Ed Henry

@EdHenry_

Sr. Scientist - Machine Learning . Things I like : Mathematics, Machine Learning, Causality, and Networks. In that order.

Vrijeme pridruživanja: siječanj 2011.

Tweetovi

Blokirali ste korisnika/cu @EdHenry_

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

  1. proslijedio/la je Tweet
    30. sij

    Pandas 1.0 is here! * Read the release notes: * Read the blogpost reflecting on what 1.0 means to our project: * Install with conda / PyPI: Thanks to our 300+ contributors to this release.

    Poništi
  2. proslijedio/la je Tweet

    The best explanation of how science works that I've seen in a long time (from ).

    Poništi
  3. proslijedio/la je Tweet
    23. sij

    Reminders of deadlines: Papers: abstracts due 30 Jan, papers due 6 Feb Workshops: due 14 Feb Tutorials: due 21 Feb details on each: Please submit (and circulate the calls!)

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

    Announcing new medical imaging dataset for an important clinical use case - and our first for ultrasound/ cardiac echo. Hope this release will help ML researchers engage in medical applications and improve diagnostics for patients worldwide. More to come in 2020 🤖

    Poništi
  5. proslijedio/la je Tweet
    21. sij

    I'm working on a new series of notebooks to teach probability and Bayesian statistics. The first notebook starts with a famous example of the conjunction fallacy, Tversky and Kahneman's Linda the banker. Want to play along at home?

    Poništi
  6. proslijedio/la je Tweet
    20. sij

    I analyzed compensation & level details of 19k tech workers to find answers to: 1. How long does it take for SWEs to reach a certain level? 2. Compensations across jobs/levels? 3. Do women get paid less than men in tech? 4. Is there a deadline for SWEs?

    Poništi
  7. proslijedio/la je Tweet
    9. sij

    We are organizing a workshop on Causal learning for Decision Making at along with , Jovana Mitrovic, , Stefan and . Consider submitting your work!

    Poništi
  8. 14. sij

    More progress on my latest lab addition. Some of the camera and servo control work is piped into Jupyter. Now for the TFRecords work and on to trying out some interesting grasping and manipulation projects. 🙂

    Poništi
  9. 9. sij

    the shit thing is i'd bet i'll reference this tweet some day as a point of truth for this build. 😂🙄

    Prikaži ovu nit
    Poništi
  10. 9. sij

    right after tweeting this it finally worked. pip freezing this bitch

    Prikaži ovu nit
    Poništi
  11. 9. sij

    Who else's entire day was eaten by python's dependency mgmt system(s)? 🙋‍♂️

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

    There's far too much focus on deepfakes and manipulated video and far too little focus on generated text. I cannot say this enough.

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

    First batch of Normcore stickers just went out to paid subscribers! If you sign up for a paid subscription and want a sticker, DM me. They’re on sale for real next week ☺️.

    Poništi
  14. proslijedio/la je Tweet
    7. sij

    Our paper "On the information bottleneck theory of deep learning" has been republished (with small edits) in J Stat Mech ML special issue: A wonderful collaboration with @laika117 Artemy Kolchinsky

    Prikaži ovu nit
    Poništi
  15. 5. sij

    Added a new toy to the lab last week. Still waiting on the gripper, but I have a vacuum to play with for now. 🙂

    Poništi
  16. 5. sij

    I've been exploring, while trying to understand, the limitations of induction through limitations of measurement recently and found this paper interesting. "Theoretical and practical limits of measurement" :

    Poništi
  17. proslijedio/la je Tweet
    2. sij

    People tweet all sorts of things about real numbers, especially when it comes to computation. I've studied the topic for years, and I often disagree with such statements. Let me address just one such statement: "A computer cannot represent all reals, only the computable ones."

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    3. sij

    ”Imagine that DNA had a diameter of 1 m. Then the complex that copies the DNA would be the size of a truck. It would be traveling at a speed of 500 km/h. It would be making a delivery on both sides of the street every ~10 cm. It would finish its journey in 40 min... 1/2

    Prikaži ovu nit
    Poništi
  19. 4. sij

    Consult your resident domain expert when applying machine learning to a problem. Function approximation has this bad side effect of finding "fits" that might be ill-conditioned that which can only be exposed via experimental setup.

    Poništi
  20. proslijedio/la je Tweet
    3. sij

    no line in this video is actually changing size

    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:

    ·