Tweetovi

Blokirali ste korisnika/cu @Moha_Magdy

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

  1. proslijedio/la je Tweet
    31. sij

    Through this great story from James Briggs, a computational physicist turned data scientist, I came across his totally amazing deep learning notes, which are some of the best I've seen:

    Poništi
  2. proslijedio/la je Tweet
    31. sij

    On Tuesday, in my class, we have learnt that all a neural net does is stretching / contracting the space fabric. For example this 3-layer net (1 hidden layer of 100 positive neurons) gets its 5D logits (2D projections) linearly separable by the classifier hyperplanes (lines).

    Poništi
  3. proslijedio/la je Tweet
    31. sij

    دعوة للنشر والمشاركة في الورشة الدولية الرابعة للمدونات العربية وأدواتها (OSACT4) وبها مسابقة "اكتشاف تغريدات بالعربية تحث على الكراهية" موعد التسليم *25 فبراير* يشارك في تنظيمها التفاصيل:

    Poništi
  4. proslijedio/la je Tweet
    30. sij

    The 4th Workshop on Open-Source Arabic Corpora and Processing Tools () to be held with . We organise a task on Arabic hate-speech detection within our workshop. Submisssion deadline: 25th Feb 2020 Details here:

    Poništi
  5. proslijedio/la je Tweet
    29. sij

    I love hearing about results like this. When I saw 's brilliant work on AI-powered movie shot analysis last year I was blown away. I had no idea he'd started coding just in Aug 2018! Now he's a DL practitioner working in this space. Inspiring.

    Poništi
  6. proslijedio/la je Tweet
    28. sij

    Interesting to hear of folks getting better results from ULMFiT / AWD-LSTM and fastai2 vs BERT/transformer based models. Anyone else tried comparing these? cc

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

    Huge contribution to fast_template from : you can now write your blog posts in Word or Google Docs (including images), put them in the _word folder, and they'll appear in your blog! Nothing to install. No code to write. No ads. And its free.

    Poništi
  8. proslijedio/la je Tweet
    27. sij
    Poništi
  9. proslijedio/la je Tweet
    27. sij

    “letting the model learn how to process time series data on its own is a more promising solution when dealing with unstructured noisy data” — Vasilis Stylianou, PhD

    Poništi
  10. proslijedio/la je Tweet

    Honestly, the question is not, and has never been, "can machine learning replace radiologists/etc" (which won't happen in the foreseeable future). The question is, how can radiology/etc utilize ML to improve outcomes, decrease the cost of care, and broaden accessibility.

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    27. sij

    Very cool - a high school junior built a state of the art classifier for classifying cardiac arrhythmias with fastai and and got into an international science fair!

    Poništi
  12. proslijedio/la je Tweet
    20. sij

    I've just finished a 4 part series on hosting your own blog; no coding, ads, paywalls, or fees. You can write in an online editor, MS Word, or Google Docs (including images). If you haven't started blogging yet, perhaps this will help you get started! 😊

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    17. sij
    Odgovor korisnicima

    Just launched using this! It was seamless and I did it mostly from my phone. Having seen all the magic that is voila with jupyter notebooks + widgets + nbdev, I'm thinking a jupyter-based blog is the next step!

    Poništi
  14. proslijedio/la je Tweet
    16. sij

    I did a deep-dive into Pages, and found it's possible to create a *really* easy way to host your own blog: no code, no terminal, no template syntax. I made "fast_template" to pull this together, & a guide showing beginners how to get blogging

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

    It's also a great, gentle intro to the world of git. In a future post I'll show how to use git to work on your blog locally. This tool is designed for folks who are new to coding. I'd love your help getting the word out about this to them! :)

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    16. sij

    torchtext v0.5: improved data API, unsupervised text tokenization - bindings for SentencePiece - New: enwiki9, revisions to PennTreebank, WikiText103, WikiText2, IMDb (looking for feedback) Release Notes:

    Poništi
  17. proslijedio/la je Tweet
    15. sij

    Stunning results in genomics using language model pretraining!

    Poništi
  18. proslijedio/la je Tweet
    15. sij

    Don't just teach your students to read. • Teach them to question what they read, what they study. • Teach them to doubt. • Teach them to think. • Teach them to make mistakes and learn from them. • Teach them how to understand something.

    Poništi
  19. proslijedio/la je Tweet
    15. sij

    Since the popularity of nbdev () is kinda taking off now (yay!) we've created a dedicated forum category for discussing it.

    Poništi
  20. proslijedio/la je Tweet
    15. sij

    This is an absolutely first-class article with a much clearer explanation of the joy of developing with and nbdev then I've ever managed! :)

    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:

    ·