Tanishka Singh

@tanishkasingh

CS grad student at ASU, research aide at Robotics and Information system lab and data science junkie

Vrijeme pridruživanja: srpanj 2008.

Tweetovi

Blokirali ste korisnika/cu @tanishkasingh

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

  1. Prikvačeni tweet
    2. tra 2019.

    When your edited model takes off smoothly.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    3. velj

    This is an incredible conceptual piece. I'm really taken with the simplicity and the inherent message about adversarial AI attacks.

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet

    If an algorithm has "mastered natural language", I would expect it to be able to do some of the things language is for -- communicating information, receiving information, acting on the world... Not merely output something that statistically sounds like language.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    2. velj

    Wow: Google's "Meena" chatbot was trained on a full TPUv3 pod (2048 TPU cores) for **30 full days** - That's more than $1,400,000 of compute time to train this chatbot model. (! 100+ petaflops of sustained compute !)

    Poništi
  5. 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?

    Poništi
  6. proslijedio/la je Tweet
    2. velj

    delivering education to remote areas of the world. (World Economic Forum)

    Poništi
  7. proslijedio/la je Tweet
    1. velj

    Probably my last cog neuro paper. This piece is such a great example of team work. I couldn’t be more thankful for all the authors hard work and help: , , , , , .

    Poništi
  8. proslijedio/la je Tweet
    1. velj

    Shimon says, Play On! Robotic band member joins the group. (Now This) .

    Poništi
  9. proslijedio/la je Tweet
    31. sij

    Parametric density fitting is a parameter estimation problem aiming at registering a template distribution to samples.

    Poništi
  10. proslijedio/la je Tweet
    30. sij

    YouTube is full of teachers who will happily repeat themselves until you get it. A rewindable instructor has infinite patience. One of the great resources of our time.

    Poništi
  11. proslijedio/la je Tweet
    24. sij

    When I see someone succeed, it inspires me, it makes me happy, it makes me proud to be human. Envy, derision are human inclinations too, but in the long-run they are counter-productive. Enjoying the success of others is the easiest way to be happy, second only to Baby Yoda pics.

    Poništi
  12. proslijedio/la je Tweet
    23. sij

    250M customer service & support records exposed due to misconfiguration of an internal database. 14 years of conversation with Microsoft 👉

    Poništi
  13. proslijedio/la je Tweet
    21. sij

    We’ve had a , and now we’ve got the , so clearly it’s time for me to start drafting up my ultra hands-on causal inference text, .

    Poništi
  14. proslijedio/la je Tweet
    18. sij

    Open Syllabus Project Open Syllabus is a non-profit organization that maps the curriculum of higher education. Database of / stats from 7M class syllabi 👏

    Poništi
  15. proslijedio/la je Tweet
    Poništi
  16. proslijedio/la je Tweet
    17. sij

    As someone with a nascent interest in causal inference, I agree with this sentiment. I think when most ML folks hear causal inference, they think "learning the causal structure of the world from data". This is actually causal discovery, and is much harder.

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    14. sij

    Hey / Grounded Language folks -- VLN is now in Habitat. Instruction following ("Go outside the room, stop at the brown door") with continuous state-space navigation. Thanks and !

    Poništi
  18. proslijedio/la je Tweet
    11. sij

    Unbelievable—7 years today. RIP my darling boy.

    Poništi
  19. proslijedio/la je Tweet
    12. sij

    Oldies but goldies: Robert May, Simple mathematical models with very complicated dynamics, 1976. The logistic map is the simplest dynamical system which exhibits bifurcations toward chaotic behavior as a function of its parameter r.

    Poništi
  20. proslijedio/la je Tweet
    12. sij

    I have to disagree with this. PowerPoint is Turing Complete, so it can be used to perform any decidable computation. Conclusion: people are just using it for the wrong things, like giving presentations

    Poništi
  21. proslijedio/la je Tweet
    10. sij

    week #2. 🥠💬 "Nobody actually knows what 'Digital' is."

    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:

    ·