Handling knowledge in high order neural networks: the combinatorial neural model

Summary form only given, as follows. A description is given of the combinatorial neural model, a high-order neural network suitable for classification tasks. The model is based on fuzzy set theory, neural sciences studies, and expert knowledge analysis results. It presents interesting properties such as modularity, explanation capacity, knowledge and data representation, high speed of training, incremental learning, generalization capacity, processing of uncertain and incomplete data, and ability to reason nonmonotonically when representing only relevant evidence, and graceful decay.<>