Abstract: A system and method for configuring a unique computer name record for an information handling system included in a network of a plurality of information handling systems. The method and system for dynamically generating a unique computer name for each information handling system that is connected to a network of information handling systems includes reading a service tag identifier that uniquely identifies the information handling system, incorporating at least a portion of the service tag identifier to define the unique computer name record; and using a substantially similar boot program to boot the information handling system and the plurality of information handling systems.

Abstract: A converged network accessible by client terminals is provided. The converged network includes a wide area network, a local area network, and a gateway linked to the wide area and local area networks. The gateway integrates billing and authentication functions of the wide area and local area networks.

Abstract: The present disclosure addresses a system and method for failure tolerant communications using a transmission control protocol, preferably SCTP. In a preferred embodiment, an association is created between two instances of SCTP, where each instance is an endpoint. While an SCTP association provides for multiple IP addresses providing for multiple paths between the instances, it expressly does not provide for failover of the node occupied by the instance itself. The preferred embodiment provides a duplicate instance of SCTP on a separate node in the cluster which provides a hot back-up to the primary instance. The duplicate instance is maintained by replicating the state information for the association to keep the duplicate instance relatively synchronized with the primary instance.

Abstract: The invention provides in one aspect a method for generating a schedule for the performance of a process, wherein the process comprises a plurality of steps. Each step of the process comprises one or more operations. The method comprises first obtaining input containing information defining the process and then generating from the input a series of nodes definitions, each node definition corresponding to at least one step of the process. Each node definition includes duration and device usage information relating to at least one step and further includes information identifying at least one previous step and at least one subsequent step. Then, one or more tasks are generated using the series of node definitions, each task comprising at least one step of the process, such that every step in the process is associated with at least one task.

Abstract: A process modeling system and method develop a set of process model inputs for a process model, such as a neural network, from values for a number of process input variables and at least one process output variable. The system and method first determine a correlation measurement between each of the process input variables and the process output variable and select a set of potential model input variables based on the correlation measurements. The system and method then iteratively determine a succession of sets of potential model input variables by performing a regression analysis on the selected set of potential model input variables and the model output variable and by then refining the set of potential model input variables based on the result of the regression analysis and on the correlation measurements. After a number of iterations, the system and method choose a set of potential model input variables as the set of model inputs and develop a process model from the chosen set of model inputs.

Abstract: The present invention provides a method and apparatus for measuring at least one signal characteristic. Initially, a set of features is selected which characterize a signal. An intelligent system, such as a neural network, is trained in the relationship between feature sets and signal characteristics. The selected feature set is then extracted from a first input signal. The extracted feature set from the first signal is input to the trained intelligent system. The intelligent system creates an output signal based on the feature set extracted from the first input signal. This output signal is then used to characterize the input signal. In one embodiment, the invention assesses voice quality, typically as expressed in MOS scores, in a manner which accurately corresponds to the analysis of human evaluators. For voice signals processed by voice coders, the present invention provides a measurement technique which is independent of various voice coding algorithms and consistent for any given algorithm.

Abstract: A knowledge processing system and method provides a personal computer-based intelligent network to incorporate personal functions with knowledge domain functions and database management functions. The knowledge processing system includes: a memory for storing knowledge in a plurality of knowledge modules in a knowledge bank, in which the knowledge includes data associated with pre-existing solutions to previous problems; and a processing unit, operating knowledge-based software configured to represent a specific user, for generating a plurality of artificial intelligence based modules, and for executing the plurality of artificial intelligence base modules to process input data, including problem related data, for generating a solution-related module from the data representing the pre-existing solutions, with the solution-related module corresponding to a solution to the current problem.

Abstract: Each daisy chain circuit is serially connected to the two adjacent neuron circuits, so that all the neuron circuits form a chain. The daisy chain circuit distinguishes between the two possible states of the neuron circuit (engaged or free) and identifies the first free "or ready to learn" neuron circuit in the chain, based on the respective values of the input (DCI) and output (DCO) signals of the daisy chain circuit. The ready to learn neuron circuit is the only neuron circuit of the neural network having daisy chain input and output signals complementary to each other. The daisy chain circuit includes a 1-bit register (601) controlled by a store enable signal (ST) which is active at initialization or, during the learning phase when a new neuron circuit is engaged. At initialization, all the Daisy registers of the chain are forced to a first logic value.

Abstract: A fuzzy development-support device includes a data input unit, a fuzzy-inference execution unit and a result verification unit. As an example, the data input unit includes a display unit connected to a membership function generator and a grid pitch designation unit for designating a grid pitch on a grid sheet displayed on the display unit for creation of membership functions. The grid pitch designation unit allows variation of grid pitch on the grid sheet. Thus, an operator uses the grid pitch designation unit to achieve an effective input of membership functions by generating the grid sheet with a pitch adequate for a desired shape of membership function.

