Deepia
Deepia
  • Видео 6
  • Просмотров 106 546
Contrastive Learning with SimCLR | Deep Learning Animated
To try everything Brilliant has to offer-free-for a full 30 days, visit brilliant.org/Deepia .
You’ll also get 20% off an annual premium subscription.
In this video you will learn the basics of contrastive learning, and how these approaches were used successfully in SimCLR.
If you want to know more about contrastive learning, you should definitely read the following papers:
- FaceNet: A Unified Embedding for Face Recognition and Clustering arxiv.org/abs/1503.03832
- Deep metric learning using Triplet network arxiv.org/abs/1412.6622
- A Simple Framework for Contrastive Learning of Visual Representations arxiv.org/abs/2002.05709
And for self-supervised learning in general, I strongly recommend t...
Просмотров: 4 066

Видео

Variational Autoencoders | Generative AI Animated
Просмотров 34 тыс.2 месяца назад
In this video you will learn everything about variational autoencoders. These generative models have been popular for more than a decade, and are still used in many applications. If you want to dive even deeper into this topic, I would suggest you read the original paper from Kingma, and an overview he wrote later on: - Auto-Encoding Variational Bayes arxiv.org/abs/1312.6114 - An Introduction t...
Latent Space Visualisation: PCA, t-SNE, UMAP | Deep Learning Animated
Просмотров 46 тыс.3 месяца назад
In this video you will learn about three very common methods for data dimensionality reduction: PCA, t-SNE and UMAP. These are especially useful when you want to visualise the latent space of an autoencoder. If you want to learn more about these techniques, here are some key papers: - UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction arxiv.org/abs/1802.03426 - Stochast...
Autoencoders | Deep Learning Animated
Просмотров 13 тыс.5 месяцев назад
In this video, we dive into the world of autoencoders, a fundamental concept in deep learning. You'll learn how autoencoders simplify complex data into essential representations, known as latent spaces. We'll break down the architecture, training process, and real-world applications of autoencoders, explaining how and why we use the latent space of these models. We start by defining what an aut...
CNN Receptive Field | Deep Learning Animated
Просмотров 6 тыс.5 месяцев назад
In this video, we explore the critical concept of the receptive field in convolutional neural networks (CNNs). Understanding the receptive field is essential for grasping how CNNs process images and detect patterns. We will explain both the theoretical and effective receptive fields, highlighting how they influence network performance and design. We start by defining the receptive field and its...
Convolutional Neural Networks | Deep Learning Animated
Просмотров 4 тыс.6 месяцев назад
In this video we will dive into the inner workings of Convolutional Neural Networks. These networks are one of the most widely used basis in Deep Learning, and are at the origin of the rapid growth of this field around 10 years ago. We will first see how the convolution operation works, then how it integrates into a neural network architecture. We will also see some operations specific to CNNs,...

Комментарии

  • @authenticallysuperficial9874
    @authenticallysuperficial9874 10 часов назад

    Audio comes out from under water at 2:09 btw

    • @Deepia-ls2fo
      @Deepia-ls2fo 3 часа назад

      Thank you, I had some issues with copyrighted music which led to RUclips removing it but also degrading the audio...

  • @authenticallysuperficial9874
    @authenticallysuperficial9874 10 часов назад

    Thanks!

  • @jchealyify
    @jchealyify День назад

    A really solid explanation. Well done! You are a wonderful communicator and your visualizations are top notch. I do have one very small suggestion that might help. When sweeping through hyperparameters and showing their effect on the embedding it can be helpful to correct a bit of the stochastic nature of layout. When transitioning between your embeddings in low dimensions it can be helpful to a user for you to run a procrustes algorithm on the two embeddings. This will just flip, rotate and scale the point clouds to be best aligned. It really helps users see consistent patterns as hyperparameters change without altering the embedding in any meaningful ways. Keep up the fantastic work. I'll definitely be following your channel.

