Abhishek Naik

@anaik96

PhD student at University of Alberta

Edmonton, Canada
Vrijeme pridruživanja: studeni 2015.

Tweetovi

Blokirali ste korisnika/cu @anaik96

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @anaik96

  1. 19. sij
    Poništi
  2. 19. sij

    I have written about this in more detail here: If interested, this is the book!

    Prikaži ovu nit
    Poništi
  3. 19. sij

    Check out Alex in action in this small clip!

    Prikaži ovu nit
    Poništi
  4. 19. sij

    Would get bored and fool around — suggestive of sophisticated cognitive processes. E.g., when presented a silver object, he said the names of all the colours he knew except the correct colour — statistically highly unlikely.

    Prikaži ovu nit
    Poništi
  5. 19. sij

    Alex the parrot could add, understood the concept of zero, label objects and colors, had a functional use of 'no'. He even put two different words together to form a new word — called an apple ‘banerry’ because it tasted like a banana and looked like a large cherry.

    Prikaži ovu nit
    Poništi
  6. 19. sij

    So I just finished reading this cool book. Turns out, Grey parrots — non-primate, non-mammalian creatures with brains the size of a shelled walnut — have cognitive and linguistic skills on par with those of large-brained mammalian chimps and 5-year old humans. Wow...

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

    Consider: millions of years ago our antecedents gave a massive sacrifice of their left hemisphere. We lost a tremendous amount of short term memory and replaced it with Broca’s, Wernicke & the phonological loop. But why? So we can—talk. Thus chimpanzees can do this—we can’t:

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    18. pro 2019.
    Poništi
  9. proslijedio/la je Tweet
    17. pro 2019.

    Discounted Reinforcement Learning Is Not an Optimization Problem This paper by et al. presented at Optimization Foundations of RL workshop examined and questioned the role of discounting in great detail. The conclusions are quite interesting:

    Prikaži ovu nit
    Poništi
  10. 9. pro 2019.

    A bunch of new CIFAR AI chairs from all over the world share why they chose Canada 🇨🇦 to pursue their research.

    Poništi
  11. 21. stu 2019.

    Discounted reinforcement learning is fundamentally incompatible with function approximation for control in continuing tasks. To learn exactly why, check out our new paper (w/ Roshan Shariff, , and Rich Sutton):

    Poništi
  12. 11. stu 2019.

    Hope you have as much fun taking the course as we had making it! 👨‍🏫👩‍🏫📹🖥️📝

    Poništi
  13. proslijedio/la je Tweet

    Hello World! This account will share the latest news and updates about what the Reinforcement Learning and Artificial Intelligence (RLAI) Lab at the University of Alberta is up to. Let’s figure out intelligence!

    Poništi
  14. 12. lis 2019.

    Awesome job, team! It was so much fun! 😃⚽️✌️🎉 🏆

    Poništi
  15. 2. kol 2019.

    An amazing two weeks of mingling with the some of the brightest minds that will help shape the future of humanity! Ladies and gentlemen, by at .

    Poništi
  16. 2. kol 2019.

    An exciting future lies ahead – with AI 'a'mplifying our 'i'ntelligence. (4/4)

    Prikaži ovu nit
    Poništi
  17. 2. kol 2019.

    "It is often useful to think of people and AIs as similar – both are agents with goals, which may be compatible or conflicting". (3/4)

    Prikaži ovu nit
    Poništi
  18. 2. kol 2019.

    Maintaining a research journal helps in organizing our thoughts and sifting through them. (2/4) (pictured are all his journals, all the way from 1974!!!)

    Prikaži ovu nit
    Poništi
  19. 2. kol 2019.

    Rich Sutton brings the to a close with some insightful thoughts on the future of AI and advice for young researchers! (1/4)

    Prikaži ovu nit
    Poništi
  20. 31. srp 2019.

    Brilliant insights from Rich Sutton, Yoshua Bengio, and Martha White on the state of the AI research community, work-life balance, career choices, and much more at the at and !

    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:

    ·