StyleGAN3, CGAN?

    • @TechWithAbee
      @TechWithAbee 7 місяців тому +2

      just try them out

    • @fsaudm
      @fsaudm 7 місяців тому

      Try fine tuning the models with your data

  • @veganath
    @veganath 5 місяців тому

    32:33 *_"and so with ????? they employ this really clever trick that effectively"_* Did any body catch what she was saying here, thanks

  • @miroslavdyer-wd1ei
    @miroslavdyer-wd1ei 5 місяців тому

    Is there such a thing as a Generative Modelling Agency???

  • @newmood24
    @newmood24 Місяць тому

    The website aint working since a few days :/

    • @newmood24
      @newmood24 Місяць тому

      It's back lesgooo

  • @genkideska4486
    @genkideska4486 7 місяців тому +3

    5 mins more let's gooooo

  • @usver911
    @usver911 5 місяців тому

    This proves Plato's idealism is working.

  • @zoomemes4336
    @zoomemes4336 2 місяці тому

    Very rush description.

  • @veganath
    @veganath 5 місяців тому

    28:20 A Joe Biden moment. Does anyone know what she attempted to communicate here, even the closed captions fail to make coherency?

  • @miroslavdyer-wd1ei
    @miroslavdyer-wd1ei 5 місяців тому +10

    OK, I lied. Her hair is AI too.

  • @gapcreator726
    @gapcreator726 7 місяців тому

    Nice amini teaching❤ and your curly hair nice😮

  • @Lima3578user
    @Lima3578user 7 місяців тому

    Spellbound by the lecture, great insights. Is she Indian

    • @dragonartgroup6982
      @dragonartgroup6982 6 місяців тому

      She's Persian

    • @veganath
      @veganath 5 місяців тому

      @@dragonartgroup6982 it just geography.... analogues to padding....

  • @OGaurabless
    @OGaurabless 7 місяців тому

    when gpt 4o lectures :D

  • @miroslavdyer-wd1ei
    @miroslavdyer-wd1ei 5 місяців тому +1

    IMHO commenting about appearance is a bit sexist. Wake up boys!!

  • @miroslavdyer-wd1ei
    @miroslavdyer-wd1ei 5 місяців тому +2

    She's an AI, but her hair is real

  • @SubhashMannava-v8n
    @SubhashMannava-v8n 4 місяці тому +2

    completely lost me in this lecture.

    • @xxyyzz8464
      @xxyyzz8464 2 місяці тому +2

      At what point? Surely the basic AE stuff up front made sense, and at a high level many of the concepts made sense even if there wasn’t a good explanation of how, for example, CycleGAN works.