Abstract: An adaptive integration network includes a plurality of interconnected neurons that are configured to fire when their excitation level, which is responsive to weighted input signals, is greater than or equal to a threshold. When two neurons fire in close temporal proximity, the weight of the connection is strengthened. Adaptive learning is induced by increasing the activity of the adaptive integration network, such as by lowering the threshold level.

Abstract: The invention relates to a learning process generating neural networks designed to sort data into two classes separated by a non-linear surface and built up as the needs of the task to be carried out are defined. This surface is either quadratic, or partly linear and partly quadratic. Applications include shape recognition and sorting of objects or data.

Abstract: An adaptive interface for a programmable system, for predicting a desired user function, based on user history, as well as machine internal status and context. The apparatus receives an input from the user and other data. A predicted input is presented for confirmation by the user, and the predictive mechanism is updated based on this feedback. Also provided is a pattern recognition system for a multimedia device, wherein a user input is matched to a video stream on a conceptual basis, allowing inexact programming of a multimedia device. The system analyzes a data stream for correspondence with a data pattern for processing and storage. The data stream is subjected to adaptive pattern recognition to extract features of interest to provide a highly compressed representation which may be efficiently processed to determine correspondence.

Abstract: A reduced control system suitable for control of a nonlinear or unstable plant is described. The reduced control system is configured to use a reduced sensor set for controlling the plant without significant loss of control quality (accuracy) as compared to an optimal control system with an optimum sensor set. The control system calculates the information content provided by the reduced sensor set as compared to the information content provided by the optimum set. The control system also calculates the difference between the entropy production rate of the plant and the entropy production rate of the controller. A genetic optimizer is used to tune a fuzzy neural network in the reduced controller. A fitness function for the genetic optimizer provides optimum control accuracy in the reduced control system by minimizing the difference in entropy production while maximizing the sensor information content.

Abstract: A machine control system for controlling an unstable or transition running condition of a machine which is operable by a causative signal and the performance of which is indicatable by an indicative signal. The control system includes: (a) a model-based control unit for outputting an estimated value of a causative signal when receiving an indicative signal, which model-based control unit undergoes learning based on teacher data; (b) a feedback control unit for providing first teacher data to the model-control unit upon receiving feedback information from the machine; and (c) an anticipatory control unit for providing second teacher data to the model-based control unit.

Abstract: A self-organizing control system suitable for nonlinear control of a physical object is described. The control system calculates the entropy production difference between a time differentiation (dSu/dt) of the entropy inside the controlled object and a time differentiation (dSc/dt) of the entropy given to the controlled object from a PID controller that controls the object. The entropy production difference is used to generate an evolving control rule by using the entropy production difference as a performance function for a genetic optimizer.

Abstract: In an optimization apparatus 30, a known compositional ratios and the like, and mechanical behaviors thereof are inputted by an experimental data input unit 40 and a learning is conducted in a non-linear calculation unit 32 in order to establish a corresponding relation between compositional ratios of multi-component materials and the like, and mechanical behaviors thereof as a conversion system based on a neural network. Compositional ratios and the like are inputted in an optimization item input unit 42, and a mechanical behaviors are predicted in an optimization calculation unit 34 from compositional ratios and the like of the multi-component materials using the optimization item and the conversion system of the calculation unit 32, and an objective function is optimized until the objective function, expressing the mechanical behaviors are converged.

Abstract: In an information filtering method, attributes included in information items are extracted and stored, and ratings relative to the information items carried out by users are stored. The users include a subject user and other users. A relationship between the ratings relative to the information items rated by the subject user and the attributes thereof and a relationship between the ratings relative to the information items rated by the other users and the attributes thereof are utilized for estimating relevances to the subject user of the information items not rated by the subject user. The estimated relevances are used to carry out recommendation or filtering-in of the information item which matches with the subject user.

Abstract: Image processing for multimedia workstations is a computationally intensive task requiring special purpose hardware to meet the high speed requirements associated with the task. One type of specialized hardware that meets the computation high speed requirements is the mesh connected computer. Such a computer becomes a massively parallel machine when an array of computers interconnected by a network are replicated in a machine. The nearest neighbor mesh computer consists of an N×N square array of Processor Elements(PEs) where each PE is connected to the North, South, East and West PEs only. The diagonal folded mesh array processor, which is called Oracle, allows the matrix transformation operation to be accomplished in one cycle by simple interchange of the data elements in the dual symmetric processor elements.

Abstract: A method for generating fault classification signals which identify faulty loops which develop in a multiphase energy supply network observed in the event of a fault from a protective device with a starting arrangement. To be able to generate such fault classification signals in a relatively simple manner, a neural network is used which is trained using input variables simulating faulty loops in the form of normalized resistance and reactance variables formed taking into consideration the starting characteristic of the starting arrangement. In the case of a fault, normalized resistance and reactance measured variables network for generating fault classification signals.

Abstract: A method and system for training a computer classification system which can be defined by a network of a number of n-tuples or Look Up Tables (LUTs), with each n-tuple or LUT including a number of rows corresponding to at least a subset of possible classes and further including a number of columns being addressed by signals or elements of sampled training input data examples, each column being defined by a vector having cells with values, wherein the column vector cell values are determined based on one or more training sets of input data examples for different classes so that at least part of the cells comprise or point to information based on the number of times the corresponding cell address is sample from one or more sets of training input examples, and weight cell values are determined, corresponding to one or more column vector cells being addressed or sampled by the training examples.