  • @samuelschonenberger
    @samuelschonenberger 2 дня назад

    Watching this while my first VAE is training

  • @hichamaniba9041
    @hichamaniba9041 2 дня назад

    Thank you , still looking for VAE variants videos

  • @Polycephalum-AI
    @Polycephalum-AI 2 дня назад

    Dude awesome video! I did a similar one a few days ago.

  • @EigenA
    @EigenA 3 дня назад

    Great video. What is your educational background?

    • @Deepia-ls2fo
      @Deepia-ls2fo 2 дня назад

      Thanks ! Bachelor in math, bachelor in computer science, master in AI/ML, currently doing a PhD in applied maths and deep learning

    • @EigenA
      @EigenA 2 дня назад

      @ legendary. Good luck on the PhD! I’m 3rd year EE PhD student, you have phenomenal content. Looking forward to watching your channel grow.

  • @EigenA
    @EigenA 3 дня назад

    Great video

  • @chcyzh
    @chcyzh 3 дня назад

    Thank you very much! It's pretty clear

  • @alexmattyou
    @alexmattyou 4 дня назад

    I can visualize autoencoders better now. Keep doing animations. My brain just encodes animation data easily And I need to decode them in exam paper / seminar

  • @beowolx
    @beowolx 8 дней назад

    wow, that was such a good video! Thanks for that

  • @pritamswarnakar6855
    @pritamswarnakar6855 8 дней назад

    I am sharing this and will endorse people in my contact to subscribe, as exaplaining this "not so common" topics, with this much ease is really a art and this efforts of yours deserves a great amount of respect and appreciation.

  • @EdeYOlorDSZs
    @EdeYOlorDSZs 8 дней назад

    top tier video!

  • @shashankjha8454
    @shashankjha8454 9 дней назад

    do u use manim for animations ?

    • @Deepia-ls2fo
      @Deepia-ls2fo 9 дней назад

      @@shashankjha8454 Yes indeed!

  • @hannes7218
    @hannes7218 10 дней назад

    good stuff! keep it going

  • @rishidixit7939
    @rishidixit7939 11 дней назад

    At 7:45 why is the assumption for p(z) as a Normal Distribution important ? Without that are further calculations not possible ? At 8:01 why is the posterior assumed to be Gaussian ?

    • @Deepia-ls2fo
      @Deepia-ls2fo 11 дней назад

      @@rishidixit7939 Hi again, indeed further calculations are intractable without assuming both the prior and the posterior to be Gaussian. Some other research works have replaced these assumptions by other well known distributions such as mixtures of Gaussians, which results in another training objective.

  • @rishidixit7939
    @rishidixit7939 11 дней назад

    For the applications like Domain Adaptation and Image Colorization how does the loss function look like for an AutoEncoder ? Also you said that the MSE Loss is used but then in that case a trivial solution exists where the image is copied pixel by pixel and the Network Learns Nothing. How is that problem taken care of ?

    • @Deepia-ls2fo
      @Deepia-ls2fo 11 дней назад

      @@rishidixit7939 Hi, I'm not familiar with those two tasks, but for Image Colorization an MSE would probably do just fine ? For preventing the Network to simply copy the image pixel by pixel, we have the bottleneck layer! Remember that this layer has a lot fewer neurons than there are pixels, so you can't just "copy" the values :)

  • @toninikoloski110
    @toninikoloski110 11 дней назад

    Amazing wow!

  • @timewasting7574
    @timewasting7574 12 дней назад

    3:25 - 6:20 is so distracting. Just assume your audience knows these. No need to conform your target group to general public. Just assume senior-year undergraduate please.

  • @virgenalosveinte5915
    @virgenalosveinte5915 12 дней назад

    Your channel is astounding brobro thank you

  • @Darkev77
    @Darkev77 15 дней назад

    I SWEAR I was trying to understand BYOL just a few minutes and was struggling, then this video came up, THANK YOU! CAN'T WAIT! Also, please do SwaV as well!

