Abstract: A finite state electrical automaton modeled after a human neuron comprises a plurality of weighted inputs that pass into a state computing unit. A feedback mechanism changes the weights of the inputs as needed to control the response of the automaton to a desired output. A clock signal allows the automaton to function as a discrete time system. Unlike the threshold gates, the present automaton is capable of outputting an n-bit digital value analogous to a cell membrane potential. Because this automaton is capable of outputting more than two simple states it is a better building block for building neural nets.

Abstract: An apparatus, computer-readable medium and method for use in association with case-based reasoning and the like utilize a novel decision tree data structure that incorporates a search criterion in association with each test answer to a test criterion defined within a decision node, for use in selecting cases from a search space that match the associated test answer to the test criterion. As such, rather than storing identifiers to the actual cases in a case library, or search space, within a decision tree data structure, search criteria are used to provide the mechanism by which those cases that represent most likely best matches can be dynamically selected.

Abstract: The computer system includes a receptor field (2) with sensors (Ri) each of which receives data with specific characteristic (A, B, C). These data are passed to processors (Pi, Pi/k), whereby only those connections (Li) between sensors and processors are released that are suited to an evaluation of the data according to a combination of specific data dictated by a phase program of a phase program circuit (7). The computer system also includes a selector circuit (71) that discards those program commands from dictated program commands (73) that lead to a “senseless” computation result. A motor program circuit (8) for the control of effectors (9) may be connected to the computer system that at least contribute to the movement of the receptor field (2) in order to bring the receptor field closer to suitable data with specific characteristics in order to enable better execution of the program.

Abstract: A technique is provided for systematically constructing one or more correlation rules for use by an event management system for managing a network with one or more computing devices. The technique comprises the following steps. First, in association with an event cache, event data representing past or historical events associated with the network of computing devices being managed by the event management system is obtained. Next, a first pattern is found or detected in the obtained event data associated with the event cache. The pattern is then classified. Then, at least one correlation rule is constructed based on the classified pattern. Lastly, in association with the event cache, the one or more events included in the pattern are replaced with a composite or cumulative event such that hierarchical patterns may be subsequently found for use in constructing further correlation rules.

Abstract: The present invention provides a system, method and article of manufacture for personal catalog and knowledge management. The system includes a data collection module for collecting data from a visible data source, a data classification module for classifying the data, a data commentary module for adding value to the data and for providing comment on the data, and a data access module for accessing the data in a storage device. The present invention avoids disadvantages of lacking effective management for personal massive information and can be applied in various data sources. The information can be effectively transferred to personal useful knowledge and further managed by data classification and adding value to the data.

Abstract: A method of and system for determining the state-of-health of a proton exchange membrane fuel cell stack connected to a load comprises detecting the real part of the impedance Z1 of the fuel cell stack at a selected frequency; detecting the voltage V1 of the fuel cell stack at open circuit; detecting the voltage V2 of the fuel cell stack when the maximum load current is being drawn from said fuel cell stack; and determining the state of health of said fuel cell stack from a fuzzy system trained in a relationship between said real part of the impedance of the fuel cell stack at the selected frequency, the voltage of the fuel cell stack at open circuit, and the voltage of the fuel cell stack when the maximum load current is being drawn from said fuel cell stack.

Abstract: A system and method for improving a causal network is provided. A new apriori probability is determined for a repair or a configuration factor within the causal network and compared to an old apriori probability. If the new apriori probability differs from the old apriori probability by more than a predetermined amount, the causal network is updated. Further, in another aspect, a causal network result is stored for a causal network, wherein the causal network includes a plurality of root causes with a symptom being associated with each of said root causes. An existing link probability is related to the symptom and root cause. An expert result or an actual data result related to each of the symptoms is stored. A new link probability is computed based on the stored causal network result, and expert result or the actual data result.

Abstract: A circuit implementing a non-integer order dynamic system includes a neural network that receives at least one input signal and generates therefrom at least one output signal. The input and output signals are related to each by a non-integer order integro-differential relationship through the coefficients of the neural network. A plurality of such circuits, implementing respective non-integer order controllers can be interconnected in an arrangement wherein any of the integral or differential blocks included in one of these circuits generates a signal which is fed to any of the integral or differential blocks of another circuit in the system.

Abstract: Apparatus for control of a complex process, said process being described by a plurality of input variables, a plurality of intermediate variables and a plurality of output variables having relationships therebetween such that ones of said inputs and said intermediate variables effect respectively different output variables, each of said output variables having a target, said apparatus comprising an optimizer for finding an optimum value for respective ones of said input and intermediate variables to maximize a summed convergence of said output variables to said targets.

Abstract: The invention provides an arrangement optimization problem processing apparatus for arranging a plurality of nodes in an optimum condition in a two- or more-dimensional space, by which an optimum arrangement of a plurality of nodes can be determined at a high speed even where a node arrangement optimization problem having a large problem scale is to be processed. The arrangement optimization problem processing apparatus includes a hyper node formation section for grouping the plurality of nodes to form a plurality of hyper nodes each formed from a set of nodes, a hyper node arrangement section for executing an optimization problem solution algorithm to determine solutions to a problem of arrangement of the plurality of hyper nodes formed by the hyper node formation section in the generation space and arranging the plurality of hyper nodes in the generation space based on one of the determined solutions.

