Tweetovi

Blokirali ste korisnika/cu @BecarPeter

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

  1. proslijedio/la je Tweet
    30. ruj 2019.

    First fastai v2 starter pack! :O (Note that v2 is very very pre-release - is an early adopter!)

    Poništi
  2. proslijedio/la je Tweet
    23. ruj 2019.

    Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented...

    Poništi
  3. proslijedio/la je Tweet
    15. ruj 2019.

    Ensemble Methods for Machine Learning: AdaBoost

    Poništi
  4. proslijedio/la je Tweet
    6. stu 2018.

    Got an interesting research dataset and problem, but don't have the AI skill set you need in-house? Our new medical AI research institute can work with you to create a cross-domain team to test and develop your project. For free.

    Poništi
  5. proslijedio/la je Tweet
    12. lis 2018.

    Wait what? Umm it seems that you guys have ripped off our entire course without providing any credit or mention or asked for permission? Could you please explain to the folks involved a little about standards of academic conduct? cc (sponsors)

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet

    Kubernetes is great for deploying ML apps. Here's a detailed guide on how to use Kubernetes to deploy a Keras model as a REST API on Google Cloud:

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    2. lis 2018.

    Wow just made my day at the conference: "I tell everyone to do . There's nothing better out there." :) I still refer to his CS231n course notes all the time to figure out how best to explain things...

    Poništi
  8. 26. srp 2018.
    Poništi
  9. proslijedio/la je Tweet
    24. srp 2018.

    Operational Machine Learning: Seven Considerations for Successful MLOps

    Poništi
  10. proslijedio/la je Tweet
    20. srp 2018.

    Doing : A Walkthrough Cleaning Data

    Poništi
  11. proslijedio/la je Tweet
    21. srp 2018.

    Deep Learning Part 2 Complete Course Notes

    Poništi
  12. proslijedio/la je Tweet
    18. srp 2018.
    Poništi
  13. proslijedio/la je Tweet
    16. srp 2018.

    Ouch: “prestigious institutions had on average 65% higher grant application success rates and 50% larger award sizes, whereas less-prestigious institutions produced 65% more publications and had a 35% higher citation impact per dollar of funding”

    Poništi
  14. proslijedio/la je Tweet
    16. srp 2018.

    a really solid blog post detailing the evolution of a fraud detection model at Lyft 📝 tldr; logistic regression -> xgboost -> NNs this was driven by 1) need for more nuanced decision boundaries & 2) an increasing difficulty engineering useful features

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    6. srp 2018.

    Machine Learning Course Notes - a set of fantastic notes on the freely available machine learning MOOC

    Poništi
  16. proslijedio/la je Tweet
    6. srp 2018.

    5 Things You Need to Know about Reinforcement Learning

    Poništi
  17. proslijedio/la je Tweet
    6. srp 2018.

    Time Series for Dummies – The 3 Step Process

    Poništi
  18. proslijedio/la je Tweet

    most common neural net mistakes: 1) you didn't try to overfit a single batch first. 2) you forgot to toggle train/eval mode for the net. 3) you forgot to .zero_grad() (in pytorch) before .backward(). 4) you passed softmaxed outputs to a loss that expects raw logits. ; others? :)

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    2. srp 2018.

    New post: "AdamW and Super-convergence is now the fastest way to train neural nets". Practically important new results from the amazing . Easily beats our winning DAWNBench approach!

    Poništi
  20. proslijedio/la je Tweet

    Our latest work demonstrates how agents achieve human-level performance in a complex first-person multiplayer game, and can even collaborate with human teammates!

    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:

    ·