Abstract: Method of incrementally forming and adaptively updating a neural net model are provided. A function approximation node is incrementally added to the neural net model. Function parameters for the function approximation node are determined and function parameters of other nodes in the neural network model are updated, by using the function parameters of the other nodes prior to addition of the function approximation node to the neural network model.

Abstract: A plurality of neural networks or other models can be used in employee selection technologies. A hiring recommendation can be based at least on processing performed by a plurality of neural networks. For example, parallel or series processing by neural networks can be performed. A neural network can be coupled to one or more other neural networks. A binary or other n-ary output can be generated by one or more of the neural networks. In a series arrangement, candidates can be processed sequentially in multiple stages, and those surviving the stages are recommended for hire.

Abstract: A neural network component includes a plurality of inputs, at least one processing element, at least one output, and a digital memory storing values at addresses respectively corresponding to the at least one processing element, wherein the at least one processing element is arranged to receive a value from the digital memory in response to an input signal, and is instructed to execute one of a plurality of operations by the value that is received from the digital memory.

Abstract: A simulated neural circuit includes a plurality of simulated neurons. The simulated neurons have input branches that are configured to connect to a plurality of inputs and activate in response to activity in the inputs to which they are connected. In addition, the simulated neurons are configured to activate in response to activity in their input branches. Initial connections are formed between various input branches and various inputs and a set of the inputs are activated. Thereafter, the stability of connections between input branches and inputs to which they are connected is moderated based on the activated set of inputs and a pattern of activity generated in the input branches and simulated neurons in response to the activated set of inputs.

Abstract: A first array of simulated neurons having trees of output branches and a second array of simulated neurons having trees of input branches are generated. Thereafter, the output branches of one or more of the simulated neurons of the first array and the input branches of one or more of the simulated neurons of the second array are grown and connections are formed between individual output branches of the simulated neurons of the first array and individual input branches of the simulated neurons of the second array that grow to within a vicinity of each other.

Abstract: A physical neural network is disclosed, which includes a connection network comprising a plurality of molecular conducting connections suspended within a connection gap formed between one or more input electrodes and one or more output electrodes. One or more molecular connections of the molecular conducting connections can be strengthened or weakened according to an application of an electric field across said connection gap. Thus, a plurality of physical neurons can be formed from said molecular conducting connections of said connection network. Additionally, a gate can be located adjacent said connection gap and which comes into contact with said connection network. The gate can be connected to logic circuitry which can activate or deactivate individual physical neurons among said plurality of physical neurons.

Abstract: This processing is distributed among number of simple hexagonal units distributed in a honeycomb layer, consisting of a central hexagram surrounded by six receiving cells, each representing an invariable binary place fed into central hexagram's CPU controlled by a simple program. The activated receiving cells indicate the presence of a stimulus. The interconnected layers overlap so that the higher-level receiving cells get input from the lower-level central hexagrams and higher-level output modifies lower-level programs as well as sends input to other levels or Memory Units. Integration of layer output is achieved in 3D Memory Unit Complex consisting of truncated octagons, where each hexagonal side represents a binary number linked to 6 others through one binary place that makes adjacent numbers different. The input into each Memory Unit comes from the output of a Patch of central hexagrams a clocked input, other-layer output or a Memory Unit feedback.

Abstract: Methods and systems are disclosed herein in which a physical neural network can be configured utilizing nanotechnology. Such a physical neural network can comprise a plurality of molecular conductors (e.g., nanoconductors) which form neural connections between pre-synaptic and post-synaptic components of the physical neural network. Additionally, a learning mechanism can be applied for implementing Hebbian learning via the physical neural network. Such a learning mechanism can utilize a voltage gradient or voltage gradient dependencies to implement Hebbian and/or anti-Hebbian plasticity within the physical neural network. The learning mechanism can also utilize pre-synaptic and post-synaptic frequencies to provide Hebbian and/or anti-Hebbian learning within the physical neural network.

