Abstract: An expert system selects a computer solution from a set of predefined, proven solution to meet a specific need. Each of the predefined solutions comprises a plurality of hardware platforms and associated software, and a communication facility between the hardware platforms. The system identifies and directs display of a multiplicity of different characteristics of computer solutions within the set. Then, the user selects one of the characteristics to reduce the number of possible solutions from the set. In response, the system may then display other characteristics which can be selected to further reduce the number of possible solutions from those identified after the one characteristic was selected. According to a preferred embodiment of the present invention, this narrowing process always results in one or more solutions from the set; there are no “dead ends”.

Abstract: A method implemented on a network of computers for allowing a plurality of users to collaborate in decision making to solve a problem, includes the steps of processing, at a central server, a group of proposals for solving the problem, submitting the group of proposals to the plurality of users at remote clients, and thereafter receiving, at the central server from the plurality of users, selections of proposals from the group of proposals. Determining, at the central server, a narrowed group of proposals in response to the selections of proposals, communicating the narrowed group of proposals to the plurality of users at the remote clients, each proposal in the narrowed group of proposals including sets of statements, and thereafter receiving, at the central server from one of the plurality of users, suggestions for modifying proposals in the narrowed group of proposals, are also included.

Abstract: A problem solving unit for obtaining a solution in a symbol process in response to a given problem is provided with a learning control unit for making a neural network learn the solution output from the problem solving unit. The output in response to the given problem from the learned neural network is transmitted to the problem solving unit as a (first) hint on obtaining the solution to the problem. Furthermore, a second neural network for outputting a second hint is provided, selects either the first hint or the second hint, and provides the selection result to the problem solving unit.

Abstract: A method implemented on a network of computers for allowing a plurality of users to collaborate in decision making to solve a problem, includes the steps of processing, at a central server, a group of proposals for solving the problem, submitting the group of proposals to the plurality of users at remote clients, and thereafter receiving, at the central server from the plurality of users, selections of proposals from the group of proposals. Determining, at the central server, a narrowed group of proposals in response to the selections of proposals, communicating the narrowed group of proposals to the plurality of users at the remote clients, each proposal in the narrowed group of proposals including sets of statements, and thereafter receiving, at the central server from one of the plurality of users, suggestions for modifying proposals in the narrowed group of proposals, are also included.

Abstract: A system for automatically detecting fires in select areas, and reacting thereto to put out the fires. A stationary, earth orbit satellite, pilotless drone aircrafts or piloted aircraft contains one or more infrared detectors and optical means for detecting small fires when they first occur in fields and wooded areas, preferably where man made campfires and trash dumping are prohibited. A computer in the satellite, drone or piloted aircraft and/or on the ground receives and analyzes image signals of the earth area or areas being monitored and, upon detecting infrared radiation of varying intensity and variable shape, indicative that a fire has started, generates coded signals which are (a) indicative of the coordinate locations of the fire, (b) the extent of the fire, (c) the shape of the area(s) burning, (d) the direction of movement of the fires (e) the speed(s) of the flame fronts, (f) smoke condition, (g) intensity of the fire, (h) fire ball location(s), etc.

Abstract: A fuzzy logic information processing system and method are disclosed that may be used not only with known or definite data input but also with uncertain data input. The uncertain data input may be represented by a set of values wherein the possibility of any particular or specific value within the set being the true or accurate value is uncertain. The preferred embodiment of the system provides for an extensor to extend or map a representation of the uncertain data into at least one additional dimension related to dimensions of a set of rules used for making fuzzy logic inferences. The set of rules may be provided effectively in a mapped or graphed form. The set of rules and uncertain data are combined, for instance by locating intersection regions, to produce an output set that may be also be described as a map or plot. In a presently preferred embodiment the uncertain inputs and rules are represented mathematically or symbolically and then operated on to produce an output set.

Abstract: A hospital-based integrated medical computer system for processing medical and patient information and for evolving medical knowledge, diagnoses and prognoses is disclosed. The system includes a medical processor including a memory and a plurality of medical data banks connected thereto. The medical processor and the medical data banks are designed to work in tandem for executing a plurality of instructions and/or obtaining information. A plurality of separate processor hardware modules are operatively connected to the medical processor. The modules include a communication module, at least one switching module, an administrative module and a knowledge module.

