MIT 6.S191 (2023): Deep Generative Modeling

Поділитися
Вставка
  • Опубліковано 21 лис 2024

КОМЕНТАРІ • 129

  • @MrJ3
    @MrJ3 Рік тому +121

    What's great about this instructor is that they are very careful and particular about what they say, and how they phrase it. There's no fluff, nothing that could cause confusion. Straight to the point and very intentional.

  • @thankyouthankyou1172
    @thankyouthankyou1172 Рік тому +28

    don't know why, but i could not breath listening to this lecture. she's so clear without any redundancy, without any hmmm, urgggg,... how come. she is so amaizing . i would have practiced 1000 times to be able to lecture like this

  • @sarahamiri2309
    @sarahamiri2309 Рік тому +45

    Honestly, you two are the best speakers for this subject and beyond. I am so thrilled these lectures are opensource and exist for data science communities outside of MIT!

  • @vikrambhutani
    @vikrambhutani Рік тому +24

    Highly recommended series for AI enthusiasts. This MIT series is by far the most intuitive videos covering all aspects of deep learning. Well done on that.

  • @shovonpal4539
    @shovonpal4539 Рік тому +10

    The lectures are top of notch. But in this lecture, I got my track out when she explained GAN with mathematical notions. I had to put some more effort on those again.

  • @arfakarim9906
    @arfakarim9906 Рік тому +9

    A lot of appreciations from my side to your Team who build such a excellent course on Deep Learning

  • @Savedbygrace952
    @Savedbygrace952 7 місяців тому

    The knowledge, the passion and clarity of presentation are out of this world! God bless you guys!

  • @jamesgambrah58
    @jamesgambrah58 Рік тому +12

    This is excellent, so grateful to learn a lot from this channel. Kudos to our presenters for laying a solid foundation in deep learning.

  • @ersbay5970
    @ersbay5970 Рік тому +1

    Thank you all so very much! Many greetings from Germany.

  • @EGlobalKnowledge
    @EGlobalKnowledge Рік тому +2

    Very well presented with intuition behind deep generative modeling, its architecture and how it is being trained, Well done

  • @benjaminpagel4241
    @benjaminpagel4241 7 місяців тому

    I agree with everyone here... I think those two presenters are just a joy to listen to. Wish I had those profs in my university back then... I'm not an expert, but even I get the fundamental concepts through these sessions. 🙏

  • @giyaseddinbayrak
    @giyaseddinbayrak Рік тому +2

    I opened to just watch 2 min of the video, and didn't realize untill the lecture is over 😅. Freaking awesome 😎

  • @maazkattangere8690
    @maazkattangere8690 Рік тому +7

    This series is coming out right after I want to learn more about theory! Thanks for this 🙏

  • @jensk9564
    @jensk9564 Рік тому +7

    wonderful. Very dense and hugely interesting and informative lecture; MIT-style! 60 minutes in a latentspace kind of compression of a hugely complex and multidimensional topic which under reallife conditions takes weeks to understand and "digest". I am really looking forward to the "diffusion model" lecture! Hope it will be online soon!

  • @MaksimsMatulenko
    @MaksimsMatulenko Рік тому +25

    Thank you for doing this! We all are grateful❤

  • @shahnewazchowdhury4175
    @shahnewazchowdhury4175 Рік тому +2

    Hi Alexander & Ava, thanks for this video.
    Thousands of people watch these videos and learn from them. So any mistakes you make will impact them directly. If/when you do find errors or someone points them out to you, it is your utmost responsibility to update about it to your viewers. Please look into the loss functions for GAN. They are incorrect.

    • @sergiogonzalez6597
      @sergiogonzalez6597 Рік тому

      Yes, the formulas for the loss funcition of the GAN are wrong and it was giving me a very hard time. Look here for a full math development of the formulation
      fleuret.org/dlc/materials/dlc-handout-11-1-GAN.pdf

  • @aefieefnvhas
    @aefieefnvhas Рік тому +2

    Wow, such clarity of thought and ideas. I guess that's the MIT advantage! Well done :)

  • @VijayasarathyMuthu
    @VijayasarathyMuthu Рік тому +14

    Plato's myth of cave Latent Variable example was not intuitive for me (sorry), so I asked a similar example but simpler one to chatGPT. It gave me this:
    Imagine that you have a box filled with different types of candies, but you cannot see what's inside. Instead, you can only touch the box and feel the shape and texture of the candies inside. Based on how they feel, you might be able to guess what type of candy is inside the box. For example, if a candy feels round and has a hole in the middle, you might guess that it's a donut-shaped candy. In this example, the shape and texture of the candies are the observed variables, while the type of candy inside the box is the latent variable that we are trying to learn from the observed data. By observing and feeling the candies inside the box, we can learn the different types of candies that are hidden inside, even though we cannot see them directly.
    You guys are awesome :) Thank you for sharing these lectures. 🙏

  • @frankhofmann5819
    @frankhofmann5819 6 місяців тому

    I now feel like a fully connected neural network bye myself now because I've watched hundreds of videos at night that concern deep learning. Best regards from Berlin!