Abstract: A system for independent component analysis includes a feedback mechanism based on a plasticity rule, and an electro-kinetic induced particle chain, wherein the feedback mechanism and the electro-kinetic induced particle chain is utilized to extract independent components from a data set or data stream. The electro-kinetic induced particle chain is generally composed of a plurality of interconnected nanoconnections (e.g., nanoparticles) disposed between at least two electrodes in a solution, including for example one or more pre-synaptic electrodes and one or more post-synaptic electrodes. The feedback mechanism generally provides feedback to one or more particles within the electro-kinetic induced particle chain, while the plasticity rule can be non-linear in nature. The feedback mechanism also provides for one or more evaluate phases and one or more feedback phases.

Abstract: Physical neural network systems and methods are disclosed. A physical neural network can be configured utilizing molecular technology, wherein said physical neural network comprises a plurality of molecular conductors, which form neural network connections thereof. A training mechanism can be provided for training said physical neural network to accomplish a particular neural network task based on a neural network training rule. The neural network connections are formed between pre-synaptic and post-synaptic components of said physical neural network. The neural network generally includes dynamic and modifiable connections for adaptive signal processing. The neural network training mechanism can be based, for example, on the Anti-Hebbian and Hebbian (AHAH) rule and/or other plasticity rules.

Abstract: A neural network system is described. The neural network system includes an artificial neural network including a plurality of neurons. One of the neurons includes an analog electrical circuit and the neurons are interconnected.

Abstract: A physical neural network is disclosed, which comprises a liquid state machine. The physical neural network is configured from molecular connections located within a dielectric solvent between pre-synaptic and post-synaptic electrodes thereof, such that the molecular connections are strengthened or weakened according to an application of an electric field or a frequency thereof to provide physical neural network connections thereof. A supervised learning mechanism is associated with the liquid state machine, whereby connections strengths of the molecular connections are determined by pre-synaptic and post-synaptic activity respectively associated with the pre-synaptic and post-synaptic electrodes, wherein the liquid state machine comprises a dynamic fading memory mechanism.

Abstract: An information processing method and an information processing apparatus in which the learning efficiency may be improved and the scale may be extended readily. An integrated module 42 is formed by a movement pattern learning module by a local expression scheme. The local modules 43-1 to 43-3 of the integrated module 42 are each formed by a recurrent neural network as a movement pattern learning model by a distributed expression scheme. The local modules 43-1 to 43-3 are caused to learn plural movement patterns. Outputs from the local modules 43-1 to 43-3, supplied with preset parameters, as inputs, are multiplied by gates 44-1 to 44-3 with coefficients W1 to W3, respectively, and the resulting products are summed together and output.

Abstract: Apparatus for generating sequences of elements including at least one task unit, each of which has an upper and a lower neural network connected in a hierarchical relationship and is operable to output a sequence of elements. Each of the upper and lower neural networks is a class of temporal neural networks having an infinite number of internal states.

Abstract: A method for using a neural network to deconvolute the effects due to surface topography from the effects due to the other physical property being measured in a scanning probe microscopy (SPM) or atomic force microscopy (AFM) image. In the case of a thermal SPM, the SPM probe is scanned across the surface of a sample having known uniform thermal properties, measuring both the surface topography and thermal properties of the sample. The data thus collected forms a training data set. Several training data sets can be collected, preferably on samples having different surface topographies. A neural network is applied to the training data sets, such that the neural network learns how to deconvolute the effects dues to surface topography from the effects dues to the variations in thermal properties of a sample.

Abstract: A method for configuring nanoscale neural network circuits using molecular-junction-nanowire crossbars, and nanoscale neural networks produced by this method. Summing of weighted inputs within a neural-network node is implemented using variable-resistance resistors selectively configured at molecular-junction-nanowire-crossbar junctions. Thresholding functions for neural network nodes are implemented using pFET and nFET components selectively configured at molecular-junction-nanowire-crossbar junctions to provide an inverter. The output of one level of neural network nodes is directed, through selectively configured connections, to the resistor elements of a second level of neural network nodes via circuits created in the molecular-junction-nanowire crossbar. An arbitrary number of inputs, outputs, neural network node levels, nodes, weighting functions, and thresholding functions for any desired neural network are readily obtained by the methods of the present invention.

