I’m writing these things down over time because I’d like to figure out how to make artificial neural networks better at storing and retrieving knowledge, and the human brain is pretty good at that.
- When knowledge is new, it sometimes only comes back to me when I’m in the right context. For example, right now I can only think vaguely of how to adjust a chain derailleur on a bike, but I know that if I walked up to my bike and looked closely at the derailleur some more knowledge would appear. And we all have the familiar experience of being able to predict whether we’d recognize the name of a person or a song once it’s been said to us, but we can’t think of what it is until then.