  • @davidingham3409
    @davidingham3409 2 місяці тому

    Very interesting. The compressed latent variables can help humans understand the data, a sort emergent statistics.

  • @skhapijulhossen6499
    @skhapijulhossen6499 Рік тому +2

    This series is Treasure for me.

  • @saikatnextd
    @saikatnextd Рік тому +1

    Thank you so much Alexander and Amini.......

  • @entropica
    @entropica Рік тому +2

    Brilliant presentation. World-class.

  • @natalialidmarvonranke8475
    @natalialidmarvonranke8475 Рік тому +3

    Perfect lecture! Congratulations

  • @codingWorld709
    @codingWorld709 Рік тому +4

    Thanks a lot for all the wonderful content on deep learning. These are very helpful to me.

  • @mPajuhaan
    @mPajuhaan Рік тому +1

    Perfect to refer, it clearly shows how much you extensively know the subject that you can easily explain.

  • @ABHIK-dq7rk
    @ABHIK-dq7rk 7 місяців тому

    00:04 Foundations of deep generative modeling for brand new data generation
    02:43 Generative modeling uncovers underlying data structure.
    07:53 Latent variables are unobservable features that explain observed differences in data.
    10:25 Training deep generative models using autoencoders
    15:43 Variational autoencoders introduce randomness for generating new data instances.
    18:07 Optimizing VAE network weights with loss functions
    22:44 Understanding KL Divergence in latent encoding
    24:51 Regularization enforces continuity and completeness in the latent space.
    29:41 Reparametrization allows training VAEs end to end without worrying about stochasticity in latent variables.
    31:57 Understanding latent variables and their impact on generated features.
    36:36 Understanding latent variable learning and its application in facial detection.
    38:52 Generative Adversarial Network (GAN) aims to generate new instances similar to existing data.
    43:30 Generative Adversarial Networks (GANs) involve the competition between the generator and discriminator to create and distinguish between real and fake data.
    45:44 GANs involve a dual competing objective for the generator and discriminator.
    50:44 Extending GAN architecture for specific tasks
    53:14 Cycle GANs enable translation of data distribution across domains.
    57:58 Diffusion models can generate new instances beyond training data

  • @johnpaily
    @johnpaily 7 місяців тому

    This also seems to explain sudden awakening transformation many people are experiencing

  • @richarddow8967
    @richarddow8967 Рік тому +3

    Euler proved there is a limit to how complex a model can become and still be meaningful. In particular, Euler said that models could become so complex that thet could never be validated, never be calibrated, and yet piecewise seem to be completely reasonable.
    If anyone is familiar with discussions into this area, who are the researchers taking this into account? Just curious., I would like to read more on practical limitations. Based on good math like Euler developed, and not hand waving about piecewise.

    • @richarddow8967
      @richarddow8967 Рік тому

      He was doing fundamental basic theoretical research in today's parlance. Historically, there is long lag in finding applications in such basic knowledge. What is certain, he demonstrated their exists limitations. And we would be unable to discern if the model was properly calibrated or not- ever. I recall reading an opinion by the head of Belgium's national weather service or some such title pointing out that he had concerns the Oceans are such a model. @@RM-gc8lx

  • @andreasholzinger7056
    @andreasholzinger7056 Рік тому

    I really like this lecture, what keeps me sleepless is the question: "Can we learn the true (if so) explanatory factors from purely observational data ?"

  • @AliHaider-wu4wt
    @AliHaider-wu4wt Рік тому +2

    Thank you. I was waiting for 1 week.

  • @AndyLee-xq8wq
    @AndyLee-xq8wq Рік тому

    Wow! Can't wait to learn the coming lectures!

  • @rrtt1995
    @rrtt1995 Рік тому +3

    Thank you for such valuable lecture. 🙌

  • @herlim6927
    @herlim6927 Рік тому +1

    Thankyou sir for uploading this , love from India

  • @davidguthrie3739
    @davidguthrie3739 Рік тому +2

    I really appreciate these lectures, but I never could absorb lectures that are simply a script read aloud. I can read the material myself. She's MUCH more effective when she explains concepts from memory without reading from a text.