Abstract: A learning apparatus for learning time series data, includes a learning unit for updating, in a self-organizing manner based on an observed value of the time series data, a time series pattern storage network including a plurality of nodes, each node having a time series pattern model representing a time series pattern of the time series data.

Abstract: A method for organizing processors to perform artificial neural network tasks is provided. The method provides a computer executable methodology for organizing processors in a self-organizing, data driven, learning hardware with local interconnections. A training data is processed substantially in parallel by the locally interconnected processors. The local processors determine local interconnections between the processors based on the training data. The local processors then determine, substantially in parallel, transformation functions and/or entropy based thresholds for the processors based on the training data.

Abstract: A method of marketing tangible and intangible products using existing devices and networks. Product information is transmitted along with content by radio stations. The information is displayed or is sent by text message to an integrated mobile telephone, radio, multimedia player. The user purchases the product by using a dedicated function to transmit the purchase information. The purchase is either accepted by the mobile telephone provider or approved by a financial institution and the order is fulfilled.

Abstract: A neural network computer (20) includes a weighting network (21) coupled to a plurality of phase-locked loop circuits (251-25N). The weighting network (21) has a plurality of weighting circuits (C11, . . . , CNN) having output terminals connected to a plurality of adder circuits (311-31N). A single weighting element (Ckj) typically has a plurality of output terminals coupled to a corresponding adder circuit (31k). Each adder circuit (31k) is coupled to a corresponding bandpass filter circuit (31k) which is in turn coupled to a corresponding phase-locked loop circuit (25k). The weighting elements (C1,1, . . . , CN,N) are programmed with connection strengths, wherein the connection strengths have phase-encoded weights. The phase relationships are used to recognize an incoming pattern.

Abstract: A monitoring system including a baseline model that automatically captures and models normal system behavior, a correlation model that employs multivariate autoregression analysis to detect abnormal system behavior, and an alarm service that weights and scores a variety of alerts to determine an alarm status and implement appropriate response actions. The baseline model decomposes the input variables into a number of components representing relatively predictable behaviors so that the erratic component e(t) may be isolated for further processing. These components include a global trend component, a cyclical component, and a seasonal component. Modeling and continually updating these components separately permits a more accurate identification of the erratic component of the input variable, which typically reflects abnormal patterns when they occur.

Abstract: A product-sum operation circuit includes a pulse width/digital conversion circuit (9) which converts a pulse signal having a pulse width representing an operand value into a digital signal, a sorting circuit (4) which outputs, in descending or ascending order of magnitude, a plurality of operand values Xi converted into digital signals by the pulse width/digital conversion circuit (9), and an accumulated sum circuit (1) which multiplies each operand value output from the sorting circuit (4) by a corresponding operand value Wi and calculates the accumulated sum of multiplication results. The pulse width/digital conversion circuit (9) includes a counter (10) which counts a clock and outputs a count value as a digital signal, and n trailing edge latch circuits (11-0-11-(n?1)) each of which latches a common count value output from the counter at the trailing edge of the input pulse signal.

Abstract: According to the invention, a method for creating an electronic greeting card enclosing an electronic gift is disclosed. In one step, the electronic greeting card selection is received from a sender along with a selection of at least one of a type of electronic gift, an amount for the electronic gift, and an identifier for a receiver of the electronic gift. Payment for the electronic gift is received from a money handler chosen by the sender. A code indicative of the electronic gift is received, whereby the code facilitates redemption of the electronic gift. The code is embedded in the electronic greeting card.

