What exactly is the difference between weight-space programming and something like back propagation? I guess AI can reason deeper about the weights somehow and take into account more parameters than a simple feedback from back propagation?
Weight-space programming doesn't have an established definition yet afaik, but it would implement weight changes using a trained model using forward passes, no derivatives needed
Weight-space programming doesn't have an established definition yet afaik, but it would implement weight changes using a trained model using forward passes, no derivatives needed