Many aspects of the human nervous system are not represented in current neural network models. An aspect that appears to be of great importance in human decision-making is focus of attention. This focus determines the level of detail that should be considered in addressing the current situation. For example, if you wish to drive from Rome to the Grand Hotel di Como at Lake Como you first check a map of Italy to determine which major road to take. You only consult a detailed map of the Lake Como area after arriving in the general vicinity. This process is related to breaking a problem in to sub-problems [1], where the level of detail required will vary from problem to problem. Determining the appropriate level of detail is crucial for much of human decision-making.Classification neural networks as they currently exist generally rely on building an overall model based on the data presented. Implementation of a level of detail structure depends on hierarchical modeling. Neural networks at each level of detail must be trained separately, with each requiring different data sets for training and testing. In addition, a method for deciding which level is appropriate must be developed. In the work described here, Meta knowledge, a technique derived from knowledge-based reasoning [2], is used to transition between multiple levels.Although a number of hybrid systems that incorporate neural network models with expert-supplied knowledge have been developed [3,4], in general they rely upon using the output of one method as input to another method. In the work described here, the Meta knowledge internally structures transitions among the neural network layers.