Santiago Cadena

@SantiagoACadena

Neuroscience, Machine Learning, Deep Learning, Vision Science. PhD student

Tübingen, Deutschland
Vrijeme pridruživanja: siječanj 2017.

Tweetovi

Blokirali ste korisnika/cu @SantiagoACadena

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

  1. Prikvačeni tweet
    15. stu 2019.

    Check out our work on modeling the mouse visual system with pretrained networks trained on static object recognition. We find that equivalent random networks are just as useful! Come by if you’ll be at . Colab of

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

    Beautiful extension of the generalized linear model for understanding the contribution of synaptic inputs to neural coding by , Fred Rieke, and

    Poništi
  3. proslijedio/la je Tweet
    31. sij

    Fresh on : What the zebrafish’s eye tells the zebrafish’s brain. We used 2P imaging and photolabeling to systematically chart the structure and function of zebrafish retinal ganglion cells in the live eye. . 👇

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

    This is a nice package for making pyplot animations more intuitive: All you do is call "camera.snap()" every time you re-do the plot.

    Poništi
  5. proslijedio/la je Tweet
    25. sij

    What an exciting couple of months for the field of connectomics! Thought it would be good to post a thread that captures recent progress--

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    22. sij

    Presenting: The most detailed map yet of the fruit fly brain. Janelia’s FlyEM team has traced the paths of some 25,000 neurons in the fruit fly brain and pinpointed the places where they connect. Now, all the data is available online for free.

    Poništi
  7. proslijedio/la je Tweet
    17. sij

    This review on normalizing flows is excellent. It's full of clear writing, precise claims, and useful connections.

    Poništi
  8. proslijedio/la je Tweet
    18. sij

    My paper is out on ! We explored movement signals in visual cortex and found a lot of surprising things.

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

    Our new adversarial attack published @ NeurIPS 2019 is now available for Foolbox and CleverHans! The attack is SOTA in L0, L1, L2 & Linf, needs close to no hyperparameter tuning & is less susceptible to some types of gradient masking. Blog post @

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

    New paper out! We provide evidence that feedforward convnets (ffCNNs) cannot implement human-like global computations because of their *architecture*, and not merely because of the way they are *trained*.

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    2. sij

    HNY and 1st discovery from mouse V1 serial section EM dataset! Largest wiring diagram yet btw identified cortical neurons Brain Science supported by MICrONS. 1/n

    Ovo je potencijalno osjetljiv multimedijski sadržaj. Saznajte više
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    23. pro 2019.

    Interested on the neural code of uncertainty and how likelihood functions are represented in the brain. Have fun over the holidays reading our paper with that just came out today

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

    Two papers accepted to ICLR 2020 -- a festivus miracle! Recurrent neural circuits for contour detection Disentangling neural mechanisms for perceptual grouping (Spotlight) With JK Kim, , Alekh Ashok, and 1/17

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    17. pro 2019.

    MetaInit: Initializing learning by learning to initialize They propose a strategy to automatically identify good initial parameters, and show that deep architectures *without* batch norm or residual connections can be trained to get near SOTA results. 🔥

    Poništi
  15. proslijedio/la je Tweet
    16. pro 2019.

    DeepInsight is a decoding framework for discovering and characterising the neural correlates of behaviour and stimuli in unprocessed biological data:

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    16. pro 2019.

    "The art of using t-SNE for single-cell transcriptomics" by and myself was published two weeks ago: . This is a thread about the initialisation, the learning rate, and the exaggeration in t-SNE. I'll use MNIST to illustrate. (1/16)

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    12. pro 2019.

    e2cnn: A comprehensive library for easy construction of rotation-reflection-translation equivariant CNNs in + thorough a experimental study of equivariant network architectures. By and .

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    11. pro 2019.

    Interested in a postdoc with us, on image processing in visual cortex and/or biological and artificial image segmentation? Consider this

    Poništi
  19. proslijedio/la je Tweet
    11. pro 2019.

    At Turing award winner Yoshua Bengio, Bernhard Schoelkopf , Nuria Olivier, , Max Welling, , Sepp Hochreiter and Turing award winner Yann LeCun are all

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

    Neural Tangents is a Python library designed to enable research into “infinite-width” neural networks. They provide an API for specifying complex neural network architectures that can then be trained and evaluated in their infinite-width limit. 🙉🤯

    Poništi
  21. proslijedio/la je Tweet
    6. pro 2019.
    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:

    ·