Lane McIntosh

@lmcintosh

graduate student in theoretical neuroscience at Stanford

Palo Alto, CA
Vrijeme pridruživanja: rujan 2008.

Tweetovi

Blokirali ste korisnika/cu @lmcintosh

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

  1. proslijedio/la je 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. proslijedio/la je Tweet
    5. lis 2019.

    Officially got tenure in Applied Physics ! This feat is really due to a brilliant, creative, and fun group of students and postdocs I have had the great fortune of working with over the years. And thanks to amazing colleagues and mentors at Stanford and beyond!

    Poništi
  3. proslijedio/la je Tweet

    We see more significant improvements from training data distribution search (data splits + oversampling factor ratios) than neural architecture search. The latter is so overrated :)

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

    🥁🥁🥁 🥁🥁🥁 🥁🥁🥁 please: We are excited to announce that Model 3 just earned a 5-star safety rating from ⭐️⭐️⭐️⭐️⭐️

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    6. svi 2019.

    The Pokémon paper is out! In this study, we scanned the brains of adults, who as children, became Pokémon experts. We find a region of their brain becomes uniquely responsive to , helping us get at why the brain is organized the way it is.

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    6. svi 2019.
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    29. tra 2019.

    The old car companies think what separates them from Tesla is that Teslas are electric. But they're also separated by the fact that Teslas are software, and that, they will discover, is an unbridgeable gulf.

    Poništi
  8. proslijedio/la je Tweet

    New blog post: "A Recipe for Training Neural Networks" a collection of attempted advice for training neural nets with a focus on how to structure that process over time

    Poništi
  9. proslijedio/la je Tweet

    So proud of the Tesla Autopilot team and very excited to see the the veil lifted on some of their work earlier today 👏 A number of people got to experience this:

    Poništi
  10. proslijedio/la je Tweet
    3. sij 2019.

    Please read 's post about the undesirable behaviors she has experienced in the field of ML & CS (the anecdote about her CS professor showing another female student how to use a mouse was pretty egregious). Let's all strive to create a welcoming environment for all.

    Poništi
  11. proslijedio/la je Tweet

    "Tesla's Navigate on Autopilot Hands-On: Road trip to CES 2019!" with NoA enabled and a nav path set, Autopilot automagically suggests & negotiates the right lane changes, takes the right forks, and overtakes slow vehicles while respecting passing lanes ✨

    Poništi
  12. proslijedio/la je Tweet
    19. pro 2018.

    Cards Against Machine Learning

    Poništi
  13. proslijedio/la je Tweet
    8. pro 2018.

    My new post for the Human Centered AI Initiative: a personal vision of how and other fields can work together to both understand biological intelligence and create artificial intelligence!

    Poništi
  14. 1. lis 2018.

    Wish more ML papers gave statistics on the success of their methods! "We observe that without Orthogonal Regularization, only 16% of models are amenable to truncation, compared to 60% when trained with Orthogonal Regularization."

    Poništi
  15. proslijedio/la je Tweet
    13. ruj 2018.

    Preprint of my new paper! We use to answer a fundamental question about the human brain: Why is visual cortex organized so consistently across people? Give it a read, and see how becoming a childhood expert with Pokemon leads to a new brain representation.

    Poništi
  16. proslijedio/la je Tweet
    1. kol 2018.

    I’m excited to announce that I’ll be joining the Statistics and faculty in summer 2019!

    Poništi
  17. proslijedio/la je Tweet
    1. kol 2018.

    Congrats Scott! Super excited to have you in the bay!!

    Poništi
  18. proslijedio/la je Tweet
    27. lip 2018.

    Guided evolutionary strategies: escaping the curse of dimensionality in random search. A principled method to leverage training signals which are not the gradient, but which may be correlated with the gradient. Work with .

    Prikaži ovu nit
    Poništi
  19. 22. lip 2018.

    If you're at come check out our talk in 30 min on RNNs for efficient video scene understanding from just labeled images! Ballroom F w/

    Poništi
  20. proslijedio/la je Tweet
    12. lip 2018.

    Woohoo yay ! So cool. +1 point for team ‘deep learning helps us understand the brain’ 😜

    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:

    ·