Abstract: A method of classifying objects in a system having an electrical signal receiver scans the objects to be classified and outputs for each object M scanned values, and an evaluation unit evaluates the M scanned values and classifies the objects into classes. Classification takes place by performing a learning process to learn adjoint prototypes corresponding to the classes, wherein an adjoint prototype is learned for each of the classes through minimization of a potential function. A classifying process is then performed wherein an object to be classified is assigned to one of the classes, according to a potential function, corresponding to the learned adjoint prototypes.

Abstract: A likelihood of detecting a reflected signal characterized by phase discontinuities and background noise is enhanced by utilizing neural networks to identify coherency intervals. The received signal is processed into a predetermined format such as a digital time series. Neural networks perform different tests over arbitrary testing intervals to determine the likelihood of a phase discontinuity occurring in any such interval. An integration time generator subsequently uses this information to define a series of contiguous coherency intervals over the duration of the received signal. These coherency intervals are then used for piece-wise processing of the received signal by parallel quadrature receivers. The outputs are combined and processed for detecting the presence of the reflected signal.

Abstract: The invention is directed to means, utilizing a neural network, for estimating helicopter airspeed at speeds below about 50 knots using only fixed system parameters as inputs to the neural network.

Abstract: A neural network is made to undergo learning such that at least three characteristic parameters, which correspond to an inputted set of color information values when the set of color information values, including at least three color information values, is inputted and which are obtained by multivariate analysis of the spectral reflectance distribution or the spectral transmittance distribution, are outputted. A subject set of color information values is transformed into the characteristic parameters by using the neural network which has completed learning, and a spectral reflectance distribution or a spectral transmittance distribution is estimated by linear polynomial approximation using the transformed characteristic parameters, eigenvectors obtained by the multivariate analysis, and a mean vector of the spectral reflectance distribution or the spectral transmittance distribution.