ImageGPT (Generative Pre-training from Pixels)

Поділитися
Вставка
  • Опубліковано 17 чер 2024
  • This video will explore the exciting new 6.8 Billion parameter ImageGPT model! The researchers show that better and larger generative models learn better representations for tasks like ImageNet classification!
    Thanks for watching! Please Subscribe!
    Paper Links:
    ImageGPT (Blog Post): openai.com/blog/image-gpt/
    ImageGPT (Paper): cdn.openai.com/papers/Generat...
    A Survey of Long-term Context in Transformers: www.pragmatic.ml/a-survey-of-...
    Google TPUs: cloud.google.com/tpu/docs/tpus
    The Illustrated Transformer: jalammar.github.io/illustrated...
    PixelCNN: keras.io/examples/generative/...
    PixelCNN (Paper): arxiv.org/pdf/1606.05328.pdf
    Contrastive Predictive Coding: arxiv.org/pdf/1905.09272.pdf
    Big BiGAN: arxiv.org/pdf/1907.02544.pdf
    BERT: arxiv.org/pdf/1810.04805.pdf
    Rethinking Pre-training and Self-Training: arxiv.org/pdf/2006.06882.pdf
  • Наука та технологія

КОМЕНТАРІ • 12

  • @connorshorten6311
    @connorshorten6311  4 роки тому +4

    2:18 Auto-Regressive modeling of Pixels
    4:18 Denoising Autoencoders: AR and BERT
    5:40 GPT Architecture, No CNN Prior!
    7:00 6.8 BILLION parameters!! Comparison with SimCLR, CPC, BigBiGAN
    8:24 Generative Models and Representation Learning for Vision
    10:30 Fine-Tuning with Linear Probes
    11:50 Working around Quadratic Complexity of Self-Attention
    12:50 Context Reduction
    13:52 Results and Ablations
    18:50 Promise of Longer Context Transformers and Visual Representation Learning

  • @herp_derpingson
    @herp_derpingson 4 роки тому +7

    Yannic Kilcher sent me here. Good channel. Subbed!

  • @Schematical
    @Schematical 4 роки тому

    Awesome stuff. Have to watch it a couple times to wrap my head around it.

  • @citiblocsMaster
    @citiblocsMaster 4 роки тому +2

    That imageGPT result is crazy. It seems that you can replace inductive biases (translation invariance via convolutions) with just more data and compute.

    • @jeremykothe2847
      @jeremykothe2847 4 роки тому +1

      The resolution is so low though - not sure it would scale as well even if memory was available for a larger size.

  • @airazure2050
    @airazure2050 4 роки тому +1

    Awesome content! Thanks!

  • @erikacardenas2964
    @erikacardenas2964 4 роки тому +2

    Awesome video!

  • @Ritrixone
    @Ritrixone 4 роки тому

    Good job!

  • @AbdennacerAyeb
    @AbdennacerAyeb 4 роки тому +1

    Great job. We need colab tutorials.

  • @geekionizado
    @geekionizado 4 роки тому

    😩 too awesome i can't even process

  • @quadhd1121
    @quadhd1121 4 роки тому +2

    Can u use plain English please ,it still sounds complex for bigginners