olti

@battle8500

Applied statistician. Economist.

Vrijeme pridruživanja: veljača 2018.
9 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @battle8500

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @battle8500

  1. proslijedio/la je Tweet
    4. velj

    It's official, has hit 100k downloads in just 5 months! 45k just in the last 2 months. If you are still coding for-loops by hand or doing your own distributed training, you should REALLY check out lightning.

    37 proslijeđenih tweetova 197 korisnika označava da im se sviđa
    Poništi
  2. prije 16 sati

    Seems like 's 1984 is already here (in China) 🙄🙄🙄🙄

    Poništi
  3. proslijedio/la je Tweet
    prije 18 sati

    Underrated skill for founders: Altitude shifting. People are often either good at high-level strategy or atomic-level execution, but rarely both. It's the ability to zoom out & paint the 5 yr vision, and then drop down into the weeds of day-to-day, & see how the two connect.

    350 proslijeđenih tweetova 1.945 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    prije 20 sati

    Check out the all new, all Swift CSVDataLoader! (19µs/row) With the new data loader you can have access to any CSV dataset in under a minute! Check it out by creating a PR Here's a quick guide:

    1 reply 3 proslijeđena tweeta 4 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    prije 18 sati

    List of Machine Learning and Deep Learning conferences in 2020

    2 proslijeđena tweeta 2 korisnika označavaju da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    prije 21 sat

    Interested in helping build the most awesome blogging platform around? Then please come help me and as we create `fastpages` together.

    6 replies 23 proslijeđena tweeta 163 korisnika označavaju da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    3. velj

    MIT's new CS class teaches you things that all the other classes don't teach you, like... 🖥️Shell tools and scripting 🖥️Vim 🖥️Data wrangling 🖥️Command-line environment 🖥️Version control Watch all 11 lectures for free here:

    10 replies 366 proslijeđenih tweetova 1.092 korisnika označavaju da im se sviđa
    Poništi
  8. 3. velj

    Nice representation of vs set

    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
    1 korisnik označava da mu se sviđa
    Poništi
  9. 3. velj

    Today's plunge of Shangai stock exchange of about 7.7% in 🇨🇳 is the perfect example of . Who knows if and others following his advice got even more richer today 😎😎😎

    Poništi
  10. proslijedio/la je Tweet
    2. velj

    The Wall Street Journal just published an article about me and Bridgewater that is filled with intentional factual errors. You can read about my account of what's happening here:

    55 replies 150 proslijeđenih tweetova 728 korisnika označava da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    2. velj

    Thread 👇 We’ve also had a difficult time with CuDNN as soon as you want to go beyond a basic LSTM and grab cell states, do -style dropout, etc. Maybe now that has an team, things might get better?

    What are the best solns for high level to low level performant creation of RNN/LSTM layers? - Reason: seem unlikely to release new cuDNN RNNs (i.e. LayerNorm LSTM) - The JIT looked promising but JIT LSTM had many problems for me - JAX? TF? Back to CUDA?
    Prikaži ovu nit
    1 reply 12 proslijeđenih tweetova 65 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    2. velj

    My attempt for our book at explaining the difficulty of training deep networks, for folks not familiar with math beyond high school. Any suggestions to make this clearer or simpler (*not* more mathematically rigorous)?

    40 replies 50 proslijeđenih tweetova 393 korisnika označavaju da im se sviđa
    Poništi
  13. 2. velj

    A good article about how to deal with

    The Quarantiner’s Dilemma is similar to the Innovator’s Dilemma. There’s a fast-growing but still small threat. Throw all your weight at it early? Then you seem to have overreacted. Wait till it gets big enough to be undeniable? Then you’re surely dead.
    Prikaži ovu nit
    Poništi
  14. 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).

    202 proslijeđena tweeta 1.058 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    30. sij

    I was just thinking it would be cool if you could do hyperparameter tuning directly in Keras and then found this blog post published yesterday 🤯 The best part? I got it working in 5 minutes!

    35 proslijeđenih tweetova 175 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    31. sij

    Here, I write about where I’ve been, where I’m at, and where I want to go next. I approach this process with an attitude of loving criticism, so I can celebrate my wins while striving for improvement. And by sharing my goals, I hold myself accountable.

    5 proslijeđenih tweetova 40 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    31. sij

    If you're running xgboost, lgbm, or other forest based models in production you need to check out our new forest inference library. 40x faster predictions, cheaper than cpu and way less rack space.

    40x faster predictions for even the deepest random forests with FIL’s new sparse forest support -
    69 proslijeđenih tweetova 308 korisnika označava da im se sviđa
    Poništi
  18. 30. sij

    After only a few days it was available in , just released 1.0 It comes with some new very interesting features. Check it out!

    We’re so excited for the milestone the pandas team has reached with the release of 1.0 today!
    Poništi
  19. proslijedio/la je Tweet
    30. sij

    slides from my "Muppets and Transformers" talk at

    1 reply 6 proslijeđenih tweetova 20 korisnika označava da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    30. sij

    New dataset coming soon for recsys and Twitter will release a large public dataset of ~200M public tweets, obtained by subsampling within ~2 weeks, that contains engagement features, user features, and tweet features.

    1 reply 31 proslijeđeni tweet 116 korisnika označava da im se sviđa
    Poništi

@battle8500 još nije objavio nijedan Tweet.

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:

    ·