Ayman Shams

@aymanshams__

Generative modelling, medical imaging enthusiast. Researcher . Musician. Opinions my own.

Montréal, Québec
Vrijeme pridruživanja: rujan 2016.

Tweetovi

Blokirali ste korisnika/cu @aymanshams__

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @aymanshams__

  1. Prikvačeni tweet
    27. srp 2019.

    It was an absolute pleasure organizing Ai in Medicine meetup at the Thank you everyone for attending! – mjesto: University of Alberta | Edmonton, CAN

    Poništi
  2. proslijedio/la je Tweet
    30. sij

    We're standardizing OpenAI's deep learning framework on PyTorch to increase our research productivity at scale on GPUs (and have just released a PyTorch version of Spinning Up in Deep RL):

    Poništi
  3. proslijedio/la je Tweet
    15. sij

    Differentiable Digital Signal Processing (DDSP)! Fusing classic interpretable DSP with neural networks. ⌨️ Blog: 🎵 Examples: ⏯ Colab: 💻 Code: 📝 Paper: 1/

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    15. sij

    More exciting news today: an example of how AI and neuroscience continue to propel each other forward. (1/2)

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    18. sij

    i just read this excellent paper from 2018: "Relational inductive biases, deep learning, and graph networks". extremely well written, very clear, excellent graphics, and with code. highly recommended! paper: code: :

    Poništi
  6. proslijedio/la je Tweet
    11. sij

    On the Relationship between Self-Attention and Convolutional Layers This work shows that attention layers can perform convolution and that they often learn to do so in practice. They also prove that a self-attention layer is as expressive as a conv layer.

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    10. sij

    Very happy to share our latest work accepted at : we prove that a Self-Attention layer can express any CNN layer. 1/5 📄Paper: 🍿Interactive website : 🖥Code: 📝Blog:

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    31. pro 2019.

    Don't get frightened by not knowing things. I have approximate answers, and possible beliefs, and different degrees of certainty about different things, but I'm not absolutely sure of anything. There are many things I don't know anything about. It doesn't frighten me. 🧠

    Poništi
  9. proslijedio/la je Tweet
    13. pro 2019.

    Finally I can replace ‘watch -d -n .5 nvidia-smi’!!! Great work by ⁦⁦⁩ et al from ⁩ “GPU Dashboards in Jupyter Lab”

    Poništi
  10. proslijedio/la je Tweet
    6. pro 2019.

    Still deciding which workshop to attend at ? Maybe pop by wrkshop next Saturday morning for an oral on the Hierarchical Probabilistic U-Net! Find the full paper at: And the open-sourced code + data under:

    Poništi
  11. proslijedio/la je Tweet
    5. pro 2019.
    Poništi
  12. proslijedio/la je Tweet
    26. stu 2019.

    🎟️🎟️make everyone a lottery winner🎟️🎟️ train sparse networks (with a randomly initialized topology) end-to-end without sacrificing (much) accuracy! joint work with and 👇🏾🎟️👇🏾🎟️👇🏾

    Poništi
  13. proslijedio/la je Tweet
    17. stu 2019.

    A flow of incredibly enthusiastic and knowledge-hungry researchers in Neuro-AI pouring down the stairs at at Université de Montreal.

    Poništi
  14. proslijedio/la je Tweet

    I've just released a fairly lengthy paper on defining & measuring intelligence, as well as a new AI evaluation dataset, the "Abstraction and Reasoning Corpus". I've been working on this for the past 2 years, on & off. Paper: ARC:

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    28. lis 2019.

    Such a cool way to explain logic gates.

    Poništi
  16. proslijedio/la je Tweet
    20. lis 2019.

    That Rubik's cube thing was pretty cool and all, but I just successfully installed a brand new faucet for the first time in my kitchen sink, WITHOUT any Bluetooth sensors nor LEDs in my fingertips. Zero-shot learning, y'all!

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    21. lis 2019.

    there, you have them on one slide

    Poništi
  18. proslijedio/la je Tweet

    GANs have lagged far behind in the audio domain compared to the image domain, but MelGAN (from & at Lyrebird) seems to have finally achieved reasonable spectrogram inversion with a GAN! (At least for speech and some music.)

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    17. lis 2019.

    It's a tiny thing, but here's how to stop Git from naming the first branch "master" by default

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    16. lis 2019.

    We'd like to make this happen! Any folks out there know jazz clubs in they could put me in touch with? Also, could play bass, but he'd rather stick to sax, so if there are any jazz bass players who are attending , speak up! 🎹🎸🥁🎷🎶

    Poništi
  21. proslijedio/la je Tweet

    My new paper is out! We show a framework in which we can both derive and gradient penalized ! We also show how to make better gradient penalties!

    Prikaži ovu nit
    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·