Peng Liu

@PengRocMind

Ph.D. candidate in neuroscience and biomedical image using machine learning at

United States
Vrijeme pridruživanja: ožujak 2018.

Tweetovi

Blokirali ste korisnika/cu @PengRocMind

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

  1. 30. sij

    “Taking inspiration from distributional reinforcement learning in artificial intelligence, the researchers analysed neuronal recordings from the mouse midbrain and found that instead of the brain representing the future as a single mean, it uses a probability...” lovely work!

    Poništi
  2. proslijedio/la je Tweet
    26. sij

    This looks pretty interesting Neurons in Visual Cortex are Driven by Feedback Projections when their Feedforward Sensory Input is Missing

    Poništi
  3. 26. sij

    Recurrent feedback can improve deep neural network and our brains to better identify objects from DiCarlo lab

    Poništi
  4. proslijedio/la je Tweet
    20. sij

    Given the smoothness of videos, can we learn models more efficiently than with ? We present Sideways - a step towards a high-throughput, approximate backprop that considers the one-way direction of time and pipelines forward and backward passes.

    Poništi
  5. proslijedio/la je Tweet
    18. sij

    I am frequently asked by students about transition into "independence in science", the ability "to do things alone". I want to challenge that concept and argue that framing training as path towards "independence" is confusing for many. True "independence"="interdependence"(1/n)

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

    A fascinating new Nature paper from hypothesizes (and shows supporting data!) about how state of the art reinforcement-learning algorithms may explain how dopamine works in our brains.

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

    University courses at bachelor degree level seriously need to address their lack of coding courses. These should be mandatory for all sciences, especially social sciences, and part of every research methods course. It should be integral to the teaching of statistics.

    Prikaži ovu nit
    Poništi
  8. 11. sij

    The intuitive interactions between brain and physics! Interesting!

    Poništi
  9. proslijedio/la je Tweet
    6. sij

    A prospective clinical trial of to determine intraoperative in near real time using label-free imaging: impressive rapid, accurate results by & collaborators

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

    Brains are amazing. Our lab demonstrates that single human layer 2/3 neurons can compute the XOR operation. Never seen before in any neuron in any other species. Out now in . Congrats Albert, Tim  & CO

    Poništi
  11. proslijedio/la je Tweet
    31. srp 2019.

    The latest from Martin Haesemeyer, comparing artificial and biological neural networks - now published in Neuron! We find striking parallels and use the ANN to make testable predictions about the biology.

    Poništi
  12. proslijedio/la je Tweet

    While Bayesian models provide good accounts of perceptual decisions, it is unclear how their components are represented in the brain. Here, the authors show that uncertainty decoded from visual cortex helps predict behavior.

    Poništi
  13. proslijedio/la je Tweet
    12. lis 2019.

    1/ New tweeprint from my lab! This one is work done by the amazing , and was inspired by the work of and (who was also a collaborator in this project).

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet

    My talk at China on latest works on generative models that I have been involved in both at and Some topics: competitive optimization, disentanglement in StyleGAN, flow-based models for turbulence modeling, CNN-feedback networks

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

    Amazing new study from led by & on SOM interneurons being critical to emotion discrimination! The nVistaᵀᴹ + nVokeᵀᴹ are proud to be part of it.👏Read more- .

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

    On some level, I would have been shocked if this didn't exist in the brain, but cool to see it demonstrated! Invariant representations of mass in the human brain:

    Poništi
  17. 16. pro 2019.

    nice! I've been thinking of this for a while. Will be much helpful

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

    What does it mean to understand language? We argue that human-like understanding requires complementary memory systems and rich representations of situations. A roadmap for extending ML models toward human-level language understanding:

    Prikaži ovu nit
    Poništi
  19. 14. pro 2019.

    the points" Raising research quality will require collective action. Institutions must act together to reform research culture. If we want researchers to work well in large collaborations, we need to train them in communication skills and collective self-scrutiny"

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

    I have a new paper with Dan Rubin & on biorxiv! "A simple circuit model of visual cortex explains neural and behavioral aspects of attention" We replicated findings (and figures) from several experimental papers, all using the same basic 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:

    ·