Abstract: An improved Artificial Neural Network (ANN) is disclosed that comprises a conventional ANN, a database block, and a compare and update circuit. The conventional ANN is formed by a plurality of neurons, each neuron having a prototype memory dedicated to store a prototype and a distance evaluator to evaluate the distance between the input pattern presented to the ANN and the prototype stored therein. The database block has: all the prototypes arranged in slices, each slice being capable to store up to a maximum number of prototypes; the input patterns or queries to be presented to the ANN; and the distances resulting of the evaluation performed during the recognition/classification phase. The compare and update circuit compares the distance with the distance previously found for the same input pattern updates or not the distance previously stored.

Abstract: A system and method for generating context vectors for use in storage and retrieval of documents and other information items. Context vectors represent conceptual relationships among information items by quantitative means. A neural network operates on a training corpus of records to develop relationship-based context vectors based on word proximity and co-importance using a technique of “windowed co-occurrence”. Relationships among context vectors are deterministic, so that a context vector set has one logical solution, although it may have a plurality of physical solutions. No human knowledge, thesaurus, synonym list, knowledge base, or conceptual hierarchy, is required. Summary vectors of records may be clustered to reduce searching time, by forming a tree of clustered nodes. Once the context vectors are determined, records may be retrieved using a query interface that allows a user to specify content terms, Boolean terms, and/or document feedback.

Abstract: According to a first aspect of the present invention there is provided a method of modelling a network comprising operating the network as a neural network and executing a neural network modelling algorithm on the network, whereby the network models its own response to a requested action.

Abstract: The present invention relates to a optimization method based on an evolution strategy according to which a model/structure/shape/design to be optimized is described by parameter sets comprising object parameters. The object parameters are mutated to create offsprings of the parameter set. The quality of the offsprings is evaluated. The parameter set furthermore comprises at least one strategy parameter representing the step-size of the mutation (f.e. the variance of the normal distribution) of associated object parameters. The number of object parameters as well as the number of associated strategy parameters can be adapted during the optimization process. The value of newly inserted strategy parameters can be estimated based on the information of correlated object parameters.

Abstract: Convolutional networks can be defined by a set of layers being respectively made up by a two-dimensional lattice of neurons. Each layer—with the exception of the last layer—represents a source layer for respectively following target layer. A plurality of neurons of a source layer called a source sub-area respectively share the identical connectivity weight matrix type. Each connectivity weight matrix type is represented by a scalar product of an encoding filter and a decoding filter. For each source layer a source reconstruction image is calculated on the basis of the corresponding encoding filters and the activities of the corresponding source sub-area. For each connectivity weight matrix type, each target sub-area and each target layer the input of the target layer is calculated as a convolution of the source reconstruction image and the decoding filter.

Abstract: An image commercial transactions system and method that implement sales according to the purpose of the seller is disclosed. An e-commerce system sells a picture and a handling condition specific to the picture, both being recorded on a predetermined recording medium in a predetermined format. The picture to be sold and the handling condition are accepted by an acceptor in a digital format. When a transaction is established, an accounting company carries out an accounting electronically for a purchaser of the data of the picture and the e-commerce condition, thereby both the picture to be sold and the handling condition are sold as digital data so that the purchased picture is used in a handling manner as intended by the seller. Consequently, the sale of the picture can be made so as to satisfy the intention of the seller.

Abstract: A memory system and a method as well as robotic apparatus are strong against noise and excellent in memory capacity, volume of calculation, quantity of physical memory, and memory responsiveness. It is designed to store, in the frame form, the first information on a symbol as well as the second information on a symbol supplied separately from a variety of inputs in relation to competitive neurons corresponding to the symbol in a way to strengthen the connection between relevant input neurons and competitive neurons in response to the input patterns of a variety of inputs for each symbol with the use of a competitive neural network having a set of input layers composed of a plurality of input neurons and a set of competitive layers composed of a plurality of competitive neurons.

