Abstract: A neural network for processing arrays of data with pertinent topology comprises 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 neighbourhood of a cell (Ki); Each cell (Ki) having 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); each cell being characterised 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) being a function of its internal value and of the input signals form the neighbouring cells; each cell being associated univoquely 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 less dimensions a method for the cognitive analysis of multidimensional information data based on the said algorithm and a program comprising the 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 for encoding pixels of digital or digitized images, i.e., images consisting of a set of image dots, named pixels in two-dimensional images and voxels in three-dimensional images, each of said pixels or voxels being represented by a set of values which correspond to a visual aspect of the pixel on a display screen or in a printed image. According to the invention, the pixels or voxels of at least one portion of interest of the digital or digitized image or each pixel or voxel of the set of pixels or voxels which form the image is uniquely identified with a vector whose components are given by the date of the pixels or voxels to be encoded and by the data of at least one or at least some or of all of the pixels around the pixels to be encoded and arranged within a predetermined subset of pixels or voxels included in the whole set of pixels or voxels which form the image.

Abstract: A method for evaluating the cognitive performance of an individual by qualitative/quantitative analysis of the performance of a task, characterized in that: The task is a practical problem which may be exactly represented both graphically and mathematically and solved both graphically and computationally; The task has a set of solutions with a number of elements greater than one, one element being the best possible solution; And wherein the individual provides a graphical solution; Said graphical solution is converted into a numerical solution; A reference numerical solution is computed; The graphical solution converted into the numerical solution is compared with the computed reference numerical solution, a difference index being determined between the computed reference solution and the graphical solution proposed by the individual. The invention also relates to an apparatus for implementing said method.