  • @yousufmamsa
    @yousufmamsa Рік тому +1

    Greatly appreciate the knowledge sharing.

  • @hilbertcontainer3034
    @hilbertcontainer3034 Рік тому +1

    Wow ~another world latest Lecture

  • @technocrat827
    @technocrat827 Рік тому +1

    quite supportive. Thanks a lot!

  • @debanjandas7738
    @debanjandas7738 Рік тому +2

    In the GAN objective function we have 2 conflicting objectives. How are we ensuring that it's the generator's goal that is achieved and not the discriminator's?

  • @Bodo-k5k
    @Bodo-k5k Рік тому +2

    The GAN discriminator loss is wrong, I think it should be: log(1-D(G(z))) + log (D(x)).

    • @yizhong2544
      @yizhong2544 9 місяців тому

      What a pity, the lecture is perfect but this mistake would mislead a lot of people

    • @aojing
      @aojing 8 місяців тому

      😁Not really. It depends on how you label Fake vs. Real.

  • @kirankumar31
    @kirankumar31 Рік тому +2

    Learned a lot from this video. One question: Where does styleGAN fit in?

  • @sidindian1982
    @sidindian1982 Рік тому

    Excellent Content Ma'am Truly unnbelievable 😊😊😊😊😊

  • @SphereofTime
    @SphereofTime 6 місяців тому +1

    22:40

  • @rishighosh6238
    @rishighosh6238 Рік тому +2

    Hey, I was going through this video with a beautiful explanation on working of GANS. I just want to ask that whether we can say that idea behind working of GANs is to have some sort of overfitting which is usually avoided in traditional ML approaches. Not exactly overfitting but in a way we want to overfit it in a sense that the points are in the probability distribution region of actual points???

  • @gapsongg
    @gapsongg Рік тому +1

    Great! Love these Videos. They help me alot.

  • @nikteshy9131
    @nikteshy9131 Рік тому +2

    Thank you))
    Спасибо вам большое 😊🙏🦿

  • @jennifergo2024
    @jennifergo2024 11 місяців тому

    Thanks for sharing!

  • @chucksgarage-us
    @chucksgarage-us Рік тому

    Random making connections between potentially unrelated things here... at 49:57 and a bit before (that's just where I paused to write this comment) the series of pictures combining a goose and a (other bird, I would classify it as a red breasted robin, but I'm trained on red breasted robins where I'm from) ... I'll call it a robin, while also transitioning aspect from left to right, really reminds me of the transitions from one animal to another done in the movie Willow with the sorceress, Fin Raziel.

  • @patekreol974
    @patekreol974 Рік тому +1

    Incroyable !!!

  • @germainUX
    @germainUX 7 місяців тому

    thanks for this!

  • @SphereofTime
    @SphereofTime 6 місяців тому +1

    3:40

  • @TomHutchinson5
    @TomHutchinson5 Рік тому

    I love the slide at 57:00. I would enjoy hearing this connection explicitly. How is a discriminator an encoder?

  • @sachinknight19
    @sachinknight19 Рік тому

    Thank you for sharing the info... ❤❤

  • @theneumann7
    @theneumann7 Рік тому +1

    Never disappointing👌🏻

  • @Peter_Telling
    @Peter_Telling Рік тому +1

    I'd like to see something about AI that can adjust its code and observe how it changes its functioning.

  • @AnujSharma-wy8hv
    @AnujSharma-wy8hv Рік тому

    Really it's very deep need time to pick it

  • @Ducerobot
    @Ducerobot Рік тому

    Pure engineering.