Abstract: A rules data method is devised that records, documents, organizes, filters, and sorts a set of engineering rules along with other sets of rules. The rules database method may also correctly devise an order or sequence for a set of engineering rules. The rules database method comprises firstly, to create a database (14); secondly, to convert a set of symbolic equations to spreadsheet formula; thirdly, to write spreadsheet formula to a spreadsheet (18); and fourthly, to share a set of parameters of the database (14) with a computer aided design geometry (22).

Abstract: An integrated system and method for providing a flexible expert system development and runtime environment with an integrated natural language processor and set-oriented knowledge base. The system and process include an input device, a spreading activation module, a reasoning module, a decision module, and a knowledge base. The system and method may also include a natural language processing module. The spreading activation module utilizes the knowledge base, which is set-oriented with named relationships between concepts to traverse the knowledge base efficiently. The reasoning module executes related, nested logic statements which manipulate the complex facts in the knowledge base. The decision module selects the value or values from a list which are most relevant at the moment the module is called. The knowledge base represents all data in a nested, set-oriented manner. The system and method, in turn, produce an output in response to the input or command into the system.

Abstract: A semiotic decision making system operates to respond, for example, to natural language queries. The system operates independent of the type of symbolic elements in which queries are cast. A training corpus of information in the form of sequential sets of a selected type of element is input to the system and processed by a semiotic processing module to create a knowledge database based upon the lineal relationship of elements within the training corpus. The knowledge database is then used to make decisions relating to queries input in the same type of elements. Accordingly, inputting a French training corpus results in a knowledge base useful in answering French questions. Multiple semiotic processing modules may be used to enhance performance.

Abstract: A fuzzy processor with an improved architecture. The fuzzy processor includes a fuzzy rule processor, an internal fuzzy instruction memory, an internal knowledge base memory, an arithmetic-logic unit, a control unit that can execute non-fuzzy instructions that are typical of conventional microprocessors, and an internal memory for storing the non-fuzzy instructions. The improved fuzzy processor architecture has an ability to load other knowledge bases and other fuzzy rules from outside the processor concurrently and transparently with respect to instruction processing. The processor can also process both fuzzy instructions and non-fuzzy instructions, can perform conditional and unconditional jumps within a set of fuzzy rules that are being processed, and can conditionally swap the knowledge base or the set of rules that are to be processed.

Abstract: A method of achieving automatic learning of an input vector presented to an artificial neural network (ANN) formed by a plurality of neurons, using the K nearest neighbor (KNN) mode. Upon providing an input vector to be learned to the ANN, a Write component operation is performed to store the input vector components in the first available free neuron of the ANN. Then, a Write category operation is performed by assigning a category defined by the user to the input vector. Next, a test is performed to determine whether this category matches the categories of the nearest prototypes, i.e. which are located at the minimum distance. If it matches, this first free neuron is not engaged. Otherwise, it is engaged by assigning the matching category to it. As a result, the input vector becomes the new prototype with the matching category associated thereto. Further described is a circuit which automatically retains the first free neuron of the ANN for learning.

Abstract: A cortronic neural network defines connections between neurons in a number of regions using target lists, which identify the output connections of each neuron and the connection strength. Neurons are preferably sparsely interconnected between regions. Training of connection weights employs a three stage process, which involves computation of the contribution to the input intensity of each neuron by every currently active neuron, a competition process that determines the next set of active neurons based on their current input intensity, and a weight adjustment process that updates and normalizes the connection weights based on which neurons won the competition process, and their connectivity with other winning neurons.

Abstract: Sonar method and system for determining and using beamform factors for forming sonar beams approximating an optimum sonar beam for the directional transmission or reception of sonar energy by a sonar phased array system. Optimum maximum and minimum dependent beamform factors are determined from initial beamform factors and an initial parent population of chromosomes is generated, each chromosome including a gene corresponding to a dependent beamform factor and representing an initial candidate beam. Subsequent parent populations are generated by chromosome cloning. A child population is generated from a parent population by exchanging statistically selected pairs of genes and generating a mutated population. A surviving population is selected from the mutated population by a chromosomes comparison. When the surviving population chromosomes meet the criteria, the best match genes of the surviving population are selected for forming a beam.

Abstract: An adaptive agent including an artificial neural network having a plurality of input nodes for receiving input signals and a plurality of output nodes generating responses. A situation value unit receives a plurality of the responses and generating a situation value signal. A change sensor coupled to receive the situation value signal generates an output signal representing a change of the situation value signal from a prior time to a current time. A connection coupling the change sensor output to one of the input nodes of the artificial neural network.

Abstract: The invention provides a technique regarding an optimal solution search method suitable for use for optimization of a system, wherein genetic algorithms can be executed at a high speed to allow an optimal solution to a problem to be searched for at a high speed. The optimal solution search method wherein candidates for solution to a problem are represented as chromosomes which are arrangements of genes and genetic operations are performed for individual chromosomes for each generation to successively update the generation to search for an optimal solution to the problem based on fitness values calculated from gene arrangements of the chromosomes.