On one side of the hidden layer(s) 406, hidden nodes are interconnected to the input nodes. Each of the input nodes may be connected to each of the hidden nodes of the hidden layer connected to the input layer 402. On the other side of the hidden layer(s) 406, hidden nodes are connected to the output nodes. Each of the output nodes may be connected to each of the hidden nodes of the hidden layer connected to the output layer 404. In other words, each input node connects to each hidden node in the hidden layer closest to the input layer 402 and each output node connects to each hidden node in the hidden layer closest to the output layer 404. The input nodes are not directly interconnected to the output nodes. If multiple hidden layers exist, the input nodes are interconnected to hidden nodes of the closest hidden layer only. In turn, these hidden nodes are interconnected to the hidden nodes of the next hidden layer and so on and so forth.

An interconnection may represent a piece of information learned about the two interconnected nodes. In comparison, a connection between a hidden node and an output node may represent a piece of information learned that is specific to the output node. The interconnection may be assigned a numeric weight that can be tuned (e.g., based on a training dataset), rendering the adaptive learning system 400 adaptive to inputs and outputs and capable of “l(fā)earning.”