Edgar Y. Walker

@eywalker

Post-Doc and co-founder of - computational/experimental neuroscientist and machine learning researcher with passion in teaching and coffee

Vrijeme pridruživanja: prosinac 2009.

Tweetovi

Blokirali ste korisnika/cu @eywalker

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

  1. proslijedio/la je Tweet
    23. sij
    Odgovor korisniku/ci

    Oh you mean a no hidden layer deep neural network with only 1 sigmoidal output neuron? Why didn’t you just say so - instead of using obscure statistical jargon like “logistic regression?” :)

    Poništi
  2. proslijedio/la je Tweet
    24. sij

    Just got a very kind email from a university I applied to more than two years ago notifying me that I didn't get the job. I guess I can move on now.

    Poništi
  3. proslijedio/la je Tweet
    6. sij

    as educators we often don't do a great job teaching debugging. this is my favorite book on the topic: cc

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

    We are really happy to announce that our paper on 'Long-term stability of cortical population dynamics underlying consistent behavior' has finally appeared in Nature Neuroscience . A great collaboration with 1/n

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

    Really pleased to have a new preprint looking at distractor statistics in visual search with . We looked for patterns identified decades ago, and then asked whether we could explain them with an optimal observer model.

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

    After getting published in ICLR as an Independent Researcher, I have received nearly 100 messages from others who are looking to do the same. So I wrote a blog post on why I decided to do it and my advice to others.

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet

    Likelihood functions encoded in the primary visual cortex better predict decision making under uncertainty than point estimates alone, consistent with PPC predictions. work with out today

    Prikaži ovu nit
    Poništi
  8. 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
  9. proslijedio/la je Tweet
    23. pro 2019.

    Sick and tired of holiday fun? A cure: our paper on V1! (and for the image: apologies to Jorge Cham )

    Poništi
  10. proslijedio/la je Tweet
    16. pro 2019.
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je 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
  12. 5. stu 2019.

    I’m really excited to see our paper finally out!! We combine in silico DNN with in vivo experiment to generate the most exciting inputs for the neurons and verify this back in vivo in a closed loop fashion!

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

    combine large scale recordings with to reveal a neuron's feature selectivity, such as most exciting inputs. Optimal stimuli for mouse V1 are not Gabors. in Lead by together with

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    4. lis 2019.

    Periodical reminder that .docx, .pptx, and .xlsx files are zip files. Change the file extension to .zip and VOILÀ! Embedded images neatly organized in a folder within.

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

    The NSF NeuroNex team has created a site that could become a useful forum for neuroscience: matchmaking, searchable discussions, question-answer. It's just a newborn baby right now, so it could use some love.

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

    New issue full of exciting work, and also Viewpoint on recording every neuron, NeuroViews on networking & PIing, & more Cover illustrates a Perspective by & coll. on the complementary interaction between brain sciences & machine learning 1/2

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    27. ruj 2019.

    Very happy to be among such a great and diverse selection of speakers at (). Come visit if you get the chance.

    Poništi
  18. proslijedio/la je Tweet
    25. ruj 2019.

    surpasses humans in many tasks () but does not generalize well to new situations. With we discuss ideas in how neuroscience can guide the quest for better generalization.

    Poništi
  19. 23. ruj 2019.
    Poništi
  20. 22. ruj 2019.

    With all the fun I had in Berlin attending conferences and doing a bit of sight seeing, I completely have forgotten I much I loathed Tegel airport, only to be reminded badly now as I tried to navigate the chaotic system...

    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:

    ·