Deepak Bhatt

@self_supervised

Building dumb machines with supervised learning; AI researcher in practice | past 》MERL, SamsungResearch | Current 》 Credit and Fraud modeling using AI

Vrijeme pridruživanja: studeni 2012.

Tweetovi

Blokirali ste korisnika/cu @self_supervised

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

  1. proslijedio/la je Tweet
    29. sij

    Anima Anandkumar's Caltech 2020 lectures on "Foundations of Machine Learning and Statistical Inference" are now available online.

    Poništi
  2. 19. sij

    Wonder what is Bayesian community take on this

    Poništi
  3. 18. sij
    Poništi
  4. proslijedio/la je Tweet
    15. sij

    Apophenia: The tendency to see patterns in random data.

    Poništi
  5. proslijedio/la je Tweet

    My machine learning education has progressed to the point where I lose sleep tossing around a “brilliant” idea, only to find the next day that it doesn’t actually work. This is great! I talked about this a few years ago:

    Poništi
  6. proslijedio/la je Tweet
    31. pro 2019.

    Here's a special countdown for 2020. Happy New Year!

    Poništi
  7. 29. pro 2019.

    Right when there is a big debate around deep learning

    Poništi
  8. proslijedio/la je Tweet
    7. pro 2019.

    I am looking for Masters and Ph.D. students to start in Fall 2020. If you are interested in working with me at (), the deadline is Dec 15. More info here: . You can also come to talk to me at .

    Poništi
  9. proslijedio/la je Tweet
    6. pro 2019.

    Why do deep ensembles trained with just random initialization work surprisingly well in practice?  In our recent paper with & Huiyi Hu, we investigate this by using insights from recent work on loss landscape of neural nets.  More below:

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    5. pro 2019.

    I'm looking for 2 PhD students in on a funded grant. Come join us in lovely Copenhagen! Deadline: Feb 1, 2020.

    Prikaži ovu nit
    Poništi
  11. 28. stu 2019.

    Boarded and interesting announcement got me Vision 2020. Says: Despite heavy traffic, you should reach your destination in 20:20

    Poništi
  12. 18. stu 2019.
    Poništi
  13. proslijedio/la je Tweet
    13. stu 2019.

    Interested in working on rubber-meets-the-road ML on a small team where you can publish AND build the future of medicine? is hiring ML Scientists, remote or local!

    Prikaži ovu nit
    Poništi
  14. 7. stu 2019.

    I was referred by our CTO to follow and I found the ideas shared really enlightening. I am sure there must be something great being noticed in our Honourable PM which led to this tweet. Look forward to watch the conversation

    Poništi
  15. proslijedio/la je Tweet

    Open Call: Turing AI Acceleration Fellowships✨ push the boundaries of what can do for the good of society, the economy, and for the planet. Do you want to see your ideas for AI embedded into real world applications? Apply here:

    Poništi
  16. proslijedio/la je Tweet
    17. lis 2019.

    Come work with me as a Data Ethics Fellow at ! We are hiring for 1 year fellowships: (if you have a graduate degree, more similar to postdoc) (no graduate degree required)

    Prikaži ovu nit
    Poništi
  17. 11. lis 2019.
    Poništi
  18. 10. lis 2019.

    Looks like I have always used Mode Collapse (wrongly); though I meant mode dropping.

    Poništi
  19. proslijedio/la je Tweet

    I just wrote an extensive TensorFlow 2.0 + Keras overview, targeted at deep learning researchers: Hope you will find it useful! Let me know if you have any feedback.

    Poništi
  20. 3. lis 2019.
    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:

    ·