Sam Finlayson

@IAmSamFin

MD-PhD Candidate, working on machine learning for (bio)medicine at + . Past: (BA, MS)

Boston, MA
Vrijeme pridruživanja: listopad 2014.

Tweetovi

Blokirali ste korisnika/cu @IAmSamFin

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

  1. Prikvačeni tweet
    14. lip 2019.

    Meta-pin👇

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    prije 15 sati

    Since everyone's so read up on R0 (reproductive number) of diseases due to the now, thought I'd do a quick thread explaining herd immunity Both concepts are closely related!

    Prikaži ovu nit
    Poništi
  3. prije 12 sati

    Post on the history of Machine Learning, its relationship with statistics, and some common land mines in public discourse about the field

    Prikaži ovu nit
    Poništi
  4. 2. velj

    PS Thanks for prompting me to write it, and for commenting on my raw initial thoughts yesterday.

    Prikaži ovu nit
    Poništi
  5. 2. velj

    To be clear, I’m under no illusion that this post will change anyone’s mind about anything. It was written quickly, and reasonable can disagree with many of my points. Rather, I hope it rids me of desire to waste time on toxic instantiations of this debate in the future. 3/3

    Prikaži ovu nit
    Poništi
  6. 2. velj

    Here are some thoughts on stats “vs” ML. Rel btwn the fields, why debates on topic are almost always fundamentally flawed, why I think there’s so much talking past each other, and why I wish we could focus instead on *specific* methods + problems 2/3

    Prikaži ovu nit
    Poništi
  7. 2. velj

    There is one topic that’s always my twitter Achilles heel: stats “vs” ML debates. Their existence frustrates me and I can never help myself. So, a few months back, I promised myself that the next time one came up, instead of entering the scrum, I’d just write a post. So.. 1/3

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    2. velj
    Poništi
  9. proslijedio/la je Tweet
    31. sij

    So I set up a blog to share 'non-traditional research outputs'. First up is the code from yesterday to make an interactive filtered list of predicted ligands

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

    integrates really nicely with interactive widgets. Here's an example filtering predicted ligands for a target of interest by synthetic accessibility, drug-likeness, or similarity to prior art drugs

    Poništi
  11. 29. sij

    I’ve tweeted this several times but please sign and amplify. Access to papers is often quite literally a matter of life+death for families affected by rare disease. It’s difficult for me to overstate how repugnant I find the opposition to this from the publishing industry.

    Poništi
  12. proslijedio/la je Tweet

    “Polygenic scores are revolutionary because they are causal in only one direction. They don’t drop because tests make you nervous or rise because you grew up rich. They’re impervious to racism and other forms of prejudice.”

    Poništi
  13. 28. sij

    Really interesting thread on the disturbing transformation of an EHR company

    Poništi
  14. proslijedio/la je Tweet
    28. sij

    Ever wonder, are there any machine learning applications actually being used to care for patients in health care? If yes, check out our new review: In it, we ( ) present 21 ML products translated into clinical care THREAD

    Prikaži ovu nit
    Poništi
  15. 28. sij
    Poništi
  16. proslijedio/la je Tweet
    27. sij
    Odgovor korisniku/ci

    I'd love to see how any normal ct head detector performs on something rare and subtle like leptomeningeal disease. Until someone shows me conclusively otherwise (even a single example), I'm going to keep ranking "normal detectors" as among the most dangerous applications of AI.

    Poništi
  17. proslijedio/la je Tweet
    27. sij

    In a opinion essay I wrote with we ask Epic to stop its aggressive campaign opposing interoperability and to not block patients' rights to computable copies of their health data.

    Poništi
  18. 27. sij
    Poništi
  19. 27. sij

    Really enjoyed this thread showing data on ER doctor choices and the ramifications for observational research. (AKA medical research is hard reason #2436380)

    Poništi
  20. proslijedio/la je Tweet
    24. sij
    Odgovor korisniku/ci

    I use , it generates tikz code from drawings you make. I like it more than ipe

    Poništi
  21. proslijedio/la je Tweet
    26. sij

    If you want to learn about privacy-preserving machine learning, then there is no better resource than this step-by-step notebook tutorial by . From the basics of private deep learning to building secure ML classifiers using PyTorch & PySyft.

    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:

    ·