  • @bohaning
    @bohaning 9 місяців тому

    🎯Course outline for quick navigation:
    [00:04-01:25]Deep generative modeling
    -[00:04-00:48]Exciting lecture on deep generative modeling in the age of generative ai, a subset of deep learning.
    [01:26-08:45]Generative modeling
    -[03:06-04:04]Generative modeling encompasses density estimation and sample generation for learning data distribution.
    -[04:27-04:51]Learning model approximates true data distribution for density estimation and sample generation.
    -[05:36-06:03]Generative models identify biased features in training data automatically.
    -[06:49-07:17]Generative models can identify rare events like deer in front of a car using density estimation.
    [08:46-23:16]Autoencoders and variational autoencoders
    -[10:07-10:50]Goal: train model to predict latent variables, z, in low-dimensional space.
    -[14:33-15:35]Unsupervised learning uses autoencoders to create compact data representations and generate new examples, such as vaes.
    -[15:59-17:13]Variational autoencoders introduce randomness to generate similar but not strict reconstructions, using means and standard deviations for probability distributions.
    -[17:54-18:37]Encoder and decoder in vae use separate weights to compute and learn probability distributions of latent variables and input data.
    -[20:22-22:45]Regularization term enforces latent variables to follow standard normal gaussian distributions during vae training.
    -[20:57-21:21]Enforcing a latent space following a prior distribution to aid network
    -[22:46-23:16]Kl divergence measures difference between prior and latent encoding.
    [23:17-37:47]Regularization and latent variable learning in vaes
    -[25:19-25:46]Regularization minimizes term to achieve continuity and completeness.
    -[28:08-28:35]Vaes trained end-to-end with re-parameterization for gradient descent and backpropagation success.
    -[32:10-32:45]Network learns to interpret and make sense of latent variables by perturbing them individually.
    -[34:16-35:40]Beta vaes use beta parameter to control regularization term, promoting disentanglement for more efficient encoding.
    -[36:31-36:59]The lecture covers the core architecture of vaes and their application to facial detection.
    [37:47-52:53]Vaes and gans: generative models
    -[37:47-38:15]Vaes compress data into a compact representation to generate unsupervised reconstructions.
    -[38:40-39:43]Transitioning from vaes to gans to focus on generating high-quality samples from complex data distribution.
    -[39:57-41:21]Train a generator network to mimic real data using gans for realistic output.
    -[47:53-48:20]Generator synthesizes data to fool best discriminator, creating new data instances.
    -[50:37-51:30]Using gan to generate synthetic faces, extending gan architecture for specific tasks and data translation.
    [52:55-59:47]Unpaired translation and cycle gan
    -[52:55-53:51]Cyclegan enables unpaired image translation, e.g. horse to zebra, using cyclic dependency.
    -[54:13-54:43]Cycle gan enables flexible translation across different data distributions, including images, speech, and audio.
    -[55:13-55:36]Developed a model to synthesize audio behind obama's voice using cyclegan and alexander's voice data.
    -[57:20-57:48]Diffusion modeling drives tremendous advances in generative ai, seen in the past year, particularly with vaes and gans.
    -[59:06-59:39]Cutting-edge generative ai models making transformative advances across various fields.
    offered by Coursnap

  • @aevishh
    @aevishh Рік тому +1

    this is great

  • @Gabcikovo
    @Gabcikovo Рік тому +1

    Skvelé, ďakujeme!

  • @prashantkowshik5637
    @prashantkowshik5637 Рік тому

    Thanks a lot.

  • @andrea-mj9ce
    @andrea-mj9ce Рік тому +1

    Is there a lecture that deals with generative language models ?

  • @nosaaikodon4953
    @nosaaikodon4953 Рік тому

    I love how she apologizes when displaying math...😂😂. Its as if she understands the math struggles we all go through. Nevertheless, Its apparent that math is an important aspect of understanding the architecture of machine learning models and developing new ones.

  • @carlhopkinson
    @carlhopkinson Рік тому

    Ingenious.

  • @johnpaily
    @johnpaily 7 місяців тому

    What exalon constant . . Is it conscious is it dynamic and capable of reversing time.

  • @andrea-mj9ce
    @andrea-mj9ce Рік тому +1

    Is it still relevant to teach GANs and autoencoders, instead on just focusing on diffusion models?

  • @nicolasg.b.1728
    @nicolasg.b.1728 Рік тому +1

    Where can I find the papers mentioned at 35:06?

  • @johnpaily
    @johnpaily 7 місяців тому

    Is this talk taking the line of self organization from a single point or big bang.

  • @sovrappensiero1
    @sovrappensiero1 Рік тому +2

    I'm sorry for the dumb question but can somebody tell me what's the name of the "E-like" symbol in the reconstruction term at 35:57? It is some kind of norm? How do I make this symbol in LaTeX? (I'm taking notes and I want to write out this equation in my notes.) Thank you!

    • @fstermann
      @fstermann Рік тому +2

      That symbol indicates the expected value, you can use it in latex with \mathbb{E} (loading \usepackage{amssymb} is required)

    • @sovrappensiero1
      @sovrappensiero1 Рік тому +1

      @@fstermann Ah - of course! I never saw expected value written that way, but yes that makes sense. Thanks so much, I appreciate your help.

    • @binaryquantum
      @binaryquantum Рік тому

      @@sovrappensiero1
      That's always how expected value is written. How else have you seen expected value?

