André Marques-Smith

@TheFrontalLobe_

Sir Henry-Wellcome Postdoctoral Fellow, London, SWC. Neuroscience and AI. Budding Neural Programmer. 🇵🇹🇬🇧

London, England
Vrijeme pridruživanja: kolovoz 2015.

Tweetovi

Blokirali ste korisnika/cu @TheFrontalLobe_

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

  1. Prikvačeni tweet

    Thread 1/ A few words on our "Recording from the same neuron with high-density CMOS probes and patch-clamp: a ground-truth dataset and an experiment in collaboration."

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    4. velj

    Does anyone know a simple, *fast* way to display a numpy array as pixels, e.g. for watching cellular automata in real time? (I usually use pygame but it has some weird issues on retina displays, so I'm wondering if there's a better option.)

    Prikaži ovu nit
    Poništi
  3. 3. velj

    Agreed. Sober and thorough critique amidst the hype. Critical and alternative voices like are important in preventing groupthink and moving the field forward.

    Poništi
  4. 2. velj

    Boa ideia e muito verdade. Visitar Oslo depois de ler Jo Nesbo deu um colorido e contexto extra à cidade.

    Poništi
  5. 2. velj
    Poništi
  6. 2. velj

    Interesting, but I'd have imagined Google maps can tell the 99 signals are coming from the same place and moving together. Suspicious. How does gmaps deal with people on buses then? Surely it doesn't "see" 50 cars and a virtual traffic jam.

    Poništi
  7. proslijedio/la je Tweet
    30. sij

    Hey people! It’s online! I am SO delighted to share my latest and favourite piece of work: Courtship behaviour reveals temporal regularity is a critical social cue in mouse communication . Work supported by

    Poništi
  8. 30. sij

    The term 'safado' in Brazilian Portuguese is a very rich word indeed 🤣

    Poništi
  9. 28. sij

    Wow, PyTorch is great. Feel much more at home with eager execution than thinking in terms of computation graphs.

    Poništi
  10. proslijedio/la je Tweet
    Odgovor korisnicima

    I remember a conference talk given by a coronavirus expert during the SARS outbreak. "Wow," he said as he scanned the packed ballroom, "This is more people than I've ever spoken to before...." Then he continued: "...in my entire career, combined."

    Poništi
  11. proslijedio/la je Tweet
    26. sij

    Are partial derivatives the computational primitives of deep neural networks? via

    Prikaži ovu nit
    Poništi
  12. 22. sij

    I've noticed this in a lot of papers. There is often a blog post with a TL; DR and a nice toy implementation to okay with, along with the codebase. It's great.

    Poništi
  13. 22. sij

    Linear Algebra is actually quite beautiful and intuitive when explained spatially as does. I always thought I didn't have the right type of brain for maths but so many things are starting to make sense now. I'm actually excited. Thank you!

    Poništi
  14. proslijedio/la je Tweet
    22. sij

    My blogpost on how & why we use convolutional neural networks as a model of the visual system is probably the most read thing I've ever written and it's now been expanded & updated into a proper review article, complete with 136 references & 5 new figures!

    Poništi
  15. proslijedio/la je Tweet
    17. sij

    I'm speaking at the ICN on monday (3:15) - if you want to know about grid cells, uncertainty or discovering neural correlates with AI then that's the place to be!

    Poništi
  16. proslijedio/la je Tweet
    15. sij
    Odgovor korisniku/ci
    Poništi
  17. 15. sij

    A tremendous resource for anyone doing extracellular recordings. Great stuff!

    Poništi
  18. 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
  19. proslijedio/la je Tweet
    11. sij

    On the Relationship between Self-Attention and Convolutional Layers This work shows that attention layers can perform convolution and that they often learn to do so in practice. They also prove that a self-attention layer is as expressive as a conv layer.

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

    We have a new paper on , up now. I wanted to call it “Crushing the Hopfield limit”, but, sadly, I was overruled. Not much time today (flying to the , yay!), but in brief, WE CRUSH IT (the hopfield limit) (and in a cool cool way) (i’m excited) Ready?

    Prikaži ovu nit
    Poništi
  21. proslijedio/la je Tweet
    9. sij

    🚨The next instalment of our PFC thalamo-cortical project is out on bioRxiv 🚨 It’s got interneurons, rabies tracing, optogenetics, 2 types of disinhibition and cell-type-specific dendritic calcium signalling. Summary below 1/n

    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:

    ·