Yeah this is a bad meme. The whole point of machine learning is to do minutely different things over millions of generations to see differences and their effects. It’s the exact opposite of doing the same thing and expecting different results. Machine learning is the summation of millions of differences.
That doesn’t really work. For example, driving is the same action. I do this action over and over again. However, I drive to vastly different destinations. I’m not in fact doing the same thing over and over even though the same action is being done.
Similarly an algorithm will give vastly different results based on the inputs I give it. Saying it’s the same formula with different inputs would be very incorrect.
Isn’t machine learning doing slightly different thing each time?
Yeah this is a bad meme. The whole point of machine learning is to do minutely different things over millions of generations to see differences and their effects. It’s the exact opposite of doing the same thing and expecting different results. Machine learning is the summation of millions of differences.
I think the point is that it’s the same (type of) computation or process over and over.
That doesn’t really work. For example, driving is the same action. I do this action over and over again. However, I drive to vastly different destinations. I’m not in fact doing the same thing over and over even though the same action is being done.
Similarly an algorithm will give vastly different results based on the inputs I give it. Saying it’s the same formula with different inputs would be very incorrect.
Listen, I identify with generation 1 here.
Or do the same thing in a very slightly different way each time until you accidentally discover a good enough way to do it?