Live data from Hacker News

Viewing profile — aria

aria

HN member
Joined
Sat, Nov 06, 2010, 1:28 AM UTC
HN karma
377
Public activity
83 items

About aria

http://aria42.com

Recent public activity

  1. comment
    Comment #15884192

    Yes this does dynamic nets, the model is the same as PyTorch, you build a graph for each input(s). I think Cortex is in the Keras-style of model (only layer abstractions and not "d…

  2. comment
    Comment #15884038

    I'll try! I've got a full time management job so this was a fun way to code again. The library is pretty small and I think easy to follow if you want to learn

  3. comment
    Comment #15883993

    Definitely doing the standard back-prop algorithm. Check out the code, it's pretty straightforward and the whole lib is about 2,500 lines

  4. comment
    Comment #15883988

    Author here, happy to answer any questions!

  5. comment
    Comment #15883986

    Author here. This is coming up. Will do OpenCL first and then CUDA.

  6. comment
    Comment #15789065

    Author here, happy to answer questions and hopefully convince someone to give the library a try.

  7. story
  8. comment
    Comment #8690976

    The interesting part of BFGS is that it directly approximates H^{-1} rather than H.

  9. comment
    Comment #8689579

    Want to try a refresh, I think it ought to be fixed now. Thanks

  10. comment
    Comment #8689574

    In practice you only need to do $H^{-1} g$; L-BFGS stores the {s_k} and {y_k} vectors which allow you to do the $H^{-1} g$ directly rather than needing to ever form the hessian or …

  11. comment
    Comment #8689426

    Typo is fixed, thanks! I think that's explicitly mentioned in the Quasi-Newton section that you only need to implicitly multiply and not form the matrix.

  12. comment
    Comment #8689418

    What browser are you in? It just using MathJax and appears to work in WebKit and Firefox.

  13. comment
    Comment #8689240

    Author here, happy to answer any questions.

  14. story
  15. comment
    Comment #6790476

    Question 1: What is the first bit in your unique 33-bit string? Question 2: What is the first bit in your unique 33-bit string? ...

  16. comment
    Comment #6509815

    Author here. Happy to answer any questions!

  17. story
  18. comment
    Comment #6337716

    Thanks! I definitely have personally run into the issue a lot and our Clojure teams at Prismatic struggled with commenting discipline. We find schemas are easier to maintain and ap…

  19. comment
  20. comment
    Comment #6335354

    Thanks! Yeah I think a traditional type system wouldn't make sense for Clojure, you need something that can describe data structures more succinctly, which is what we were shooting…

  21. comment
    Comment #6335228

    Definitely an inspiration. The core utility of Schema is that the declarations are still data and can be utilized in code. I think we'll have some interesting applications of this …

  22. comment
    Comment #6335220

    Thanks so much. We spent a long time thinking about how to have the benefits of types in a Clojure-y data-oriented way. The advantage of having Schemas as data is that we can use C…

  23. comment
    Comment #6334934

    Author here. Happy to answer any questions or comments.

  24. comment
    Comment #6258984

    Author here. Happy to answer any questions!

  25. comment
    Comment #6022200

    I could be wrong, but I don't think Incanter has any Clojure-native means of generic operations over arrays at all.