Prabhu Prakash Kagitha

@prakashkagitha

Story teller of art and science | Creo phronesis

Bengaluru, India
Vrijeme pridruživanja: studeni 2014.
Rođen/a 1995.

Tweetovi

Blokirali ste korisnika/cu @prakashkagitha

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

  1. Prikvačeni tweet

    Here are all the abstracts from , of Keynote presentations, Tutorials, Orals & Spotlights, Posters and workshops. Keynotes from , Bin Yu, , , , . Looking forward to

    Poništi
  2. proslijedio/la je Tweet
    9. sij

    We are organizing a workshop on Causal learning for Decision Making at along with , Jovana Mitrovic, , Stefan and . Consider submitting your work!

    Poništi
  3. 6. sij

    I am pretty sure I am gonna take this more seriously than intended. Like, maybe I will have some of these things on my walls or something.

    Poništi
  4. 1. sij

    Reading this thread I kinda feel more inclusive and kind all of a sudden. Kindness inspires kindness.

    Poništi
  5. proslijedio/la je Tweet

    Should a church pastor have the right to criticize the actions of the government? Not in China. The detention of 100 Christians, including prominent Pastor Wang Yi, raises concerns about a growing religious crackdown in China.

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

    Interested in how neuroscience can inspire better AI? Come to NAISys, March 24-28 Abstracts (1 page) due Jan 10 registration {Please RETWEET ME}

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

    Some people in ML share the illusion that models expressed symbolically will necessarily/magically generalise better compared to, for example, parametric model families fit on the same data. This belief seems to come from a naive understanding of mathematics 1/5

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

    I'm curious. If you're in machine learning, do you know what the Levels of Analysis are? If so, do you think they are important or relevant for research today in machine learning?

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    25. pro 2019.

    If you want to be rewarded, you have to be irreplaceable. If you want to be irreplaceable, you have to be unique. If you want to be unique, you have to be authentic. If you want to be authentic, stop listening to everyone and everything else. It’s drowning “you” out.

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

    How long until it's gone? The decomposition times of marine debris [source: ]

    Poništi
  11. Check out the outstanding paper awards of “NeurIPS 2019 Paper Awards” by Neural Information Processing Systems Conference

    Poništi
  12. proslijedio/la je Tweet
    4. pro 2019.

    . & I are co-organizing the next Conference Apr 1, 2020—no joke!—on the topic Triangulating Intelligence: Melding Neuroscience, Psychology, and AI. Botvinick——Tenenbaum——save the date!

    Poništi
  13. proslijedio/la je Tweet
    3. pro 2019.

    Some may not know that the idea of combining symbols and neural nets has been around since at least the mid-80s. This book from 1991 has many thought-provoking chapters on the topic. Smolensky is perhaps the leading (practitioner) authority on this topic.

    Prikaži ovu nit
    Poništi
  14. I am really sad to hear same arguments again and again from you which are not leading us anywhere. If you are enlightening general public, that's well and good as long as you don't accuse us not hearing to your proposals which are neither novel nor constructive.7/7

    Prikaži ovu nit
    Poništi
  15. There is a plethora of work in causality, attention, memory, compositionaly etc.., by whom who know what symbolic AI is and also who don't shy away from using it in their approaches if it helps.6/7

    Prikaži ovu nit
    Poništi
  16. Brenden lake's , Dzmitry Bahdanau's , Felix Hill's work on systematicity, Tejas kulkarni's work on object centric representations, 's work to bring system2's capabilities into DL are just a few that interests me.5/7

    Prikaži ovu nit
    Poništi
  17. I, personally, am a disciple of Marvin Minsky's theories and am trying to realize his goals through DL by adding capabilities that he conjectured DL doesn't posses. From this stance I see a lot of people trying the more or less the same. 4/7

    Prikaži ovu nit
    Poništi
  18. Practitioners tend to weigh more the proposals by people who are actively contributing to what they are proposing than somebody who is not because the nuances of DL still are hard to grapple with even for the practitioners.(& there are a lot of new things discovered each week)3/7

    Prikaži ovu nit
    Poništi
  19. objectness, language understanding with common sense .., as your proposal for hybrid models alone will add very less or no value. If people stopped practicing science and engineering of intelligence and only proposed their opinions for the progress there won't be any progress.2/7

    Prikaži ovu nit
    Poništi
  20. The idea of hybrid models is very arbitrary. As a practitioner one probably knows current DL need new capabilities (from Symbolic AI or else where) to emulate intelligence. It would be very helpful if you could give insights as to *how* we could incorporate systematicity ... 1/7

    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:

    ·