Abstract: A method and system for data modeling that incorporates the advantages of both traditional response surface methodology (RSM) and neural networks is disclosed. The invention partitions the parameters into a first set of s simple parameters, where observable data are expressible as low order polynomials, and c complex parameters that reflect more complicated variation of the observed data. Variation of the data with the simple parameters is modeled using polynomials; and variation of the data with the complex parameters at each vertex is analyzed using a neural network. Variations with the simple parameters and with the complex parameters are expressed using a first sequence of shape functions and a second sequence of neural network functions. The first and second sequences are multiplicatively combined to form a composite response surface, dependent upon the parameter values, that can be used to identify an accurate model.

Abstract: Method intended for real-time modelling, by neural networks, of hydrodynamic characteristics of multiphase flows in transient phase in pipes. In order to specifically take account of the possible flow regimes of fluids in pipes, various neural or “expert” models are formed for several flow regimes (or subregimes) in the whole of the variation range of the hydrodynamic characteristics of the flows (preferably for each one of them), as well as a neural model estimating the probability of belonging of the flows to each flow regime or subregime, knowing some of the characteristics thereof. The probabilities obtained are used for weighting the estimations delivered by each neural model, the result of the weighted sum being then the estimation eventually retained. Applications to various industries and notably for modelling of hydrocarbon flows in pipelines.

Abstract: The vehicle control system having an adaptive controller is provided that accomplishes unsupervised learning such that no prior extensive training is needed for every situation. The inventive controller system is based on a neural network evolved with genetic algorithm. The genetic algorithm will determine the parameters of the neurons, the connections between the neurons and the associated weights to yield the best results. The genetic algorithm evaluates current candidate structures for accomplishing the desired result and develops new candidate structures by reproducing prior candidate structures with modification that replaces the least fit former candidate structures until the system is well satisfied. The vehicle control system is well satisfied when the desired result is met or some failure condition is triggered for vehicle control system whereby the action is never repeated.

Abstract: In a method and system for developing a neural system adapted to perform a specified task, a population of neural systems is selected, each neural system comprising an array of interconnected neurons, and each neural system is encoded into a representative genome. For a given genome, a processing gene encodes a neural output function for each neuron, and the connections from each neuron are encoded by one or more connection genes, each connection gene including a weight function. The given neural system is operated to perform the specified task during a trial period, and performance is continually monitored during the trial period. Reinforcement signals determined from the continually monitored performance are applied as inputs to the functions respectively associated with each of the processing genes and connection genes of the given neural system.

Abstract: Let us consider a plurality of input patterns having an essential characteristic in common but which differ on at least one parameter (this parameter modifies the input pattern in some extent but not this essential characteristic for a specific application). During the learning phase, each input pattern is normalized in a normalizer, before it is presented to a classifier. If not recognized, it is learned, i.e. the normalized pattern is stored in the classifier as a prototype with its category associated thereto. From a predetermined reference value of that parameter, the normalizer computes an element related to said parameter which allows to set the normalized pattern from the input pattern and vice versa to retrieve the input pattern from the normalized pattern. As a result, all these input patterns are represented by the same normalized pattern. The above method and circuits allow to reduce the number of required prototypes in the classifier, improving thereby its response quality.

Abstract: A signal source identification system and associated method are disclosed that utilize wavelet-based signal processing to facilitate signal source identification. In particular, the wavelet-based signal processing enables the extraction of fingerprint type signatures for signal sources using wavelet packet processing, and supplementary signal processing can be used to further enhance the accuracy of the system. This signal source identification system can be used for identifying signal sources within a received data signal, used for providing security features by verifying the identify of a transmitting device, and/or used in other environments where it is desirable to identify or differentiate among signal sources. Other features and variations can be implemented, if desired.

Abstract: A product-sum operation circuit includes a pulse width/digital conversion circuit (9) which converts a pulse signal having a pulse width representing an operand value into a digital signal, a sorting circuit (4) which outputs, in descending or ascending order of magnitude, a plurality of operand values Xi converted into digital signals by the pulse width/digital conversion circuit (9), and an accumulated sum circuit (1) which multiplies each operand value output from the sorting circuit (4) by a corresponding operand value Wi and calculates the accumulated sum of multiplication results. The pulse width/digital conversion circuit (9) includes a counter (10) which counts a clock and outputs a count value as a digital signal, and n trailing edge latch circuits (11-0–11-(n?1)) each of which latches a common count value output from the counter at the trailing edge of the input pulse signal.

