Neural Network Ideas
Would it kill the whole concept to encapsulate the weight and learning rate within the link between 2 nodes? I think(very unsurely) that it would make it more versatile, and enable nodes to seem to adapt to individual connections to other nodes rather than as a whole.
I've been thinking about NNs a lot lately, and my brains kinda overflowing with ideas. As I stupid-check them, if they pass, I'll dump them here.
Each link having its own learning rate has certainly been done before. Whether it helps depends on what you are doing.
I'm not sure what I'm doing. I guess my ultimate goal would be to have a NN capable of learning anything, but that's admittedly not going to happen. So, in terms of stuff that is possible, I'm trying to get as generalized an NN as possible.