Aman Arora

@amaarora

Data scientist at CoreLogic Australia; Founder- Applied Data Science Sydney; student and contributor;

Sydney, New South Wales
Vrijeme pridruživanja: lipanj 2014.

Tweetovi

Blokirali ste korisnika/cu @amaarora

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

  1. Prikvačeni tweet
    2. stu 2019.

    Investing time in is one of the best investments I have ever made. To continue to learn, I am starting a new series where I will digging deep into the source code. This builds on top of code walkthrus.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    31. sij

    Why Random Forests can’t predict trends and how to overcome this problem. by

    Prikaži ovu nit
    Poništi
  3. prije 17 sati
    Poništi
  4. proslijedio/la je Tweet
    4. velj

    I just tried the () Neural Network that was trained for colorizing old, black and white images. This is Albert Einstein’s original footage (and his voice), then using the neural net to colorize it.

    Poništi
  5. proslijedio/la je Tweet
    3. velj

    When you are at the lowest point in your life, what you turn to probably tell you a lot about yourself. I turned on computer and started machine learning.

    Poništi
  6. proslijedio/la je Tweet
    3. velj

    Break it down! Introducing the "Break" benchmark for testing the ability of models to break down a question into required steps for computing the answer. Accepted for . Learn more about Break in this post by Tomer Wolfson on the AI2 Blog:

    Poništi
  7. proslijedio/la je Tweet
    3. velj

    In January, , , and I ran a short class at on topics we think are missing in most CS programs — tools we use every day that everyone should know, like bash, git, vim, and tmux. And now the lecture notes and videos are online!

    Poništi
  8. proslijedio/la je Tweet
    3. velj

    "We achieved an overall accuracy of 94.5%, more than 4.5% of an increase on the previous state-of-the-art"; classifying the patterns in 18,577 Scanning Electron Microscope images

    Poništi
  9. proslijedio/la je Tweet
    3. velj

    I made an illustration for my class of why you need separate validation and training sets and I'm quite happy with it. Has anyone illustrated this similarly before?

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    2. velj
    Odgovor korisniku/ci

    A PhD is definitely not required. All that matters is a deep understanding of AI & ability to implement NNs in a way that is actually useful (latter point is what’s truly hard). Don’t care if you even graduated high school.

    Poništi
  11. proslijedio/la je Tweet
    3. velj

    is more than just public code. It's a mindset of sharing, being transparent and collaborating across organizations. It's about building on the shoulders of other projects and advancing together the state of technology (1/N) , , ,

    Prikaži ovu nit
    Poništi
  12. 3. velj

    Wouldn't it just be great if started a MOOC explaining all the awesome things it was doing? I can only imaging the amount of good it would do to the NLP community. Just a question that I am gently putting out there.. :)

    Poništi
  13. proslijedio/la je Tweet
    1. tra 2019.

    If you're bootstrapping yourself into deep learning research, here’s what I would do: 1. FastAI (3m) 2. Personal projects/reproduce papers/consulting (3 - 12m) 3. Flashcard the Deep Learning Book (4-6m) 4. Flashcard ~100 papers in a niche (2m) 5. Publish your first paper (6m)

    Poništi
  14. proslijedio/la je Tweet

    Interesting costs/spec for Google's Meena chatbot. By comparison, Mitsuku takes 40Mb of space, needs 4Mb of RAM and runs on a single CPU. As a bonus, I even let people talk to it! 😉

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

    Never underestimate the bandwidth of a bored open source developer. Many developers, if given $100 of hardware, will happily provide $10,000 worth of free labour in their efforts to make it work.

    Poništi
  17. proslijedio/la je Tweet
    19. sij

    I've updated the fast_template sample post to include examples of most of the markdown syntax you might need, and have added some handle js and css to automate stuff like image captions. Markdown: Result:

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet

    my friends & I routinely have “bracket nights” where we pick 16 of something (tonight it’s “types of chairs”) & argue about them until we crown a winner & there is something magnificent about watching grown ass adults lose it over whether a rocking chair or a recliner is better

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

    Something I cant stop thinking about: With GitHub, MSFT bought direct access to all devs for ~$190 each ($7.5B/40m). Devs are currently the most undermonetized cohort relative to value created In an age where CAC is everything, this'll go down as 1 of cheapest acquisitions ever

    Poništi
  20. proslijedio/la je Tweet
    19. sij

    So I trained a model to have the reading comprehension ability of a first grader. Try it out! Built using , ALBERT, ,

    Poništi
  21. proslijedio/la je Tweet
    17. sij

    I've now added optional LaTeX equation support to this template.

    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:

    ·