Hidenori Tanaka

@Hidenori8Tanaka

Theoretical Physics, Neuroscience, Machine Learning Research Scientist at NTT Physics & Informatics Lab + , Ph.D. Views my own

Vrijeme pridruživanja: rujan 2018.

Tweetovi

Blokirali ste korisnika/cu @Hidenori8Tanaka

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @Hidenori8Tanaka

  1. Prikvačeni tweet
    21. stu 2019.

    New paper out on : “From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction” with fantastic collaborators , , , Stephen Baccus, .

    Poništi
  2. 11. pro 2019.

    Will be presenting our work this morning: Please drop by if you are at 10:45 AM—12:45 PM poster #152

    Poništi
  3. proslijedio/la je Tweet
    21. stu 2019.

    Deep learning achieved great success in modeling sensory processing. However, such models raise questions about the very nature of explanation in neuroscience. Are we simply replacing one complex system (biological circuit) with another (a deep net), without understanding either?

    Poništi
  4. proslijedio/la je Tweet
    13. stu 2019.
    Poništi
  5. proslijedio/la je Tweet

    Can model reduction with deep learning produce a meaningful causal understanding of the retina?

    Poništi
  6. proslijedio/la je Tweet
    31. lis 2019.

    When the system encourages most researchers to optimize for depth, there will be vast opportunities for the minority of researchers who are in a position to optimize for breadth.

    Prikaži ovu nit
    Poništi
  7. 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
  8. 23. lis 2019.

    Quantum supremacy using a programmable superconducting processor

    Poništi
  9. proslijedio/la je Tweet
    15. lis 2019.

    Excited to announce our new paper Emergent properties of the local geometry of neural loss landscapes with my great advisor ! We used a simple model to explain 4 surprising effects of local geometry of neural network landscapes.

    Poništi
  10. 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
  11. proslijedio/la je Tweet

    The last few months I have been at working with and Yoshua on problems in physics and machine learning. Riding the success of generative models in drug discovery, we encode and decode 3-D representations of crystal structures.

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    23. srp 2019.

    New research shows how can improve high-performance computing for solving partial differential equations, with potential applications that range from modeling to simulating fusion reactions. Learn all about it here ↓

    Poništi
  13. proslijedio/la je Tweet

    Universality and individuality in neural dynamics across large populations of recurrent networks . With fantastic collaborators , , , .

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    18. srp 2019.

    1/ New in w/ lab: : new opsin + multi-photon holography to image ~4000 cells in 3D volumes over 5 cortical layers while also stimulating ~50 neurons to directly drive visual percepts; data analysis and theory reveal…

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    3. srp 2019.

    Insects lay eggs of all shapes and sizes! This makes them a great system for exploring the way shape and size evolve. This non-technical thread highlights the findings of our new paper in by and me.

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

    New work out on arXiv! Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics (), with fantastic co-authors , , and . summary below! 👇🏾 (1/4)

    Prikaži ovu nit
    Poništi
  17. 13. lip 2019.

    Link to the paper posted on my website. (Thankfully, Physical Review allows this!)

    Prikaži ovu nit
    Poništi
  18. 13. lip 2019.

    Is there a theoretical analogy between ring attractor neural networks and Anderson localization in quantum systems? With David Nelson, we discovered a new class of random matrices whose eigenvectors are quasi-localized even with fully dense connections.

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    12. lip 2019.

    The schedule and papers for our ICML workshop "Theoretical Physics for Deep Learning" on Friday are now updated . We are looking forward to the discussions and hope you find the workshop fruitful!

    Poništi
  20. 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

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:

    ·