Integrating expert modules by local receptive neural network

In this paper, the task of integrating conflicting experts´ opinions is achieved through a training of local receptive gating network using backpropagation. The front layers of the gating network consist of local-receptive fields which form feature maps of the input that enable modulations to experts´ output. The resulting network achieves accurate modelling of the solution mapping through the efficient combination of existing experts. Experimental results on a histogram thresholding problem show the superior performance of the modular network over classical algorithms