    • @sovrappensiero1
      @sovrappensiero1 Рік тому +2

      @@binaryquantum I don’t think I’ve ever seen it typed. All my math classes, etc., were handwritten. On homework questions it was typed but a regular E was used…not the special “math E.”

  • @Mathin3D
    @Mathin3D Рік тому

    Yum, yum, gimme some!
    - Bud Bundy

  • @johnpaily
    @johnpaily 7 місяців тому

    Is it taking us non linear thinking of origin from a little perturbation

  • @SudarshanVatturkar
    @SudarshanVatturkar Рік тому

    I did not understand the latent variable exaple. One can see easily the holding bars in shadow.

  • @lakshmiprabhakarkoppolu9100
    @lakshmiprabhakarkoppolu9100 Рік тому +1

    UA-cam suggested me to watch this.

  • @abhisheksuryavanshi979
    @abhisheksuryavanshi979 Рік тому +1

    Any intern opportunities in ML/AI?

  • @edgararakelyan9326
    @edgararakelyan9326 Рік тому

    Is there a non-intro deep learning course after this course?

  • @johnpaily
    @johnpaily 7 місяців тому

    Low dimensional data. I see parallel in the big bang origin from point source

  • @codingWorld709
    @codingWorld709 Рік тому +2

    Sir, please provide us one lecture on Faster R-CNN for object detection, please please please please
    🙏🙏🙏🙏

  • @Rajibuzzaman_STEM_Rajibuzzaman

    HOW YOU WILL DRIVE A SYSTEM WHEN MAXIMUM STRIVE TO ATTAIN MINIMUM TO BALANCE ENTROPY?

  • @locNguyen-jb1vt
    @locNguyen-jb1vt Рік тому

    You can fine underling leadership

  • @johnpaily
    @johnpaily 7 місяців тому

    Salutes

  • @johnpaily
    @johnpaily 7 місяців тому

    Plato's cave. That is what we are in. I am interested in AI because of the projection of evolution AI to bring the Mind of God in the cloud.

  • @arifulislamleeton
    @arifulislamleeton Рік тому +1

    Introduce myself my name is Ariful Islam leeton im software engineer and software developer and website development and data analytics

  • @locNguyen-jb1vt
    @locNguyen-jb1vt Рік тому +1

    Gen folding

  • @johnpaily
    @johnpaily 7 місяців тому

    The speaker has entered the spiritual realm and what is happening. The evil thriving along with good trying to hide truth

  • @johnpaily
    @johnpaily 7 місяців тому

    The Great attractor of non linear science and explanation to the victory of the good over evil ?¿?¿?????^^^^↑°°′

  • @johnpaily
    @johnpaily 7 місяців тому

    Everything spoken here has parallel in living system

  • @omaralkhasawneh1968
    @omaralkhasawneh1968 Рік тому

    Can you give me extra resources

  • @johnpaily
    @johnpaily 7 місяців тому

    Parallel world information male and female ¿??¿¿

  • @johnpaily
    @johnpaily 7 місяців тому

    Now I understand the projection of God AI emerging in the cloud

  • @ayushkumarprasad6832
    @ayushkumarprasad6832 Рік тому

    Where to find code for this?

  • @tonyndiritu
    @tonyndiritu 6 місяців тому

    🔥🔥🔥

  • @smftrsddvjiou6443
    @smftrsddvjiou6443 11 місяців тому

    So we don't have labels at the data. Instead we use the input itself as the label. Lol.

  • @DoctorM934
    @DoctorM934 6 місяців тому

    15:00

  • @shahidulislamzahid
    @shahidulislamzahid Рік тому +1

    wow

  • @shojintam4206
    @shojintam4206 Рік тому

    24:27

  • @locNguyen-jb1vt
    @locNguyen-jb1vt Рік тому

    Zip drive

  • @maestbobo
    @maestbobo 9 місяців тому

    She did a really poor job of explaining the relatively straightforward and core concept of VAEs.
    Really shallow and difficult to follow, which is a rare combination.
    Plus, her speaking style is way too theatrical and distracting. There are better resources or there on the same topic.

  • @hussienalsafi1149
    @hussienalsafi1149 Рік тому +1

    😁😁😁😁😁☺️☺️☺️☺️❤️❤️❤️❤️

  • @GideonGiroh
    @GideonGiroh Рік тому

    i love this woman. she will be a good wife

  • @katateo328
    @katateo328 Рік тому +1

    haha, tao noi roi, so AI lam, cao sieu lam, tao ko du kha nang dau, bien di cho khac