Artificial Cognitive Systems

@artcogsys

The Artificial Cognitive Systems lab aims to uncover the computational principles that govern natural and artificial intelligence.

Nijmegen, Nederland
Vrijeme pridruživanja: travanj 2016.

Tweetovi

Blokirali ste korisnika/cu @artcogsys

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

  1. proslijedio/la je Tweet
    prije 2 sata

    I am happy to share the paper: Automatic structured variational inference. An algorithm for constructing rich variational distributions for arbitrary probabilistic programs. Currently implemented in Brancher, hope to see it on Edward and Pyro.

    Poništi
  2. proslijedio/la je Tweet
    4. velj

    Automatic structured variational inference.

    Poništi
  3. proslijedio/la je Tweet
    3. velj

    We are happy to share our joint work on the Indian chef process. A nonparametric prior for directed Bayesian networks. You can use this process to infer the existence of new variables affecting your observations.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    10. sij

    New preprint from the lab: "Individual differences among deep neural network models." Work with , , and Courtney Spoerer. below. 1/7

    Prikaži ovu nit
    Poništi
  5. "Temporal Factorization of 3D Convolutional Kernels" Our most recent pre-print -- starring , , , and

    Poništi
  6. proslijedio/la je Tweet
    14. pro 2019.

    My last piece of PhD work with was just (finally) out . Thanks for providing the rat hippocampus data. Here we showed the distinct theta-slow/fast gamma directional couplings in the CA1-CA3 circuit.

    Poništi
  7. proslijedio/la je Tweet
    6. pro 2019.
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    4. pro 2019.

    [News] Preferred Networks (PFN) migrates its DL platform from Chainer to PyTorch. Chainer moves to maintenance support. PFN jointly works with Facebook and the OSS community to develop PyTorch. For more information, please look at the news release:

    Poništi
  9. New paper! -- Deep Learning Improves Automated Rodent Behavior Recognition Within a Specific Experimental Setup:

    Poništi
  10. proslijedio/la je Tweet
    25. stu 2019.

    The study’s findings imply that, because of these type of eye movements, researchers should be even more careful in drawing conclusions and that there is a need to record eye movements in new experimental work.

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    25. stu 2019.

    Even though we did not record brain activity, we emphasize that such systematic eye movements will likely leak through in brain activity and have serious problematic consequences for brain research too.

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    25. stu 2019.

    Importantly, when the same participants actively view the gratings while attempting fixation, the observed eye movements show a systematic pattern unique for every orientation, easily picked up by a decoder.

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    25. stu 2019.

    We show that the orientation of the gratings cannot be decoded from eye movement traces under passive viewing, like in our previous work.

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    25. stu 2019.

    We recorded eye movements while participants perceived oriented gratings. They either passively or actively perceived them by performing a detection task. Importantly, in both cases participants were asked to fixate on a dot presented at the center of the screen.

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    25. stu 2019.

    Out now in : “Evidence for confounding eye movements under attempted fixation and active viewing in cognitive neuroscience” with , , , and Rob van Lier from and !

    Prikaži ovu nit
    Poništi
  16. Poništi
  17. proslijedio/la je Tweet
    20. stu 2019.

    I am hiring a graduate student to join our group at the (full position, 4 years funding)! Please apply if you are interested in working on machine/deep learning and visual cognitive neuroscience. Details here: Please share/RT far and wide!

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    19. stu 2019.

    Because our society faces complex challenges of Artificial Intelligence, we reach out for interdisciplinary collaboration. We encourage industry and governmental organizations to join our first Radboud AI Network Event () at January 23, 2020 in Nijmegen.

    Poništi
  19. We have a new PhD position in AI for Health together with the ICU department of the Radboud University Medical Centre. Monitoring and prediction in the ICU using state of the art machine learning methods!

    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:

    ·