Tweetovi

Blokirali ste korisnika/cu @hisspikeness

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

  1. Prikvačeni tweet
    17. lis 2019.

    Today we introduce two large spike-based data sets for the quantitative comparison of spiking neural network architectures and neuromorphic hardware. Creative Commons License. Data: Paper:

    Poništi
  2. proslijedio/la je Tweet
    29. sij

    Today I will be teaching my undergrad course "How to build a brain from scratch" for the 2nd year running. I've put the materials online - include a document with all lecture slides and notes, which is about as long as a decent novel. Enjoy!

    Prikaži ovu nit
    Poništi
  3. 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
  4. proslijedio/la je Tweet
    6. pro 2019.

    How does transfer learning for medical imaging affect performance, representations and convergence? Check out the blogpost below and our paper for some of the surprising conclusions, new approaches and open questions!

    Poništi
  5. 7. stu 2019.

    Our Surrogate Gradient Learning tutorial paper now appeared in IEEE SPM . For those who are paywalled (ironically this includes me) here is the preprint

    Poništi
  6. 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
  7. proslijedio/la je Tweet
    21. lis 2019.

    Happy to present the latest co-production of the Ferraguti & Lüthi labs with - VIP interneurons indeed are "very important players" for learning!

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    7. lip 2019.

    Single-trial variability in spike timing, even in small amounts, can mask striking firing patterns. The raster plots below show the same data (a neuron from rat motor cortex). The only difference is that we’ve re-sorted the trial ids with the help of a simple model.

    Prikaži ovu nit
    Poništi
  9. 29. svi 2019.

    Coming up: EPFL Neurosymposium “Neuroscience meets Deep Learning” July 8th to July 9th 2019 in Lausanne, Switzerland

    Poništi
  10. proslijedio/la je Tweet
    9. svi 2019.

    Exciting work in the evolution approach and meta learning! — blowing us away with neuron local meta learned update rules and their surprising generalization ability (across datasets, data modalities, and architecture!!)

    Poništi
  11. 29. tra 2019.

    Two days left to apply for PhD positions at the and at the FMI

    Poništi
  12. proslijedio/la je Tweet
    16. tra 2019.

    Interested in the latest developments in theoretical neuroscience? Want to learn and discuss how tools from math and physics are applied to neural networks? Want to visit the historic workplace of Gauss, Webber, Planck, Hilbert, Minkowski? Register now!

    Poništi
  13. 5. ožu 2019.

    Want to play with spiking neural networks trained with surrogate gradients? Here is a simple tutorial in PyTorch which should give you everything you need to get started

    Poništi
  14. proslijedio/la je Tweet
    1. velj 2019.

    The (me) is looking to fill several postdoc positions in the near future. If you are good at neuro-math-coding & interested in neuronal network dynamics, memory, plasticity & machine learning, drop me a line, or chat me up at RT please.

    Poništi
  15. 31. sij 2019.

    Short review/tutorial on different approaches for training spiking neural networks using surrogate gradients with and Hesham. Includes a section that elucidates the connection of SuperSpike and RTRL. Feedback welcome.

    Poništi
  16. 28. sij 2019.

    I should correct myself: It is rather a supervised similarity matching loss.

    Prikaži ovu nit
    Poništi
  17. 28. sij 2019.

    Very encouraging results from extending the notion of layer-wise "local error signals" () with an unsupervised similarity matching loss.

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

    Workshop: Why Spike? Understanding the power and constraints of spiking based computation in biological and artificial neuronal networks featuring , , and more!

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

    My new post for the Human Centered AI Initiative: a personal vision of how and other fields can work together to both understand biological intelligence and create artificial intelligence!

    Poništi
  20. 30. stu 2018.

    Neat work on how the dynamical repertoire of a recurrent network changes by tuning neuronal gains only. Somewhere in-between reservoir computing and training all parameters of an RNN.

    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:

    ·