Live data from Hacker News

Viewing profile — mfazalul

mfazalul

HN member
Joined
Wed, Feb 07, 2018, 7:13 PM UTC
HN karma
12
Public activity
20 items

About mfazalul

Applied ML PhD student, tech enthusiast, wannabe philosopher, pessimist, procrastination expert, stranded traveler.

mf3791 rit edu

Recent public activity

  1. story
  2. comment
    Comment #32678614

    Nuna Health | San Francisco, CA | Remote (US) or Onsite | Full-time & Internships | VISA At Nuna, our mission is to make high-quality healthcare affordable and accessible for every…

  3. story
  4. comment
    Comment #31242575

    Nuna Health | San Francisco, CA | Remote (US) or Onsite | Full-time & Internships | VISA At Nuna, our mission is to make high-quality healthcare affordable and accessible for every…

  5. comment
    Comment #29410199

    Nuna Health | San Francisco, CA | Remote (US) or Onsite | Full-time & Internships | VISA At Nuna, our mission is to make high-quality healthcare affordable and accessible for every…

  6. story
  7. story
  8. story
  9. story
  10. story
  11. story
  12. story
  13. comment
    Comment #19137309

    The official docs have some of the details: https://danielegrattarola.github.io/spektral/data/ More about Graph NNs: https://arxiv.org/pdf/1812.08434.pdf

  14. comment
    Comment #19136454

    As soon as I saw the title, my reaction was "YESSSS!"... A while ago, I was looking for something like this, but I soon realized that deep learning on graphs is still comparatively…

  15. story
  16. story
    Ask HN: Versioning and Pipeline for ML Research

    Being an applied ML PhD student, I often find myself having multiple versions of files and scripts towards the end of each research cycle. When I'm at the point of writing a paper …

  17. comment
    Comment #18922218

    I did not expect all the ants to follow the same path, but I thought maybe they'll come close since only the best generations are supposed to get passed on with mutations. I'm at g…

  18. comment
    Comment #18921729

    I've been running it for some time now and it seems that the model started to converge towards generation 35 and then diverged after that. i.e. since you consider the loss to be di…

  19. comment
    Comment #18766434

    I've made a list of things I'd like to learn soon. These are personally important to me, but based on your circumstances and specializations, it may (or may not) be important for y…

  20. comment
    Comment #18590620

    Location: Rochester, NY Remote: Yes Willing to relocate: Yes Technologies: Python (Keras, Tensorflow, scikit, etc), Java, Web development Résumé/CV: https://www.linkedin.com/in/mfa…