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 discovered today that my most played game on Steam is Astronner with about 500 hours, and my second most played is Surviving Mars with about 500 hours.
Enshittification of GitHub?
First, they restricted code search without logging in so I’m using sourcegraphBut now, I cant even view discussions or wiki without logging in....
In which game did you spend the most hours?
I discovered today that my most played game on Steam is Astronner with about 500 hours, and my second most played is Surviving Mars with about 500 hours.
What's a true fact that is so misleading it's borderline misinformation?
What would be some fact that, while true, could be told in a context or way that is misinfomating or make the other person draw incorrect conclusions?