Manoj Acharya

@manoja328

PhD student at RIT : Interested in DeepLearning , ComputerVision and NLP

Rochester, NY
Vrijeme pridruživanja: svibanj 2010.

Tweetovi

Blokirali ste korisnika/cu @manoja328

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @manoja328

  1. Prikvačeni tweet
    26. ruj 2019.

    Excited to hear that we won the 2019 OpenEDS challenge. We will be presenting our work in the "Eye Tracking for VR and AR" workshop in ICCV 2019. [1/n]

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

    Amazing: a trail of termites (up) and a trail of ants (down), both protected by a row of their soldiers in a stand-off, without fighting. from

    Poništi
  4. proslijedio/la je Tweet

    Loving this trend of impressive new scientific sites. What else is in this vein? - : learn quantum computing - : learn ML - : interactive AI journal - : Medium for scientific publishing

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

    Advice for the 21st century: If you aren’t learning everyday, quit. If you don’t have a creative hobby, start. If you dislike your body, fast, and lift. If your English isn’t top-notch, study. If you have no driven friends, find some. If you have no long-term vision, think.

    Poništi
  6. proslijedio/la je Tweet
    29. svi 2019.

    We need better ways of searching for podcast episodes by topic Right now, we can only search for specific shows You should be able to search for a specific topic (i.e., intermittent fasting) and find every single podcast episode related to it

    Poništi
  7. proslijedio/la je Tweet
    26. pro 2019.
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet

    जनकपुर वरपर हुनुहुन्छ भने भोलि र पर्सि (मंसिर २०-२१) को नछुटाउनुस् है ! प्रेरणादायी छलफल, प्रदर्शनी, कार्यशाला, कला-इतिहास-संस्कृति जान्ने अवसर । कार्यक्रमको सफलताका लागि हाम्रो तर्फबाट धेरै शुभकामना । तालिका:

    Poništi
  9. proslijedio/la je Tweet

    Much of what’s being sold as "AI" today is snake oil. It does not and cannot work. In a talk at MIT yesterday, I described why this happening, how we can recognize flawed AI claims, and push back. Here are my annotated slides:

    Prikaži ovu nit
    Poništi
  10. 15. stu 2019.
    Poništi
  11. proslijedio/la je Tweet
    27. lis 2019.

    If you aspire to spend some of your time specifically dedicated to making the world better and don’t know where to start, please DM me I will either route you to a project directly or introduce you to someone who can There’s way too much to do and not enough hands to do it 🙂

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    16. lis 2019.

    That's such a cool idea. Congrats to for doing this.

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    15. lis 2019.

    To be listed among the women I see as my rolemodel is just overwhelming & empowering at the same time. Thank you It's an honour to be included in the list of BBC 100 Women 2019.

    Poništi
  14. proslijedio/la je Tweet

    My latest podcast, in which I am dumbfounded at how much of a sham the Stanford Prison Experiment turned out to be: (audio & transcript) How did this remain reputable for decades?? Thanks to my guest Thibault Le Texier for his stellar investigative work.

    Prikaži ovu nit
    Poništi
  15. 9. lis 2019.

    I wrote a summary of the paper "Why Does Deep and Cheap Learning Work So Well?"

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

    My PhD students Tyler Hayes, , , and created a new method for instance-by-instance streaming learning that can train convolutional layers. SOTA streaming for ImageNet-1K. We pioneer streaming VQA. Very exciting work.

    Poništi
  17. 26. ruj 2019.

    Thanks to everyone involved: Aayush Chaudhary, Rakshit Kothari , Manoj Acharya, Shusil Dangi , Nitinraj Nair , Reynold Bailey ,Christopher Kanan ,Gabriel Diaz and Jeff Pelz [n/n]

    Prikaži ovu nit
    Poništi
  18. 26. ruj 2019.

    In this work, we obtained the best performance in OpenEDS semantic segmentation dataset with a model size less than 1MB suitable for many real time applications. [2/n]

    Prikaži ovu nit
    Poništi
  19. 17. ruj 2019.

    The world relies on few good people and there is corporate greed.. sigh...

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

    ok woah figured out how to do NLP Q+A (thanks fo ❤️) this is getting pretty cool

    Prikaži ovu nit
    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:

    ·