Abstract: A technical support incident resolution facility handles incidents, which are unexpected results which occur during the use of products. Within a vendor environment, a diagnostic knowledge trees database stores diagnostic knowledge trees for the products. A copy of a subset of the diagnostic knowledge trees is downloaded to a client environment. The subset of diagnostic knowledge trees provides diagnostic information for a subset of the products which are supported within the client environment. The copy of the subset of the diagnostic knowledge trees are used to supply diagnostic information to the client for incidents which potentially occur when a diagnostic program attempts to analyze the subset of the products.

Abstract: A method of displaying clustered data points in detail and in context within a data set. The method includes the step of identifying one or more clustered sets of data points within a data set. The data set includes a plurality of data points. The method also includes the steps of determining a respective data range segment for each cluster of data points, where each data range segment has a boundary and a scale interval, and displaying the data points in each segment such that each segment is mutually distinguishable. Where two or more data range segments are determined, the scale interval value for one of the data range segments is modifiable to differ from one or more of the other data range segments.

Abstract: A system for detecting interaction between different services on a telecommunications network includes a computer expert system. A data store in the expert system is programmed with data which represent attributes of service features. A rule store is programmed with rules which relate feature attributes to interaction behaviors. An inference engine is connected to the data store and to the rule store and processes the data and the rules to detect any interaction between the services. The data in the data store may be arranged as sets of objects, each object in a set corresponding to a different state transition of the corresponding feature. The different objects may be given sequence numbers corresponding to the time sequence of execution of the feature. At least some of the rules may relate to these sequence numbers.

Abstract: A computer-implemented method and apparatus for performing alpha-beta tracking, which generate an alpha curve, representing position errors between a predicted three-dimensional position and a reported three-dimensional position of the track of interest at a plurality of times; generate a beta curve, representing velocity errors between a predicted velocity and a reported velocity of the track of interest at the plurality of times; plot the alpha curve and the beta curve in a probability versus error plane; determine an acceleration and a change in acceleration for the track of interest at each of the plurality of times; and perform three-dimensional alpha-beta tracking on the track of interest such that as the three-dimensional alpha-beta tracking moves along the alpha curve and the beta curve in the probability versus error plane in a first direction, when a magnitude of the change in acceleration is negative, the three-dimensional alpha-beta tracking continues to move along the alpha curve and the beta cur

Abstract: The invention relates to a method of handling event recordings in a service database system. The database contains measurement tables (MT) which include consecutive rows (Ri). A single row contains data about a single measurement object. So that recording of a large counter group could be performed efficiently and, nonwithstanding, the measurement could be started without delay for all objects, (a) a single measurement counter is maintained copied to N copies on the row corresponding to each measurement object of the measurement table (b) time domain is divided into consecutive recording intervals so that only the values of a selected counter group located on the row are incremented during each recording interval, and (c) the recording and zeroing of the counter values is handled during a recording interval one measurement object at a time.

Abstract: The performance of a given computer task is optimized by utilizing a plurality of intelligent agents suited to perform the computer task but having varied degrees of domain knowledge. Based upon an objective criteria that may be determined for a given situation, one of the plurality of intelligent agents may be selected and dispatched to perform the task, thereby optimizing the performance of the computer task for a wide variety of situations.

Abstract: In a negotiation performed among a plurality of inferring units that are mutually connected through a network, at any time of which a consistent inferred state is obtained, the inferred state is accepted by the units as a settled inferred state. Since each inferring unit can perform an inference based on the settled inferred state, the inference can be effectively performed. Particularly, when a negotiation is hierarchically performed (hierarchical negotiation) or when a plurality of negotiations are performed in parallel (multi-negotiation), each negotiation can be consistently effected. In addition, in a negotiating process, each inferring unit negotiates with other inferring units using negotiation strategies having a standpoint of priority (role) and tolerance (transaction) of a request in the negotiation. In addition, each inferring unit autonomously changes the negotiation strategies for use corresponding to the negotiation history, the current internal state, and the current external state.

