Tweetovi

Blokirali ste korisnika/cu @BellecGuill

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

  1. proslijedio/la je Tweet
    28. sij

    Logothetis et al. are moving to . The new International Center for Primate Brain Research (sic) in Shanghai will host up to 6,000 non human primates. Most of his collaborators will leave Tubingen and move there, with family.

    Poništi
  2. proslijedio/la je Tweet
    23. sij

    I personally hope that something weird and paradigm changing, like spiking neural nets or reservoir computing will become a thing in machine learning in the roaring '20s.

    Poništi
  3. proslijedio/la je Tweet
    15. sij

    Did you know you can write your simulation with and run it up to 400x faster on GPU with GeNN using brian2genn? Check out our new paper with and .

    Poništi
  4. proslijedio/la je Tweet
    14. sij

    The Panopticon is a prison designed by philosopher Jeremy Bentham in 1791. The design allows all prisoners to be observed by a single guard, without the inmates being able to tell whether they are being watched, motivating them to act as though they are being watched at all times

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    8. sij

    Oh my god. Watch this guy who thinks he's doing something good with AI.

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

    A solution to the learning dilemma for recurrent networks of spiking neurons, et al. They show that spiking neural nets (CNN+LSTM) can learn via “e-prop” to play Atari games. Cool work presented at Biological RL Workshop at 🧠

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    10. ruj 2019.

    What does deep learning bring to neuroscience? What is the role of theory in the age of deep learning? Answers (and more questions) in our workshop "Brain Against the Machine", Berlin, Sep 17&18 at . Full schedule:

    Prikaži ovu nit
    Poništi
  8. 9. kol 2019.

    We are releasing our App. for chord recognition! 🎉🎸🎹🤳 It's called Chord AI and it's real time. I wanted to play music but I got to be a nerd. Beautiful! Thanks for the hard work Link on apple store: Android version planned for January.

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

    Learning to Learn on Neuromorphic Hardware: - Neuromorphic hardware (mixed-signal) - Transfer learning - Meta-plasticity - Spiking neural networks

    Poništi
  10. proslijedio/la je Tweet
    2. ožu 2019.

    Kudos to whoever on the team wrote their Adam optimizer docs :) Thanks for mentioning `eps`, that much under-appreciated hyperparameter! (This is a slide from a talk I'm doing at Berkeley tomorrow about training neural nets.)

    Poništi
  11. proslijedio/la je Tweet
    2. ožu 2019.

    Two posters elucidating early visual system hallmark properties, w/ & : 1) Why are receptive fields concentric in the retina and oriented in primary visual cortex? We address this question with an anatomically constrained deep CNN.

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    1. ožu 2019.

    Spread over five years, the competition focused on processes for digital information. Now the jury has selected TU Graz’s as a means of secure encryption for the internet of things.

    Poništi
  13. 30. sij 2019.

    A biological alternative to BPTT and RTRL - Broadcast/feedback alignment for recurrent spiking networks (RSNNs) - One-shot learning in RSNNs - Eligibility traces enhance synthetic gradients and BPTT With @diegosunshine1

    Poništi
  14. 17. ruj 2018.

    The paper was accepted at Thanks to the co-first authors and Thanks to our supervisors and Woflgang Maass

    Prikaži ovu nit
    Poništi
  15. 22. svi 2018.

    - Recurrent spiking neural networks perform at the level of LSTMs. - Meta-learning in spiking RNN provide a new model for fast learning in the brain: without synaptic plasticity. Check out this major update of our paper: @guillweb

    Prikaži ovu nit
    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:

    ·