Modular neural networks (MNN) are a tool that can be used for object recognition and identification. Usually the inputs of the MNN can be fed with independent data. However, there are certain limits when we may use MNN, and the number of the neurons is one of the major parameters during the implementation of the MNN. On the other hand, the greater number of neurons slows down the learning process. In the paper, we propose a method for removing the number of the inputs and, hence, the neurons, without removing the error between the target value and the real value obtained on the output of the MNN’s exit. The method uses the recently proposed approach of InterCriteria Analysis, based on index matrices and intuitionistic fuzzy sets, which aims to detect possible correlations between pairs of criteria. The coefficients of the positive and negative consonance can be combined for obtaining the best results and smaller number of the weight coefficients of the neural network.