Abstract: Method and agent network architecture for processing a subject message, where each agent has a view of its own domain of responsibility. An initiator agent which receives a user-input request and does not itself have a relevant interpretation policy, queries its downchain agents whether the queried agent considers such message to be in its domain of responsibility. Each queried agent recursively determines whether it has an interpretation policy of its own that applies to the request, and if not, further queries its own further downchain neighboring agents. The further agents eventually respond to such further queries, thereby allowing the first-queried agents to respond to the initiator agent. The recursive invocation of this procedure ultimately determines one or more paths through the network from the initiator agent to one more more leaf agents.

Abstract: A system for performing high speed exponentiation in a secure environment. The system includes an interface for receiving encrypted data sent from a host system, a plurality of exponentiators capable of operating concurrently, an encyptor decrypting data received from a host system and encrypting data produced from the exponentiators, and logic circuitry for selecting an available and properly functioning exponentiator to perform exponentiation on the received data.

Abstract: A machine learning paradigm called Graph Transformer Networks extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as inputs and produce graphs as output. Training is performed by computing gradients of a global objective function with respect to all the parameters in the system using a kind of back-propagation procedure. A complete check reading system based on these concept is described. The system uses convolutional neural network character recognizers, combined with global training techniques to provides record accuracy on business and personal checks.

Abstract: An open architecture for arbitrarily combining data analysis algorithms and databases on the Internet where the data analysis algorithm and database may be from different vendors or suppliers. At the request of a customer, the two are combined on the fly while maintaining proper security and while enforcing some agreed upon payment from the customer to both the algorithm and database suppliers. In one embodiment, a message including an identifier of a user selected independent content provider and an identifier of a particular service associated with a service provider is sent to the service provider on a communication network. The user selected independent content provider is separate from the service provider. In response to the message, a computer executable code, which when executed by the content provider will cause the particular service to be performed against content controlled by the content provider, is sent from the service provider to the content provider.

Abstract: The invention relates to a process diagnosis system and a method for the diagnosis of processes and states in a technical process, in particular for the diagnosis of a power station process. The invention is a structured multi-agent system which corresponds to the process and has a plurality of autonomous diagnostic agents. The diagnostic agents in each case contain a neural network, with whose aid a reference behavior of process components that are to be monitored can be learned. In addition, automatic adaptation to a new reference behavior is also possible by the diagnostic agents.

Abstract: An automatic aider of human cognitive functions for the operation of computerized displays. The invention estimates in real-time the mental decision made in response to a displayed stimulus from the single-even, transient, evoked cerebral potential and the corresponding visual response. The invention attains high accuracy levels of decision classification by combining a unique parametric model of the cerebral potential with advanced techniques drawn from numerical analysis, artificial intelligence, and nonlinear regression analysis. The invention uses an expert system to determine the decision aiding to be provided to the human operator from the disparities among the estimations and the decisions that are expected from task scripts for the displayed stimulus.

Abstract: An improved classification system for classifying characteristics of an article into classes of characteristics based on features associated with the characteristics. The system includes a first rule-based classifier that provides rules that embody requirements of selected features so as to together define selected classes. These rules are applied to measured features of an article characteristic to assign one of the selected classes to that characteristic, should the article characteristic meet the feature requirements of one of the selected classes. The system also includes a trainable classifier configured based on a training set of preclassified characteristics, with the trainable classifier connected so as to accept from the first rule-based classifier an article characteristic not classified by the rule based classifier.

Abstract: A Multiple-Agent Hybrid Control Architecture (MAHCA) uses agents to analyze design, and implement intelligent control of distributed processes. A single agent can be configured to control a local process and a network of agents can be configured to control more complex distributed processes. Multiple agents interact through messages and can be either permanent or temporary. The network of agents interact to create an emergent global behavior. The network of agents support construction of closed-loop, autonomous systems which react to comply with two degrees of freedom: (1) a logic degree of freedom (useful for implementing switching between modes of control) and (2) an evolution degree of freedom (useful for implementing particular modes of control). Global behavior is emergent from individual agent behaviors and is achieved without central control through the imposition of global constraints on the network of individual agent behaviors (the logic agent network).

Abstract: A method of managing the processing of information using a first neural network, the information relating to the transmission of messages in a telecommunications network, uses the steps of:(i) monitoring the performance of the first neural network in processing the information;(ii) creating a second neural network of the same topology as the first when a predetermined performance threshold is reached, and(iii) retraining the second neural network while continuing to process the information using the first neural network. If the neural networks are implemented using objects, such retraining can be facilitated by using a persistance mechanism to enable the objects to be stored and moved. Applications in fraud detection.

