Modular Neural Networks: a state of the art

The use of \global neural networks" (as the back propagation neural network) and \clustering neural networks" (as the radial basis function neural network) leads each other to diierent advantages and inconvenients. The combination of the desirable features ot those two neural ways of computation is achieved by the use of Modular Neural Networks (MNN). In addition, a considerable advantage can emerge from the use of such a MNN: an interpreatable and relevant neural representation about the plant's behaviour. This very desirable feature for function approximation and especially for control problems, is what lake other neural models. This feature is so important that we introduce it as a way to diierenciate MNN between other local computation models. However, to enable a systematic use of MNN three steps have to be achieved. First of all, the task has to be decomposed into subtasks, then the neural modules have to be properly organised considering the subtasks and nally a way of communication inter-modules has to be integrated in the whole architecture. We achieved a study of the main modular applications according to those steps. This study leads to the main fact that a systematic use of MNN depends on the type of task considered. The clustering networks and especially the Local Model Networks can be seen as MNN in the frame of classiication or recognition problems. The Euclidean distance criterion that they apply to cluster the input space leads to a relevant decomposition according to the properties of those tasks. But, it is irrelevant to apply such a criteria in case of function approximation problems. As spatial clustering seems to be the only existing decomposing method, therefore, an \ad hoc" decomposition and organisation of the architecture is achieved in case of function approximation. So, to improve the systematic use of MNN in the framework of function approximation it is now essential to conceive a method of relevant task decomposition.