The lie made into the rule of the world

  • 10 Posts
  • 650 Comments
Joined 5 months ago
cake
Cake day: October 22nd, 2024

help-circle



  • Accuracy in a classification context is defined as (N correct classifications / total classifications). So classifying everything as cancer would, in a balanced dataset, give you ~50% accuracy.

    This article is indeed badly written PR fluff. I linked the paper in a sister comment. Both the confusion matrix and the ROC curve look phenomenal. Train/test/validation split seems fine too, as do the training diagnostics, so I’m optimistic that it isn’t a case of overfitting.

    Ofcourse 3rd party replication would be welcome, and I can’t speak to the medical relevanve of the dataset. But the computer vision side of things seems well executed.








  • iii@mander.xyzOPtoMoneroMining without joining a pool?
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    13 days ago

    why do you want to do that?

    I mine mostly because I like the technology, and have (already paid for) CPU cycles spare. Plus, doing it without a pool is a bit like playing the lottery.

    local monero node and done, no?

    Aha! I have no such thing as far as I’m aware, since I use the mymonero wallet.

    I should run a node, and in the “pool” section of the xmrig config, point to localhost?