Abstract: The invention relates to a modular architecture of a cellular network for improved large-scale integration, of the type which comprises a plurality of fuzzy cellular elements (C.sub.m,n) interconnected to form a matrix of elements having at least m rows and n columns, the row and column numbers describing the location of each element. Each fuzzy processor is adapted for connection to other processors of the same type such that a parallel architecture of the modular type can be implemented. The management of the architecture is facilitated by each submatrix being controlled by an individually dedicated fuzzy processor device.

Abstract: A system is described for automatically invoking computational resources without intervention or request from a user of the system. The computational resources may operating by searching across a network, or may themselves be located across a network. In the system a query-free information retrieval system is described in which the exact technical documentation contained in existing user or other technical manuals is provided to a user investigating apparatus having a fault. The user enters symptoms based upon the user's analysis of the apparatus, and in response the system provides information concerning likely faults with the apparatus. As the symptoms are entered, the relative value of individual faults is determined and related to the symptoms they cause. The user can then select technical information relating to probable faults in the system.

Abstract: A process device couples to a process control loop. The process device receives process signals. A memory in the process device contains a nominal parameter value and a rule. Computing circuitry calculates a statistical parameter of the process signal and operates on the statistical parameter and the stored nominal value based upon the stored rule and responsively provides an event output based upon the operation. Output circuitry provides an output in response to the event output.

Abstract: A simple approach to graph layout is fast and results in graphs that lend themselves to full visualization on a standard-sized computer monitor. The algorithm implemented allows the use the same spring and repulsion energies as in the force-directed model, or any other reasonably behaved energy function. In addition, numerical methods, either the technique of polynomial approximation or quadratic approximation, are applied. This allows approximating the minimum or maximum of a general function by picking a small set of points and computing the local optima of a polynomial function that passes through them. Polynomial or quadratic approximation is used to produce candidate drawings and, ultimately, to select a low-energy drawing from these candidates.

Abstract: A method implemented on a network of computers for allowing a plurality of users to collaborate in decision making to solve a problem, includes the steps of processing, at a central server, a group of proposals for solving the problem, submitting the group of proposals to the plurality of users at remote clients, and thereafter receiving, at the central server from the plurality of users, selections of proposals from the group of proposals. Determining, at the central server, a narrowed group of proposals in response to the selections of proposals, communicating the narrowed group of proposals to the plurality of users at the remote clients, each proposal in the narrowed group of proposals including sets of statements, and thereafter receiving, at the central server from one of the plurality of users, suggestions for modifying proposals in the narrowed group of proposals, are also included.

Abstract: Apparatus and method for learning current network behavior and predicting future behavior which utilizes a state transition graph. The graph includes nodes which represent network states, and arcs which represent trends in observable network parameters that result in a transition from a current state to another state. For example, a watch service may be instituted on multiple ports of a router, and the observed network traffic on the ports over time may be transformed into a state transition graph that represents network behavior. The network states may be labeled such as "good", or "bad", etc., according to a predetermined performance criteria. Once a state transition graph is constructed, the system may then monitor the current state and current trends of the network parameters in order to predict and display future network states. The system may include an automatic warning signal for alerting a user that the network is headed in the direction of a problematic state.

Abstract: A Multiple-Agent Hybrid Control Architecture (MAHCA) uses agents to analyze design, and implement intelligent control of distributed processes. A network of agents can be configured to control more complex distributed processes. The network of agents interact to create an emergent global behavior. Global behavior is emergent from individual agent behaviors and is achieved without central control through the imposition of global constraints on the network of individual agent behaviors. Agent synchronization can be achieved by satisfaction of an interagent invariance principle. At each update time, the active plan of each of the agents in the network encodes equivalent behavior modulo a congruence relation determined by the knowledge clauses in each agents's knowledge base. The Control Loop and the Reactive Learning Loop of each agent can be implemented separately. This separation results in an implementation runs faster and with less memory requirements than an unseparated arrangement.

