Schematic structure of an agent and a module.

<p><b>A</b>) An agent consists of several modules, where each module contains an instance of the model shown in <a href="" target="_blank">Figure 1</a> and has learned to recognize a single word. Sensory input is recognized by all modules concurrently and each module experiences prediction error during recognition. A module can be considered as a sophisticated dynamic, Bayes-optimal template matcher which produces less prediction error if the stimulus matches better to the module's learned word. A minimum operator performs classification by selecting the module with the least amount of prediction error during recognition. <b>B</b>) At each level in a module, causal and hidden states ( and , respectively) try to minimize the precision-weighted prediction errors ( and ) by exchanging messages. Predictions are transferred from second level to the first and prediction error is propagated back from the first to the second level (see section <a href="" target="_blank">Model</a>: Learning and Recognition for more details). Adapted from <a href="" target="_blank">[110]</a>.</p>