The adaptive fuzzy rule-based system incorporates learning of actions based on previous inputs and outputs. For example, the initial rule base may establish some actions and scenarios based on expert knowledge, however some situations will not be anticipated, or may not perform exactly as intended by the initial rule base. The adaptive fuzzy rule-based system incorporates learning from observed frequencies to refine and generate additional rules, for example defining when and how to rearrange the display of a vehicle system with different display elements. The adaptation begins with the initial rule set, and possible actions or outcomes treated as mutually exclusive events. As they adaptive fuzzy rule-based system observes the frequency of different outcomes, and frequency of outcomes adjusted or selected by a user, the system conditionally learns relative frequencies. For example the system may identify a maximum outcome for a particular set of inputs, or an outcome that is more likely than other options and set or conditionally establish a rule that the particular set of inputs results in the selected output or action.