James Whittington

@jcrwhittington

Neuroscience, machine learning, physics, medicine.

Vrijeme pridruživanja: veljača 2012.

Tweetovi

Blokirali ste korisnika/cu @jcrwhittington

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

  1. Prikvačeni tweet
    13. sij 2019.

    Check out my Neurips talk - - starts at 23:42 :)

    Poništi
  2. proslijedio/la je Tweet
    9. pro 2019.

    I'm thrilled to be starting my research group in at . Interested in deep learning theory and neuroscience? I'm looking for team members!

    Poništi
  3. proslijedio/la je Tweet

    Would love it if candidates who know they can’t win would endorse candidate and vice versa. Only takes a few to start something big

    Poništi
  4. proslijedio/la je Tweet
    2. stu 2019.

    Our latest from . Using a "task remapping" paradigm, we show reinforcement learning problems are abstracted, and these abstract representations can be generalised to new problems.

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

    Human replay constructs entirely novel sequences in an inferred order determined by abstract structural knowledge. Replayed sequences comprise also representations of the abstract structure. An amazing MEG study by Liu, Dolan, Kurth-Nelson &

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

    Sorry, sorry. Don't blame Paul. He had to have me on as part of a series for . Everyone's heard enough of me, but if you want to hear about cool work from (Tolman Eichenbaum Machine) and (Human replay), you might find the second half ok

    Poništi
  7. proslijedio/la je Tweet
    20. svi 2019.

    This guy again?! and I discuss his Tolman Eichenbaum machine to generalize knowledge, using MEG to measure knowledge abstraction via replay, his upcoming keynote address at , being inspired, giving talks in general, and more.

    Poništi
  8. proslijedio/la je Tweet
    19. tra 2019.

    How might our brains approximate back-propagation? Rafal Bogacz enlightens us on the many ways via his review w/ . Plus more free energy principle talk, why he's so infatuated with FEP, how diff brain areas do diff things (novel!) & more.

    Poništi
  9. proslijedio/la je Tweet

    🗣️📢 Folks! Please save the date for the Conference on Cognitive Computational Neuroscience 2019! 🧠🖥️👩‍🔬🤖 When: September 13–16, 2019 Where: Berlin, back-to-back with the Bernstein Conference

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    20. velj 2019.
    Poništi
  11. proslijedio/la je Tweet
    3. velj 2019.
    Poništi
  12. proslijedio/la je Tweet
    29. sij 2019.

    Can the brain implement backprop? Check out what and Rafal Bogacz have to say on the matter in this great review!

    Poništi
  13. proslijedio/la je Tweet
    29. sij 2019.

    V cool new review of biological backprop algorithms.

    Poništi
  14. 29. sij 2019.

    New review discussing current models of how brain networks could implement the back-propagation algorithm! Work with Rafal Bogacz. We discuss models from Yoshua Bengio, Walter Senn and others :)

    Poništi
  15. proslijedio/la je Tweet
    29. sij 2019.

    Can neurons do backprop? A review of how neural circuits could approximate the error back-propagation algorithm. The dynamics and plasticity of the models can be described within a common framework of energy minimisation. By & Rafal Bogacz

    Poništi
  16. proslijedio/la je Tweet
    22. sij 2019.

    Dear organisers. Cosyne won't be any fun if you don't let me come. Who will bring the Whisky?

    Poništi
  17. proslijedio/la je Tweet
    18. sij 2019.

    Pleased as punch to see 💫 letters 💫 published by & v proud to have translated them

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    13. sij 2019.

    The awesome James Whittington discussing structural generalisation at NeurIPS.

    Poništi
  19. proslijedio/la je Tweet
    17. pro 2018.

    Newly minted Dr Tim Muller ⁦

    Poništi
  20. 4. pro 2018.
    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:

    ·