Learning in the combinatorial neural model

The combinatorial neural model (CNM) is a type of fuzzy neural network for classification problems. Learning in CNM is a complex task spanning the learning of input-neuron membership functions, the network topology and connection weights. We deal with these various aspects of learning in CNM, most notably with the learning of connection weights, whose complexity comes from the existence of nondifferentiable, nonconvex error functions associated with the learning process. We introduce several algorithms for weight learning. All the algorithms are based on “local” rules, and are therefore amenable to distributed/parallel implementations. Experimental results are provided on the large-scale problem of monitoring the deforestation of the Amazon region on satellite images. These results show that a hybrid CNM system outperforms previous results obtained with variations of error backpropagation techniques. In addition, this hybrid system has demonstrated robustness in the context under consideration