Abstract: A neural network for processing arrays of data with pertinent topology includes a n-dimensional array of cells (Ki) corresponding to the knots of the neural network, each cell having connections to the directly adjacent cells (Kj) forming the neighborhood of a cell (Ki), Each cell (Ki) has inputs for each connection to directly adjacent cells; an output for the connection to one or more of the directly adjacent cells (Kj), the connection between the cells being determined by weights (wij), and each cell being characterized by an internal value and being able to carry out signal processing for generating a cell output signal (ui), The output signal (ui) of a cell (Ki) is a function of its internal value and of the input signals from the neighboring cells, each cell being associated univocally to a record of a n-dimensional database (Pi) with pertinent topology and the value of each data record being the starting value of the corresponding cell.

Abstract: An algorithm for projecting information data belonging to a multidimensional space into a space having fewer dimensions, a method for the cognitive analysis of multidimensional information data based on said algorithm, and a program comprising said algorithm stored on a recordable support.

Abstract: An artificial neural network comprises at least one input layer with a predetermined number of input nodes and at least one output layer with a predetermined number of output nodes or also at least one intermediate hidden layer with a predetermined number of nodes between the input and the output layer. At least the nodes of the output layer and/or of the hidden layer and/or also of the input layer carry out a non linear transformation of a first non linear transformation of the input data for computing an output value to be fed as an input value to a following layer or the output data if the output layer is considered.

Abstract: A method of processing multichannel and multivariate signals as described hereinbefore, wherein the signals from each channel are subjected to a first processing step by a recirculation artificial neural network being trained to generate the recorded multichannel and multivariate signals; and a second processing step in which the weights of the connections between the knots of the recirculation neural network determined in the first processing step are processed by an artificial neural network, the recirculation neural network being preferably of the non supervised kind. A particular family of recirculation neural network which can be used according to the present invention is a so called auto-associative neural network.