Abstract: A method for linearization of feedback in neural networks, and a neural network incorporating the feedback linearization method are presented. Control action is used to achieve tracking performance for a state-feedback linearizable, but unknown nonlinear control system. The control signal comprises a feedback linearization portion provided by neural networks, plus a robustifying portion that keep the control magnitude bounded. Proofs are provided to show that all of the signals in the closed-loop system are semi-globally uniformly ultimately bounded. This eliminates an off-line learning phase, and simplifies the initialization of neural network weights.

Abstract: An inherently, and massively parallel data processing system and methodology is disclosed for evolving relative awareness, and related response states in a computerized environment. Any number of disparate data types can be configured with the goal of evolving complex data patterns involving these data forms across relative time and space. New data processing principles and a methodology are provided based on a new default logic that emulates the logic of the force of gravity as applied to proximity in time, space and form. Data form standards are provided that require time, place, and form factors at every convergent processing step. This system is capable of evolving complex awareness states as represented by ever larger associations of the original data samples without the need for knowledge bases, conditional rules or the like. Patterns are discerned in an emergent manner.

Abstract: A social learning inferencing engine for a wide range of information searching applications is generally applicable to a wide range of applications due to the engine's interfaces and the objects involved in these interfaces. The basic interfaces are a record of a user's score of a object, a count of the number of times a user references an object, and a prediction of a user's score of a object given the user has not previously scored the object. The scores of this user and other users strongly similar or strongly dissimilar to this user for this object and other objects strongly similar or strongly dissimilar to this object are used in making this prediction. The two central object classes in the system are the users and the objects. The user object class contains member fields that identify the user, specify configuration values specific to this user (these configuration values being used in predicting the scores of the objects for this user), and links to objects that the user has scored or referenced.

Abstract: A method is described for performing distributed genetic programming using a server and a plurality of client machines which are connected together by a computer network such as the Internet. The genetic programming seeks to optimise a population of individuals against one or more predetermined fitness criteria. The method includes downloading instructions for performing a fitness evaluation on an individual from the server to the client machines; distributing individuals from the population of individuals from the server across the plurality of client machines; and evaluating the fitness of the distributed individuals at the client machines by using the downloaded instructions. Those individuals which have the best fitness are preferentially selected for breeding to produce the next generation of individuals. This breeding is preferably also performed on the client machines.

Abstract: An information processing device for processing information based on object networks, each of which represents data and processing of the data as objects in a graph.

Abstract: In a cooperative reasoning apparatus comprises a plurality of problem solving units for cooperatively solving various problems and replication unit for replicating a corresponding problem solving unit in responsive to a replication request from one of the plurality of problem solving units, each problem solving unit determines whether or not its own reasoning unit has an ability of reasoning a given problem. If NO, the problem solving unit requests another problem solving unit to solve the problem. Further, each problem solving unit determines whether or not its own reasoning unit is performing reasoning of another problem. If YES, the problem solving unit requests the replication unit to replicate the problem solving unit, so that the problem is solved by the replicate.

Abstract: A rule-based data processing system includes a memory having stored therein a number of groups of agents. Each group is defined by respective sets of rules, with the system running the respective sets of rules in parallel. The agents are in two clusters: "script agents" which are arranged as a sequentially enabled chain and "operator agents" arranged to carry out selected procedural steps. The selection of the procedural step is made within each operator agent based on of one or more external factors, and is triggered by enablement of a script agent of the sequence prior to that script agent carrying a marker identifying an operator agent.

Abstract: The present invention relates to a radar emitter recognition system and method for classifying incoming emitters into their functional roles as disclosed by their electronic signatures and the context within which the radar transmissions are received. An electronic support system provides incoming data, including unknown attribute information, to a neural network which has been synthesized or trained to calculate a network solution indicative of an emitter's classification within a range of attributes. Similarly the electronic support system provides incoming data, including unknown context data, to a fuzzy logic system that has been provided with possibility distributions to classify the emitter as originating from one of several strategic contexts. The resultant categorizations from the neural network and the fuzzy logic system are combined in a classifier to yield an improved recognition of the emitter under observation.

Abstract: An optoelectronic cellular neural network, which can be programmed optically, in amorphous or polycrystalline silicon, which makes up a monolithic image processing system with optical input and output which can be programmed by optical signals. Its layered structure for both the upper and lower surfaces are occupied, without discontinuity, by photosensitive and photoemissive devices. The network basically consists of an input photosensitive layer, a processing layer, a photosensitive control layer and also an optical control mask.