  • @dhurbatripathi6924
    @dhurbatripathi6924 19 дней назад

    when's next video. Love these visualizations!

    • @Deepia-ls2fo
      @Deepia-ls2fo 19 дней назад

      @@dhurbatripathi6924 Thanks ! By the end of November!

  • @study-dogloper
    @study-dogloper 20 дней назад

    The GOAT

  • @muhammed2174
    @muhammed2174 24 дня назад

    You're a master at your craft, it is a testament to your studies!

  • @Aften_ved
    @Aften_ved 25 дней назад

    4:10 Latent Space.

  • @nitroseeks
    @nitroseeks 27 дней назад

    You are amazing. The visualisations in your lectures are top notch

  • @ProgrammingWithJulius
    @ProgrammingWithJulius 27 дней назад

    Great video as always

  • @AlëMontoya-b2w
    @AlëMontoya-b2w 27 дней назад

    Very nice video , please continue with this wonderfull work ! thanks a lot.

  • @jawaharbabuadapa
    @jawaharbabuadapa 27 дней назад

    youtube is not performing well, the view count for this video suggests a change is needed for its CEO

  • @cs-cs4mj
    @cs-cs4mj 29 дней назад

    hey, so well explained thanks for the video!! really nailed those animations as well, would be cool to make a video on adam/rmsprop as well, i have a hard time properly understanding why they work. anyway much love to you my friend

  • @user-ht4rw5wp4x
    @user-ht4rw5wp4x 29 дней назад

    How does the model/programmer know if two pictures are a positive or negative pair without labels?

    • @Deepia-ls2fo
      @Deepia-ls2fo 29 дней назад

      @@user-ht4rw5wp4x Well you have several ways of defining the pairs, for instance you create positive pairs with data augmentation as in SimCLR !

  • @adamskrodzki6152
    @adamskrodzki6152 29 дней назад

    Amazing how high quality your videos are. Hope you will have much more subscribers soon enough. This quality definetly deserve that.

  • @AbideByReason
    @AbideByReason Месяц назад

    Really nice video. Love your presentation style, so clean and well explained!

  • @babatundeonabajo
    @babatundeonabajo Месяц назад

    This is a really good video, and the animations are top-notch. I feel this video is good not just for those learning about AI but also those learning Statistics.

  • @deror007
    @deror007 Месяц назад

    How exactly in the original contrast loss, does y = 0 in the positive case and the y=1 in the negative case? In addition what is y representing here? 6:27

    • @deror007
      @deror007 Месяц назад

      Is it just a positive and negative pair label which forces the contrastive loss to focus on the positive and negative metrics in the loss function?

    • @Deepia-ls2fo
      @Deepia-ls2fo 29 дней назад

      Yes exactly !

  • @MutigerBriefkasten
    @MutigerBriefkasten Месяц назад

    Amazing presentation again 🎉 thank you for your efforts and time

  • @Bwaaz
    @Bwaaz Месяц назад

    Great video ! You mention that the contrastive loss pushes/pulls points, how does the loss function "push away" a point exactly ?

    • @Deepia-ls2fo
      @Deepia-ls2fo Месяц назад

      Thanks, it pushes negative pairs apart until their distance reaches the margin, by minimizing the difference between the margin and the distance between the points. This is the quantity in red at 06:40 :)

  • @gamma8675
    @gamma8675 Месяц назад

    awesome content!

  • @delistoyer
    @delistoyer Месяц назад

    I like that you're focusing on computer vision

  • @gx1501996
    @gx1501996 Месяц назад

    InfoNCE loss at 11:14 looks odd as Dp is the distance notation at 9:00, but you say its related to probabilities. It would break the flow to introduce new notation though. But as it stands it was a little confusing to me to see that the loss would be minimized by maximizing Dp. I checked the paper and it seems the term is an approximator for "mutual information" which we want bigger for positive samples. At least thats my rough understanding... Thanks for the video its a fantastic explanation!