Abstract: An artificial neuron is formed from an input subcircuit, a capacitor free leaky integrator subcircuit, and an output switching subcircuit. The input subcircuit is configured to supply a pulsed input signal. The capacitor free leaky integrator subcircuit is configured to supply a parasitic capacitance and to utilize the parasitic capacitance to provide differing time constants for the rising and falling edges of an output signal produced in response to the pulsed input signal. The output switching subcircuit s configured to, upon receipt of a sufficient output signal from the capacitor free leaky integrator subcircuit, switch off the input subcircuit and to release a neuron firing signal.

Abstract: An inventory management system utilizes unattended facilities remote from a central warehouse for service parts logistics. Items are placed in inventory in secure enclosures at the unattended facilities by the inventory management service or are delivered directly to the unattended facility. The unattended facilities may be located near one or more customers to reduce a service technician's travel time and customers' inventory costs. A service technician utilizes a passcode to retrieve needed items. The service technician may order items that are not kept in the inventory of the unattended facility in which case the items may be delivered to the unattended facility and the service technician may receive a notification related to all the items that comprise an order that the order is ready for pick up at an unattended facility.

Abstract: An initial set of individuals having design parameters of a blade as a gene, is determined at random (S12). Next, an analysis using Navier-Stokes equations is performed. On the basis of the analysis result, ranking (evaluation) of respective individuals are performed using a pressure loss coefficient, a trailing edge deviation angle and the like as objective functions (S14). When a shape of a blade having a desirable performance is obtained, or when a predetermined number of generations is achieved, the analysis is terminated assuming that a termination condition has been met (S22). When the termination condition has not been met, processes about individual selection, crossing between individuals and mutation are performed so that generation is incremented by 1. The above processes are repeated, so that Pareto solutions can be obtained according to MOGA in consideration of a trade-off relationship between the objective functions.

Abstract: The neural network processing system according to the present invention includes a memory circuit for storing neuron output values, connection weights, the desired values of outputs, and data necessary for learning; an input/output circuit for writing or reading data in or out of said memory circuit; a processing circuit for performing a processing for determining the neuron outputs such as the product, sum and nonlinear conversion of the data stored in said memory circuit, a comparison of the output value and its desired value, and a processing necessary for learning; and a control circuit for controlling the operations of said memory circuit, said input/output circuit and said processing circuit.

Abstract: An apparatus for maintaining components in neural network formed utilizing nanotechnology is described herein. A connection gap can be formed between two terminals. A solution comprising a melting point at approximately room temperature can be provided, wherein the solution is maintained in the connection gap and comprises a plurality of nanoparticles forming nanoconnections thereof having connection strengths thereof, wherein the solution and the connection gap are adapted for use with a neural network formed utilizing nanotechnology, such when power is removed from the neural network, the solution freezes, thereby locking into place the connection strengths.

Abstract: A method, system and machine-readable storage medium for monitoring an engine using a cascaded neural network that includes a plurality of neural networks is disclosed. In operation, the method, system and machine-readable storage medium store data corresponding to the cascaded neural network. Signals generated by a plurality of engine sensors are then inputted into the cascaded neural network. Next, a second neural network is updated at a first rate, with an output of a first neural network, wherein the output is based on the inputted signals. In response, the second neural network outputs at a second rate, at least one engine control signal, wherein the second rate is faster than the first rate.

