I am familiar with basic artificial neural networks and can program one myself using a genetic algorithm to train weights. But since the neurons only output a 0 or a 1, how can you use a neural network to use data that is not binary. Like if my inputs are 5, 7, 99 and i want it to output 44, 2, 3 how do I make the neural net do that? It only outputs 0 or 1 !How can a neural net output values other than 0 or 1?
I've never heard of binary outputs. I also use a genetic algorithm for training on this project I'm working on, and I always get a floating-point value between 0 and 1.
The synapse weights are supposed to be a percentage. That's all I can think of that may be wrong.
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment