Shahab Bakhtiari

@ShahabBakht

postdoc in computational neuroscience and machine learning at Mila - McGill || exploring representations in brains and machines

Montreal, Canada
Vrijeme pridruživanja: travanj 2013.

Medijski sadržaj

  1. 23. pro 2019.
    Odgovor korisnicima

    or more like Silhouette Optical Illusion

  2. 15. pro 2019.

    The ANN was trained to map (eye position & retinal location) —> (world-coordinate location) using backprop They showed that the representation characteristics of 7a neurons (receptive fields and spatial gain fields) were reproduced by the hidden layer neurons of the trained ANN.

    Prikaži ovu nit
  3. 15. pro 2019.

    But how are these neurons computing this coordinate transformation? This paper by Zipser and Anderson was perhaps one of the first attempts to use ANN to understand a neuronal computation in the brain.

    Prikaži ovu nit
  4. 15. pro 2019.

    Some portion of 7a neurons (~57%) represent both eyes position and the retinal location of the object. These neurons were believed to be involved in the representation of object location.

    Prikaži ovu nit
  5. 15. pro 2019.

    David Sussillo mentioned this old paper by Zipser and Anderson in his talk at : It’s perhaps one of the first examples of comparing representations in the brain and artificial neural nets.

    Prikaži ovu nit
  6. 8. pro 2019.

    (3/n) Check out this paper by Van Rullen and Koch for a review: Also, these oscillations are shown to be locked to neural oscillations in the brain:

    Prikaži ovu nit
  7. 3. pro 2019.
    Odgovor korisnicima i sljedećem broju korisnika:

    Also I don’t understand how a simple reverse correlation can generate this clean receptive field maps for a conv5 neuron, especially if the claim is that these face selective neurons are view-point invariant.

  8. 2. pro 2019.

    An encoding model that incorporates the environment-to-retina geometry of 3D motion can explain the atypical structure of 3D motion tuning in MT

    Prikaži ovu nit
  9. 2. pro 2019.

    Some examples of atypical tuning of MT neurons in response to 3D motion

    Prikaži ovu nit
  10. 1. pro 2019.

    from the paper: “values in each weight kernel were randomly drawn from a Gaussian distribution that fit the weight distribution of the pre-trained state“

  11. 1. pro 2019.
    Odgovor korisnicima

    They checked for bunch of categories of objects, see panel C here:

  12. 24. stu 2019.

    So, if we regularize an ANN to have similar representations as those of mouse visual cortex, the ANN becomes more robust to adversarial attacks. Here is the most interesting part of the paper for me:

  13. 2. stu 2019.

    Example: an ANN trained to simulate vestibule-ocular reflex

    Prikaži ovu nit
  14. 2. stu 2019.
    Prikaži ovu nit
  15. 2. stu 2019.

    No, this isn’t from et al recent perspective on . This is David Robinson trying to make a similar point in 1992:

    Prikaži ovu nit
  16. 25. srp 2016.

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:

    ·