• zr0@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    2
    ·
    5 days ago

    Fully agree, overfitting might be an issue. We don’t know how much training data was available. Just more than the first assumption suggests. But it might still not be enough.

    • acockworkorange
      link
      fedilink
      arrow-up
      1
      ·
      5 days ago

      There aren’t a lot of high resolution images of black holes. I know of one. So not a lot.

      • zr0@lemmy.dbzer0.com
        link
        fedilink
        English
        arrow-up
        1
        ·
        5 days ago

        Oh, they don’t train on image data. They train on raw sensor data. And as mentioned earlier, they used all the data that was too noisy to produce images out of it.

        • acockworkorange
          link
          fedilink
          arrow-up
          1
          ·
          5 days ago

          Of that one mission, right? Until you have thousands of these days sets, it’s the wrong approach.

          • zr0@lemmy.dbzer0.com
            link
            fedilink
            English
            arrow-up
            1
            ·
            5 days ago

            9 petabytes of raw data have been produced with the EHT in 2017 and 2018. After filtering, only about 100 terabytes were left. After final calibrations, about 150 gigabytes were then used to generate the images.

            So clearly a lot of data was thrown away, as it was not usable for generating images. However, a machine learning model might be able to use this data.