Rajeev

@rvrikhye

Vision, cognition, AI researcher. 🤖➕🧠➕💻➕👁 Alum of and Adventurer; Food enthusiast

SF Bay Area
Vrijeme pridruživanja: srpanj 2016.

Tweetovi

Blokirali ste korisnika/cu @rvrikhye

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

  1. 25. pro 2019.
    Poništi
  2. proslijedio/la je Tweet
    6. pro 2019.

    You'd think a generative model should answer different queries but deep learning models like VAEs are trained to answer just one type of query! We introduce a method called query-training that creates an inference network that can answer novel query types.

    Poništi
  3. 31. lis 2019.
    Poništi
  4. proslijedio/la je Tweet
    28. lis 2019.

    1/ SciTwitter: I'm very excited to share our new Perspective article out in Nature Neuroscience today!

    Prikaži ovu nit
    Poništi
  5. 12. lis 2019.
    Poništi
  6. proslijedio/la je Tweet
    13. ruj 2019.

    Our 2nd paper introduces Memorize-Generalize, an algo for fast and flexible learning of sequential structure: it can rapidly memorize sequences as they are encountered, and gradually generalize as more data is accumulated.

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    5. ruj 2019.

    The preprint of my commentary on 'Building machines that work like the brain' is now on arxiv. It distinguishes between AGI & AUI and uses 'airplanes don't flap wings' as the reason to look to the brain for building

    Poništi
  8. proslijedio/la je Tweet
    5. kol 2019.

    A Mathematician's Way* of Converting Miles to Kilometers • 1 mi ≈ 1.609 km • The ratio of consecutive Fibonacci numbers Fₙ₊₁/Fₙ tends to the golden ratio φ ≈ 1.618 as n increases So Fₙ mi ≈ Fₙ₊₁ km *This is how I do it 😅

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    27. kol 2019.

    Our paper proposes a new model for cognitive maps in the hippocampus which involves learning higher-order graphs of event sequences. It can explain flexible planning, route-dependence of place cells, and subsumes successor representations.

    Poništi
  10. 6. kol 2019.

    Fantastic article, highly recommend reading.

    Poništi
  11. proslijedio/la je Tweet
    18. srp 2019.
    Odgovor korisnicima i sljedećem broju korisnika:

    like what you hear? we are hiring neuroscientists! your biological and technological distinctiveness will be added to our own

    Poništi
  12. proslijedio/la je Tweet
    15. srp 2019.

    PUBLIC SERVICE ANNOUNCEMENT: You must cross-validate sorted plots!! E.g. peak-latency sorted colormaps of neural activity. Otherwise you WILL find "sequences" out of random noise. Don't believe me? A proof in four lines. Anyone feel like you have seen the last panel before?

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    5. srp 2019.

    Imagine if this happened to you 🦍💗

    Poništi
  14. proslijedio/la je Tweet
    5. srp 2019.

    Anecdotally, this kind of thing probably has some value for neuroscience too:

    Poništi
  15. 25. lip 2019.
    Poništi
  16. proslijedio/la je Tweet
    12. lip 2019.

    The special issue on 'Machine Learning, Big Data and Neuroscience' in Current Opinion is out now, with lots of interesting articles (and ours with and ...) -- thanks and Maneesh Sahani for organizing this!

    Poništi
  17. 8. lip 2019.

    Wow, the thalamus is the center of the brain!

    Poništi
  18. proslijedio/la je Tweet
    5. lip 2019.

    The first application of our latest theory of object manifolds on DCNNs is online. We characterize how ImageNet-based object manifolds untangle across layers of DCNNs, by connecting the changes in object manifold's geometry and the resultant improvement in manifold capacity.

    Poništi
  19. 30. svi 2019.

    . you have been breaking my heart since 1999

    Poništi
  20. 30. svi 2019.

    Time to rewrite the neuroscience textbook - VTA dopamine neurons encode much more than reward prediction error!

    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:

    ·