In many real world tasks, only a small fraction of the available inputs are important at any particular time. This paper presents a method for ascertaining the relevance of inputs by exploiting temporal coherence and predictability. The method pro(cid:173) posed in this paper dynamically allocates relevance to inputs by using expectations of their future values. As a model of the task is learned, the model is simulta(cid:173) neously extended to create task-specific predictions of the future values of inputs. Inputs which are either not relevant, and therefore not accounted for in the model, or those which contain noise, will not be predicted accurately. These inputs can be de-emphasized, and, in turn, a new, improved, model of the task created. The tech(cid:173) niques presented in this paper have yielded significant improvements for the vision-based autonomous control of a land vehicle, vision-based hand tracking in cluttered scenes, and the detection of faults in the etching of semiconductor wafers.