Abstract: A temporal summation device can be composed of one or more nanoconnections having an input and an output thereof, wherein an input signal provided to the input causes one or more of the nanoconnection to experience an increase in connection strength thereof over time. Additionally, a voltage divider is formed by the nanoconnection(s) and a resistor connected to the output of the nanoconnection(s), such that the voltage divider provides a voltage at the output the nanoonnection(s) that is in direct proportion to the connection strength of nanoconnection(s). An amplifier is also connected to the voltage divider, wherein when the voltage provided by the voltage divider attains a desired threshold voltage, the amplifier attains a high voltage output thereby providing a temporal summation device thereof.

Abstract: The hardware of the present invention must be structured with the Brownian motion equation, Bayes' equation and its matrices as integral components. All data are input to a common bus bar. All data are then sent to all nodes simultaneously. Each node will have coded gates to admit the proper data to the appropriate matrix and Bayes' equation. Then, as the data are processed, they will be sent to a central data processing unit that integrates the data in the Brownian motion equation. The output is displayed in linguistic terms or in digital form by means of fuzzy logic.

Abstract: An analog neural computing medium, neuron and neural networks are disclosed. The neural computing medium includes a phase change material that has the ability to cumulatively respond to multiple input signals. Input signals induce transformations among a plurality of accumulation states of the disclosed neural computing medium. The accumulation states are characterized by a high electrical resistance. Upon cumulative receipt of energy from one or more input signals that equals or exceeds a threshold value, the neural computing medium fires by transforming to a low resistance state. The disclosed neural computing medium may also be configured to perform a weighting function whereby it weights incoming signals. The disclosed neurons may also include activation units for further transforming signals transmitted by the accumulation units according to a mathematical operation. The artificial neurons, weighting units, accumulation units and activation units may be connected to form artificial neural networks.

Abstract: A method is described to improve the data transfer rate between a personal computer or a host computer and a neural network implemented in hardware by merging a plurality of input patterns into a single input pattern configured to globally represent the set of input patterns. A base consolidated vector (U?*n) representing the input pattern is defined to describe all the vectors (Un, . . . , Un+6) representing the input patterns derived thereof (U?n, . . . , U?n+6) by combining components having fixed and ‘don't care’ values. The base consolidated vector is provided only once with all the components of the vectors. An artificial neural network (ANN) is then configured as a combination of sub-networks operating in parallel. In order to compute the distances with an adequate number of components, the prototypes are to include also components having a definite value and ‘don't care’ conditions. During the learning phase, the consolidated vectors are stored as prototypes.

Abstract: System and method for performing one or more relevant measurements at a target site in an animal body, using a probe. One or more of a group of selected internal measurements is performed at the target site, is optionally combined with one or more selected external measurements, and is optionally combined with one or more selected heuristic information items, in order to reduce to a relatively small number the probable medical conditions associated with the target site. One or more of the internal measurements is optionally used to navigate the probe to the target site. Neural net information processing is performed to provide a reduced set of probable medical conditions associated with the target site.

Abstract: The learning rate used for updating the weights of a self-ordering feature map is determined by a process that injects some type of perturbation into the value so that it is not simply monotonically decreased with each training epoch. For example, the learning rate may be generated according to a pseudorandom process. The result is faster convergence of the synaptic weights.

Abstract: A method for training a recurrent network represented by x(k+1)=f(W x(k)), where W is a weight matrix, x is the output of the network, and K is a time index includes (a) determining the weight matrix at a first time increment, (b) incrementing the time increment associated with a received data point, and (c) determining a change in the weight matrix at the incremented time interval according to the formula: ? ? ? ? W ? ( K ) = ? ? ? ? W ? ( K - 1 ) + ? ? ? ? ? ? ( K ) ? x T ? ( K - 1 ) ? ? ? V - 1 ? ( K - 1 ) - B ? ( K - 1 ) ? ? ? V - 1 ? ( K - 1 ) ? ? ? x ? ? ? ( K - 1 ) ? [ V - 1 ? ( K - 1 ) ? ? ? x ? ? ? ( K - 1 ) ] T 1 + x T ? ( K - 1 ) ? ? ? V - 1 ? ( K - 1 ) ? ? ? x ? ? ? ( K - 1 )