Tweetovi

Blokirali ste korisnika/cu @KordingLab

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

  1. How can neuroscientists respond to the climate emergency?

    Poništi
  2. Learn modeling, improve your data science, learn to better answer real questions. Clarity. And improve your python skills too. If you are in the broad sensorimotor field consider attending our Cosmo 2 week summer school.

    Poništi
  3. prije 23 sata

    “Judgments of effort for magical violations of intuitive physics” or “how much harder is it to conjure a frog?” This is my new favorite Tomer paper

    Poništi
  4. By far the best introduction to probabilistic computation i have seen so far: I also love the juxtaposition of code and graphs. By /ht

    Poništi
  5. how well NTK describe actual ANN learning is still a matter of great debate.

    Prikaži ovu nit
    Poništi
  6. Neural Tangent Kernels (NTK) are a way of understanding neural networks in a certain domain (in the limit of N ->\infty, W0 not ~0). It is beautiful. And somewhat counterintuitive. Here are two nice write-ups aimed at explaining: ,

    Prikaži ovu nit
    Poništi
  7. Does the cerebellum contain internal models for self motion?

    Poništi
  8. 3. velj
    Odgovor korisnicima

    The shape of the loss surface changes rapidly in the early phase of training (e.g. ). NTK might work after some initial period of training, but not sure if it is a good model for the early phase of training? might have some thoughts :)

    Poništi
  9. Why are neural tangent kernels () not more central to the way people teach deep learning?

    Poništi
  10. 3. velj

    Large-scale analysis of the accuracy of the journal classification systems of Web of Science and Scopus

    Poništi
  11. Looking for a motor control summer school but our COSMO is not right for you? Go to the european summer school

    Poništi
  12. 1. velj

    i am proud to announce that i'm co-chairing a mini-symposium on Biology and Bioinformatics, submit your stuff!

    Poništi
  13. When it comes to causal inference and are two of my big heroes. When I grow up I want to be like them. To me their views are perfectly compatible. I don't understand why they seem to disagree.

    Poništi
  14. Interestingly, most students in my DL course didn't.

    Prikaži ovu nit
    Poništi
  15. and yes, all ML folks will probably know this ;)

    Prikaži ovu nit
    Poništi
  16. Intuition question. You draw two vectors from an n-dimensional isotropic Gaussian where n>>1. What is the typical angle between them?

    Prikaži ovu nit
    Poništi
  17. at long last, has an ISSN number: 2690-2664 which means that we can now apply to get onto medline etc. Thanks to whoever has been supporting us. And to everyone else: consider us for your papers:

    Poništi
  18. Google docs will show different document lengths on different browsers and even the same browser on different accounts. Even if you work simultaneously. Major problem when writing grants! Necessary to download pdf to find out. Ouch.

    Poništi
  19. This "presentation" contains some of the deepest insight into the nature of sciencing. Only that a real scientist would have more equations.

    Poništi
  20. Competition really does help if you want to improve your movements: Science using the game of chicken!

    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:

    ·