• 0 Posts
  • 9 Comments
Joined 1 year ago
cake
Cake day: June 29th, 2023

help-circle

  • The reason they are blackboxes is because they are function approximators with billions of parameters. Theory has not caught up with practical results. This is why you tune hyperparameters (learning rate, number of layers, number of neurons ina layer, etc.) and have multiple iterations of training to get an approximation of the distribution of the inputs. Training is also sensitive to the order of inputs to the network. A network trained on the same training set but in a different order might converge to an entirely different function. This is why you train on the same inputs in random order over multiple episodes to hopefully average out such variations. They are blackboxes simply because you can’t yet prove theoretically the function it has approximated or converged to given the input.








  • I exclusively use Freetube for my Youtube needs. It is great when it works. Sometimes you have to find the right Invidious instance for it to work properly. A few times videos play at 720p. I have also noticed search failing for specific terms sometimes - for example “machine learning”. I don’t know if it is a bug or blacklisted words/phrases.

    These are a few reality checks highlighting it isn’t a perfect experience all the time, but I will be damned if go back to a vanilla Youtube interface after having gotten used to Invidious and then Peertube.

    The upsides are less fluff that is recommended, you control your own feed with the videos from the channels you subscribe to, no ads, sponsorblock, and I guess more privacy.