    • @Deepia-ls2fo
      @Deepia-ls2fo 29 дней назад

      Indeed I should have taken the time to introduce it properly and use the correct notations

  • @itz_lucky6472
    @itz_lucky6472 Месяц назад

    At 12:04 you say that SimCLR select multiple negative pairs and then you show a picture of a cat, and a dog. I am confused, the second dog picture is also considered as a negative pair even though it's the same animal? If yes, does this mean the model train to lower the distance ONLY with the original image even though other could be dogs?

    • @Deepia-ls2fo
      @Deepia-ls2fo Месяц назад

      Exactly! The negatives can be any other image in the batch, including very similar objects

    • @itz_lucky6472
      @itz_lucky6472 Месяц назад

      @@Deepia-ls2fo That is very interesting, thank you for your answer, I have another question if you do not mind At the end when comparing classification accuracy you compare supervised, SimCLR+finetune and SimCLR, the last one have me confused, how can the model without any finetuning even work for classification? Or do they not count a trained dense layer that learn to use the latent space of SimCLR for classification, and SimCLR+finetune mean finetuning the latent space instead? My question is that does fine-tune mean finetuning a dense layer or the latent space? Your videos are high quality and I really love them, sometimes I just wish they would be longer and slightly more into the implementation details, thank you! Edit: Regarding my first question, since the negative pair can be the same class (if we imagine the ultimate goal is classification), would a low amount of class (let's say only 2) lower the quality of the latent space due to a high amount of class "collision" ? And in the opposite if there is hundreds of class it will rarely select the same class as a negative pair and improve latent space representation?

    • @Deepia-ls2fo
      @Deepia-ls2fo Месяц назад

      @@itz_lucky6472 I strongly advise you to read the SimCLR paper as it is a very easy read and they detail everything. About the classification task: for SimCLR they use what we call "linear eval", meaning they plug a fully connected head on the model and train only this part. The difference between "SimCLR" and "SimCLR fine-tune" is that the weights of the backbone are modified in a supervised fashion with a small portion of the data for "SimCLR fine-tune". For your second question I did not read a lot about this, and I'm myself new to self-supervised learning in general, so I can't answer for sure. I guess you could easily do the experiment with 2 MNIST classes though. Intuitively I think taking many semantically similar objects and treating them as negatives is bad for the representation space.

  • @444haluk
    @444haluk Месяц назад

    Augmentations ARE the labels, labels of "ignore".

  • @Omunamantech
    @Omunamantech Месяц назад

    Awesome Video :D

  • @diffpizza
    @diffpizza Месяц назад

    Nice explanation! It still isn't clear to me how to choose the metric to determine how similar or dissimilar two samples are, is it also learned by the network?

    • @Deepia-ls2fo
      @Deepia-ls2fo Месяц назад

      You can choose any differentiable metric, that's one of the strength of this framework :)

  • @zyansheep
    @zyansheep Месяц назад

    Day by day, we inch closer and closer to creating The Great Compressor.

    • @Tothefutureand
      @Tothefutureand Месяц назад

      Like the one in Silicon Valley TvSeries.

    • @WhiteWeaver-hk2nt
      @WhiteWeaver-hk2nt Месяц назад

      I'd love to be compressed between my robot anime waifu's thighs 🤤

  • @khoakirokun217
    @khoakirokun217 Месяц назад

    Outstanding technique :D thank you, it was not wrong to subscribe the channel :D

  • @dewibatista5752
    @dewibatista5752 Месяц назад

    is the voice in the vid the output of a TTS model?

    • @Deepia-ls2fo
      @Deepia-ls2fo Месяц назад

      Yes ! It's my voice though :)

  • @KoHaN7
    @KoHaN7 Месяц назад

    Amazing content! Looking forward to the next videos 😄

  • @Higgsinophysics
    @Higgsinophysics Месяц назад

    Insane technique! awesome video thanks for explaining this with tons of examples.

  • @Nomah425
    @Nomah425 Месяц назад

    Hmmmmmm YES