• 2 Posts
  • 49 Comments
Joined 1 year ago
cake
Cake day: June 6th, 2023

help-circle











  • Considering that training is extracting the main features of a dataset, there is always some data that is discarded as “noise” in the process, then when data is generated, that discarded information is filled back with actual random noise to partially replicate the original data.

    Iterate and you’re going to end up with progressively less meaningful features. I just didn’t expect it to take only 5 iterations, that’s a lot of feature loss in training even with so many parameters.



  • It’s a bit like the whole “infrastructure ain’t sexy” argument. As the chief executive administrator, you’re paid to “strategize”, when sometimes, you just need to keep the engines running and the bills paid, but in today’s society that’s not praised. You need to capture people and investors’ ADHD-span, make megalomanous plans that can’t possibly ever come true or be some guy who fires everyone to attempt to grow profit margins.