Abstract: A delay and attenuation compensation-based BSS technique for source selection and noise reduction is provided for speech recognition applications. The undesired signals are attenuated in every situation and from every direction as much as possible. For this purpose, the direction of the input signals is determined. Depending on the direction of the undesired signals, the internal delay between the microphones is calculated. This internal delay is then used in subtracting the microphone signals from each other. Therefore, the invention gives not only a good directionality on average, but the best directionality for every listening situation. Furthermore, the channel selection problem is solved in conjunction with the BSS technique.

Abstract: A handwritten character recognizer having an input cluster buffer and a point buffer with dynamic and static stroke feature extraction and segment analysis by conical boundaries for identification of stroke segments dynamic stroke feature extractor static stroke feature extractor. A stroke recognizer compares single copies of idealized stroke representations with hierarchically approximated multiple scaled topological representations of a current stroke, followed by stroke proportion discrimination comparing a selected topological representation of the current stroke with boundaries defined by linear combinations of features of direct and reversed ideal stroke prototypes to provide a stroke identification. A cluster recognizer maintains a time ordered current stroke buffer and previous stroke buffer and constructs a per stroke area of influence list. The time ordered buffers are scanned to generate a spatially ordered window buffer.

Abstract: A handwritten character recognition system that includes a document scanner for generating scanned images of a previously created document containing handwritten characters, and a pen and digitizing tablet for real time entry of handwritten characters by a user. The handwritten character recognition system includes an image processor connected from the document scanner for receiving the scanned image of a previously created document and generating one or more ordered cluster arrays. The ordered cluster arrays contain spatially ordered coordinate arrays of skeletal image arcs representing and corresponding to the strokes of the handwritten characters wherein the spatial order represents an induced time ordered sequence of creation of the strokes of the handwritten characters that emulates the sequence of creation of the character strokes.

Abstract: Long and short term memory equations for neural networks are implemented by means of exchange of signals which carry information in the form of both binary and continuously modulated energy emissions. In one embodiment, array of parallel processors exhibits behavior of cooperative-competitive neural networks. Parallel bus interconnections and digital and analog processing of analog information contained in the exchanged energy emissions are employed with generally local synchronization of the processors.

Abstract: Long and short term memory equations for neural networks are implemented by means of exchange of signals which carry information in the form of both binary and continuously modulated energy emissions. In one embodiment, array of parallel processors exhibits behavior of cooperative-competitive neural networks. Parallel bus interconnections and digital and analog processing of analog information contained in the exchanged energy emissions are employed with generally local synchronization of the processors. Energy emission and detection is modulated as a function of a random code.

Abstract: Methods of information correlation based on extremization of transmission capacity of an assembly of information processors are disclosed. In one embodiment, an assembly of processors exchanging information through the exchange of random codes serves as a correlator between two inputs adjusting its total communication capacity to achieve maximum correlation between two inputs.

Abstract: Methods of information discrimination based on extremization of local, energy related functionals defined on macroscopic states of random code information processors are disclosed. In one embodiment, an assembly of processors exchanging information through the exchange of random codes serves an an information discriminator cell between the digitally encoded, analog, quasi-periodic input function and the digitally encoded, analog, quasi-periodic memory function stored within the cell.

Abstract: Microprocessor assemblies are disclosed, which include a plurality of preprogrammed, cellular automaton microprocessors, a common radiant energy data waveguide into which said microprocessors can emit and from which said microprocessors can absorb modulated radiant energy signals, and a power supply radiant energy waveguide. Means are provided for each microprocessor to demodulate the absorbed signal and to modulate the emitted signal according to codes assigned to each said microprocessor. The common data waveguide provides for exchange of signals among the plurality of microprocessors. The relative degree of communication between two given microprocessors is determined by the degree to which the respective codes match. Said codes are subject to change. The change is determined by the demodulated inputs of the microprocessors. Means are provided for selective activation and deactivation of microprocessors through selective activation power supply.