Abstract: An RTA or similar rule-based agent (102) is enabled to construct a virtual simulation of its environment by the provision of an internal prediction module (100). The prediction module comprises a rule population run in tandem with the population (106) defining the agent behaviors. The prediction module rules represent predictions of agent behavior state changes and their accuracy is periodically checked (110), with more accurate rules being assigned a higher fitness rating. A genetic algorithm (108) defines mutation operators by which further rules are evolved from those having the highest fitness. When a predetermined level of fitness (prediction accuracy) is achieved, the prediction module rules provide (116) a virtual simulation of the environment to the agent behaviors by direct control in place of external (real world) stimuli.

Abstract: In the design and implementation of neural networks, training is determined by a series of architectural and parametric decisions. A method is disclosed that, using genetic algorithms, improves the training characteristics of a neural network. The method begins with a population and iteratively modifies one or more parameters in each generation based on the network with the best training response in the previous generation.

Abstract: Hyperlinear chromosomes are arrays of parameters stored in a computer readable memory, for use in implementing a genetic algorithm. Each chromosome may represent the mapping of a problem, including physical parameters, onto constituent genes which are addressed in memory as multiple, intersecting vectors in n-dimensions, where n is >2. A computing system is adapted to perform hyperlinear crossover, reproduction and fitness evaluation on the hyperlinear chromosomes. An adaptive computing system produces optimized control signals based on the attainment of a desired level of fitness of one or more hyperlinear chromosomes.

Abstract: An arrangement for modeling a non-linear process including at least one input variable (x1, x2) and at least one output variable (y) can include a neural network and a device for specifying functional (or operational) values. A function of the neural network is determined in a first part of the domain of input variables (x1, x2) by learning from measuring data, which are obtained from the process by acquiring measured values. An empirically based device for specifying functional (or operational) values, preferably a fuzzy system, is provided in a second part of the domain of input variables (x1, x2) in which there are no measuring data for training the neural network. This arrangement is particularly useful when it is implemented in controllers.

Abstract: In the control of a power station installation having a number of power station blocks, in which each power station block is controlled by using at least one reference variable, it is intended to permit reliable determination of especially favorable reference variables while also taking the current installation condition into account. To this end, a management system for the power station installation includes a computer unit which determines reference variables for the power station block or for each of the power station blocks through the use of a genetic algorithm, and an optimization module which is connected to the computer unit. The optimization module is connected to a number of neural networks and one neural network is assigned to each power station block.

Abstract: A signal generator implements a dynamic behaviour described by differential equations specifying a predetermined functional relationship. The generator includes a mapping section for mapping inputs onto outputs according to a mathematical correspondence, differentiators at selective ones of the inputs for providing time-derivatives, and a feedback path for selectively coupling outputs to inputs, either directly or via the differentiators. The feedback path and differentiating means constrain the mapping and establish aforesaid relationship.

Abstract: A data processing system (10) selectively weights a fuzzy logic rule in response to a single "REVW" software instruction. In response to the REVW instruction, the data processing system (10) fetches a set of fuzzy inputs associated with the fuzzy logic rule, and determines a minimum fuzzy input from the set. The data processing system (10) then selectively weights the minimum fuzzy input to provide a fuzzy output of the fuzzy logic rule, by multiplying the minimum fuzzy input by a corresponding weight. In one embodiment, a carry bit in a condition code register (60) determines whether the fuzzy logic rule is to be weighted. In response to the single REVW instruction, the data processing system (10) further performs this selective fuzzy rule weighting operation for all rules in a fuzzy rule base.

Abstract: An automatic data flow architecture builder is disclosed that is operable to take raw data which is stored in a raw data buffer (60) and transform it for storage in a transformed data buffer (78). A plurality of transform blocks (68), (70) and (72) are provided for this transform operation, these disposed in a predetermined data flow. When the user inputs a new transform to be disposed within the data flow of the transforms, rules are applied via a rule-base processing system (74) to apply a set of predetermined rules in a rule database (76) to the transform. These rules determine where the transform is to be inserted. This provides an automatic construction operation of a data flow architecture.