Figure 1.

Hierarchical model for predictive coding. Higher-level units attempt to predict the responses of units in the next lower level via feedback connections, while lower-levels signal the difference between the prediction and the actual input. Feedforward connections encode the synaptic weights represented by a matrix W ^T. Higher-level units maintain the current estimate of the input signal r and convey the top-down prediction Wr to the lower level via feedback connections. Difference detectors compute the difference I − Wr between current activity I and the top-down prediction Wr.