Regulatory feedback networks are neural networks that perform inference using Negative feedback. The feedback is not used to find optimal learning or training weights but to find the optimal activation of nodes. In effect this approach is most similar to a non-parametric method but is different from K-nearest neighbors in that it can be shown to mathematically emulate feedforward neural networks.
Regulatory feedback network Wikipedia
Regulatory feedback networks started as a model to explain brain phenomena found during recognition including network-wide bursting and difficulty with similarity found universally in sensory recognition. This approach can also perform mathematically equivalent classification as feedforward methods and is used as a tool to create and modify networks.