Abstract: The present invention provides a method and system for representing fuzzy information, and performing fuzzy logic and control operations on that information, using a quantum system. According to one embodiment fuzzy logic and control operations are performed on a quantum computer. The present invention extends quantum information processing beyond purely Boolean-logical information processing, by providing a quantum mechanical method for representing fuzzy information and realizing fuzzy logic and control.

Abstract: An autonomous system comprises an agent, constituting the behavioural identity of a robot, and a supporting device that is a physical installation which can implement the agent. The agent has a state which has a controlling influence on, and changes during, system operation. The agent's state is distinguishable from, and isolatable from, the permanent parts of the supporting device. The supporting device comprises hardware, software components for operating the hardware, software components for maintaining the agent environment and non-changing parts of the agent implementation, and software components for reading/writing the isolable agent state. An extraction module can extract the agent state and transform it into a representation for transmission across a network. An inserting module can insert a received agent state into the supporting device so as to embody a received agent on that supporting device.

Abstract: A method and apparatus for adding new learning tasks to an incremental supervised learner provide a flexible incremental representation of all training examples encountered, thereby permitting state representations for new learning tasks to take advantage of incremental training already completed by encoding all past training examples as negative examples for a hypothetical learning task. The state representation of the hypothetical learning task is copied as the initial state representation for a new learning task to be initiated, is initialized with negative training examples of all previously presented training examples, thereby permitting the learning task to incorporate the previous examples efficiently.

Abstract: A method of and system for determining the state-of-health of a lead acid battery of the type commonly used in portable external defibrillators comprises detecting an impedance characteristic of the battery at at least one selected frequency, counting the number of complete charge/discharge cycles that the battery undergoes, and determining the state of health of the battery from a fuzzy system trained in a relationship between the impedance characteristic and the cycle number of the lead acid battery and the state-of-health, wherein the state-of-health is a function of and varies with the battery's ability to deliver power required by the load and the battery's capacity to meet load requirements.

Abstract: A feedback control system for automatic on-line training of a controller for a plant, the system having a reinforcement learning agent connected in parallel with the controller. The learning agent comprises an actor network and a critic network operatively arranged to carry out at least one sequence of a stability phase followed by a learning phase. During the stability phase, a multi-dimensional boundary of values is determined. During the learning phase, a plurality of updated weight values is generated in connection with the on-line training, if and until one of the updated weight values reaches the boundary, at which time a next sequence is carried out to determine a next multi-dimensional boundary of values followed by a next learning phase.

Abstract: Data processing methods and apparatus, wherein an object to be appraised is inputted; the inputted object to be appraised is divided into at least one structural elements which are stored in storage unit; information is inputted which indicates an appraisal for the inputted object to be appraised; a combination of elements constituting the object to be appraised is corresponded to the inputted appraisal, and the correspondence is classified into at least one criterions which are stored in the storage means; an arbitrary criterion is selected from among stored criterions; a combination of structural elements is obtained on the basis of the selected criterion; appraisal information is inputted for the obtained combination of structural elements; the correspondence of the obtained combination of structural elements to the appraisal is compared with the selected criterion to identify a criterion.

Abstract: In a computer system functioning as an autonomous agent with a robotic controller wherein the computer system need not be programmed to perform a specific task, values in an array of error variables are obtained from comparison between an array of resources variables used to indicate resource use and state of an Autonomous Agent and an array of corresponding desired levels for the resource variables. Each individual value in the array of error variables represents an error in the actual value of a particular resource variable as compared to its desired value. Derivative variables for the resource variables and for parameters controlling behavior of the Autonomous Agent are created. The values of the array of error variables and their associated derivative variables are used to adjust values of the behavior-controlling parameters thereby modifying behavior of the Autonomous Agent.

Abstract: A system and method for enhancing knowledge discovery from data using multiple learning machines in general and multiple support vector machines in particular. Training data for a learning machine is pre-processed in order to add meaning thereto. Pre-processing data may involve transforming the data points and/or expanding the data points. By adding meaning to the data, the learning machine is provided with a greater amount of information for processing. With regard to support vector machines in particular, the greater the amount of information that is processed, the better generalizations about the data that may be derived. Multiple support vector machines, each comprising distinct kernels, are trained with the pre-processed training data and are tested with test data that is pre-processed in the same manner. The test outputs from multiple support vector machines are compared in order to determine which of the test outputs if any represents a optimal solution.

Abstract: A system is disclosed that provides a goal based learning system utilizing a rule based expert training system to provide a cognitive educational experience. The system provides the user with a simulated environment that presents a business opportunity to understand and solve optimally. Mistakes are noted and remedial educational material presented dynamically to build the necessary skills that a user requires for success in the business endeavor. The system utilizes an artificial intelligence engine driving individualized and dynamic feedback with synchronized video and graphics used to simulate real-world environment and interactions. Multiple “correct” answers are integrated into the learning system to allow individualized learning experiences in which navigation through the system is at a pace controlled by the learner.

Abstract: A fuzzy logic based classification (FLBC) method for the automated discrimination of objects and the automated identification of nodules based on their features, a computer programmed to implement the method, and a storage medium which stores a program for implementing the method, wherein nodule (or, object) features are first normalized and then automatically selected. Based on the selected features, suspect nodules (or, objects) are pre-grouped and then subjected to the corresponding trained linear classifier to remove those false positive nodules or abnormal objects that are linearly separable. Finally, the remaining suspect nodules or objects are further subjected to a trained fuzzy classifier for removing those false positive nodules or abnormal objects that are not linearly separable.