NYAI - A Path To Unsupervised Learning Through Adversarial Networks by Soumith Chintala

  • View
    206

  • Download
    3

Embed Size (px)

Text of NYAI - A Path To Unsupervised Learning Through Adversarial Networks by Soumith Chintala

  • A path to unsupervised learning

    Soumith ChintalaFacebook AI Research

    through Adversarial Networks

  • Overviewof the talk

    Unsupervised Learning Generative Adversarial Networks Advances Using the learnt representations Whats next?

  • Unsupervised LearningAn introduction

  • Unsupervised LearningAn introduction

    Supervised Learning

  • Unsupervised LearningAn introduction

    Unsupervised Learning

  • Unsupervised LearningUsefulness

  • Unsupervised LearningReusing representations

  • Generative ModelsAn introduction

    A model that learns a distribution of images

  • Generative ModelsAn introduction

    X = P(z), z controls dogness or catness

  • Generative ModelsAn introduction

    X = P(z), z is a latent variable

  • Generative ModelsAn introduction

    P(z) = neural network

  • Generative Adversarial Networks

  • Generative Adversarial NetworksAlternating optimization

    Generator Sample Optimizer

    Training Data

    Loss: Looks Real

  • Generative Adversarial Networks

  • Generative Adversarial NetworksAlternating optimization

    Generatornoise SampleClassification

    Loss

    Training Data

    Learnt Real/Fake Cost function

    Discriminator

  • Generative Adversarial NetworksAlternating optimization

    Generatornoise SampleClassification

    Loss

    Training Data

    Discriminator

    Trained via Gradient Descent

  • Generative Adversarial NetworksAlternating optimization

    Generatornoise SampleClassification

    Loss

    Training Data

    Discriminator

    Optimizing to fool D

  • Generative Adversarial NetworksAlternating optimization

    Generatornoise SampleClassification

    Loss

    Training Data

    Discriminator

    Optimizing to not get fooled by G

  • Generative Adversarial NetworksOptimizes Jensen-Shannon Divergence

  • Generative Adversarial NetworksSamples

  • Class-conditional GANs

  • Generatornoise

    SampleClassification

    Loss

    Training Data

    Discriminator

    Class-conditional GANsNot unsupervised

    class

  • Video Prediction GANs

  • Generatornoise SampleClassification

    Loss

    Training Data

    Discriminator

    Video Prediction GANs

  • Generatornoise SampleClassification

    Loss

    Training Data

    Discriminator

    Video Prediction GANs

    Generatornoise SampleClassification

    Loss

    Training Data

    Discriminator

    MSE Loss

  • Video Prediction GANs

  • DCGANs

  • Latent space arithmetic

  • Using the GAN feature representation

  • Using the GAN feature representation

  • Using the GAN feature representation

    Needs much lesser labeled data

  • Using the GAN feature representation

  • In-painting GANs

  • In-painting GANs

  • In-painting GANs

  • Disentangling representations

  • Disentangling representations

  • Disentangling representations

  • Disentangling representations

  • Disentangling representations

  • Disentangling representations

  • Stability and Representation Reuse

  • Stability and Representation Reuse

    Feature matching Minibatch discrimination Label smoothing Whats next?

  • Stability and Representation Reuse

  • Stability and Representation Reuse

  • Whats next? Planning and forward modeling

  • Questions

    When will adversarial networks take over the world? Soon.