ecdrid

@aditya_soni2k17

A deeply convoluted mind, hitting random keys & continuously Improving... In love with , PyTorch, Keras Interested in Maths, Programming, ML, DL, DB.

At NoWhere
kaggle.com/adityaecdrid
Vrijeme pridruživanja: studeni 2017.
6 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @aditya_soni2k17

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @aditya_soni2k17

  1. Prikvačeni tweet
    10. velj 2018.

    This set of notebooks is awesome for pandas, Do Check them out.. Thanks a lot for them.. Learnt tons of things...

    41 proslijeđeni tweet 146 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    prije 22 sata

    François () is both an independent ML researcher investigating sparse efficient models and... an early angel investor in 🤗 Happy that he agreed to share some of his knowledge and experience on sparse models in a series of posts! First one is here

    1 reply 60 proslijeđenih tweetova 244 korisnika označavaju da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    4. velj

    Git is moving away from SHA-1 hash function.

    32 proslijeđena tweeta 59 korisnika označava da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    4. velj

    Early on the neural network landscape was fragmented. In 2015, Keras started attracting attention. Today it’s Keras/TensorFlow and PyTorch. (As of TF 2.0, Keras is the high level API for TensorFlow.) 3/3

    10 proslijeđenih tweetova 36 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    4. velj

    In 2011, Random Forest started being discussed in the forums. In 2014, it was XGBoost. More recently we’ve seen LightGBM and then Catboost gaining momentum. 2/3

    11 proslijeđenih tweetova 36 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    4. velj

    The biggest reasons why PyTorch became so popular on 1. Amazing model zoo. Very imp to start with a pretrained model in any comp based on NNs. 2. Compared to TF 1.x, writing models in it felt like writing C++ vs Python

    Early on the neural network landscape was fragmented. In 2015, Keras started attracting attention. Today it’s Keras/TensorFlow and PyTorch. (As of TF 2.0, Keras is the high level API for TensorFlow.) 3/3
    Prikaži ovu nit
    1 reply 6 proslijeđenih tweetova 45 korisnika označava 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. proslijedio/la je Tweet
    4. velj
    Odgovor korisnicima

    the explanation is probably simplified. Converted to C++ doesn't mean hand-rewrite in C++, probably actually auto-converted to their low-level runtime. They have their own ASIC, sensors, etc., which probably has it's own tooling, drivers, staged IR, compiler.

    1 reply 5 proslijeđenih tweetova 100 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    2. velj

    Today is 02 02 2020, which is the first palindrome date in 909 years.

    329 replies 15.929 proslijeđenih tweetova 68.103 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    31. sij

    A few years ago TensorFlow looked indomitable. Now it's on the verge of being overtaken by Pytorch. OpenAI just announced it's standardizing on Pytorch, joining the likes of Tesla, Nvidia, and FB. Google hoped TensorFlow would cement its lead in ML. It may soon be a liability.

    187 proslijeđenih tweetova 761 korisnik označava da mu se sviđa
    Poništi
  11. proslijedio/la je Tweet
    18. sij

    Talk on "metasploit primary" by It's about understanding metasploit framework

    6 proslijeđenih tweetova 21 korisnik označava da mu se sviđa
    Poništi
  12. proslijedio/la je Tweet
    31. sij

    Happy Friday hackers! Nitesh found a critical RCE vulnerability in Jenkins that led us to discover a Bitcoin mining service running on a DoD website 😲. Head over to the disclosed report to see all the details! Thanks for being 🔥 Nitesh

    105 proslijeđenih tweetova 315 korisnika označava da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    24. sij

    I have thought about these two paragraphs so many times over the years. Huge thanks to for finding the source.

    31 reply 256 proslijeđenih tweetova 1.080 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    29. sij

    kaggle often gets a hard time because people overfit or manipulate metrics to get good scores - honestly, reading some papers I don't see how that's any different from a lot of research being done

    1 proslijeđeni tweet 4 korisnika označavaju da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    31. sij

    My Interview with Grandmaster and Data Scientist: Rohan Rao, All about his "On & Off Kaggle" Data Science and Competitive journey + ASHRAE Great Energy Prediction Comp's 2nd Pos Sol is live: Video: Audio:

    7 proslijeđenih tweetova 43 korisnika označavaju da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    30. sij

    People asking me to teach classes clearly give zero fuck to the imposter syndrome of a former physics PhD turned lawyer before joining AI Anyway I'll co-teach NLPL Winter School w Yoav Goldberg talking transfer learning, its limits & where the field might head Will share slides

    12 replies 20 proslijeđenih tweetova 432 korisnika označavaju da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    29. sij

    Thank you! 🍻🍻

    2 proslijeđena tweeta 43 korisnika označavaju da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    5. ožu 2018.

    My notes from excellent deep learning specialization on Coursera () Yay! finally finished it Full notes on slideshare:

    112 replies 1.173 proslijeđena tweeta 3.830 korisnika označava da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    27. sij

    Data scientists Phillip Singer and Dmitry Gordeev from Austria used a highly technical approach to predict rushing play outcomes. This week’s 📊 explains how their analysis earned them the top prize at the second :

    i
    46 proslijeđenih tweetova 181 korisnik označava da mu se sviđa
    Poništi
  20. proslijedio/la je Tweet
    11. pro 2019.

    2 proslijeđena tweeta 31 korisnik označava da mu se sviđa
    Poništi
  21. proslijedio/la je Tweet
    8. sij

    After a year of active kaggling for The Zoo, I am proud to recap our achievements. We participated in 7 competitions ending with 6 gold medals and 3 wins. So our win rate is above 40% so far!

    2 proslijeđena tweeta 88 korisnika označava da im se sviđa
    Poništi

@aditya_soni2k17 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:

    ·