Abstract: With respect to pattern recognition or the like, this invention is aimed at reducing the arithmetic processing steps of determining analogy between an inputted pattern and reference patterns in order to enhance the speed of the recognition process. At first, a quantization code book is designed to prepare a single-output table and a mixture-output table. Then, referring to these tables, single-output data and mixture-output data are worked out from an inputted pattern. In accordance with these data thus worked out, the adaptability between the inputted pattern and reference patterns is calculated in order to obtain the analogy between them.

Abstract: Any deterministic finite-state automata (DFA) can be implemented in a sparse recurrent neural network (RNN) with second-order weights and sigmoidal discriminant functions. Construction algorithms can be extended to fault-tolerant DFA implementations such that faults in an analog implementation of neurons or weights do not affect the desired network performance. The weights are replicated k times for k-1 fault tolerance. Alternatively, the independent network is replicated 2k+1 times and the majority of the outputs is used for a k fault tolerance. In a further alternative solution, a single network with k.eta. neurons uses a "n choose k"encoding algorithm for k fault tolerance.

Abstract: A data processing system for testing a rulebase implemented in a rule evaluation process utilized for transforming fuzzy inputs to fuzzy outputs in a fuzzy logic operation, the rule evaluation process including a plurality of rules, wherein a path in the fuzzy logic operation includes one of the fuzzy inputs specified by the path, one of the plurality of rules specified by the path, and one of the fuzzy outputs specified by the path, wherein the rule evaluation process implements a MIN/MAX method of rule evaluation. The system determines which paths in the fuzzy logic operation can be tested simultaneously, and assigns values to test vectors in order to test the paths in a manner consistent with the determination of which paths in the fuzzy logic operation can be tested simultaneously, wherein paths that can be tested simultaneously can be tested by a same test vector.

Abstract: Method and apparatus for selecting an optimized subset of trajectories from an available class of potential trajectories in a velocimetry application. In an exemplary method, a neural network is constructed wherein each neuron in the network represents a trajectory in the overall class. A binary output of each neuron indicates whether the object represented by the neuron is to be selected. In the exemplary method, the neural network is in an initially converged state. The network is then alternately excited and constrained so that it settles to additional converged states. During excitation, correction factors including a parameter-optimizing term are applied to neuron input potentials. During constraint, the parameter-optimizing terms are interrupted. Each time the network converges, the outputs of the neurons in the network are decoded to establish a subset of trajectories to be selected, and a value for an optimization parameter associated with the established subset is computed.

Abstract: Method and apparatus for selecting an optimal number of trajectories from an available class of potential trajectories in a velocimetry application. In an exemplary method, a neural network is constructed wherein each neuron in the network represents a trajectory in the overall class. A binary output of each neuron indicates whether the trajectory represented by the neuron is to be selected. In the exemplary method, the neural network is initialized with a starting solution wherein the network is in an initially converged state. The network is then alternately excited and constrained so that it settles to additional converged states. During excitation, correction factors including a set-size maximizing term are applied to neuron input potentials. During constraint, the set-size maximizing terms are interrupted. Each time the network converges, the outputs of the neurons in the network are decoded to obtain a subset of trajectories which are to be selected.

Abstract: A knowledge based computing system is authored using a directed graph presented to the author at an authoring time. The directed graph has one or more question nodes and one or more answer nodes. The question nodes and the answer nodes connected to one another on one or more paths by links between each of the question nodes and each of the answer nodes so that question nodes and answer nodes alternate as the path is traversed in a path direction so that a "QA directed graph" is created. Each question node associated with a question data structure and each answer node associated with a answer data structure that are populated with information accessed from the author using question and answer templates associated with respective question and answer nodes on the QA directed graph. After the expert system is created (authored) using the QA directed graph it can be run at a run time to provide and access information from a service user.

Abstract: Many machines, particularly computers, execute decision processes during their operation. Such decision processes generally involve ascertaining the values of a number of condition factors and then determining the desired outcome in accordance with a predetermined decision function. This decision function may take the form of a number of individual statements relating condition-factor value combinations to particular outcomes. To facilitate end-user generation and modification of a decision function by generation and modification of a set of component statements, a structured representation for the component statements is presented to the user and statements are created and modified within this structured environment. Before a new or modified set of statements is accepted, it is checked for consistency between statements.

Abstract: The pulse-coupled automatic recognition system processes information utilizing parallel neural network and transmits information to and from the processing sites as time signals which encode in their pulse phase structure the geometrical content of the spatial distributions of light. A locating device then measures the coordinates of the spatial distributions (pulsating segment) and displays the coordinates of the pulsating segment on a screen for observation. The pulsating segment indicates the presence and location of the component of the input scene that corresponds to the segment.

Abstract: A control system for controlling the output of at least one plant process output parameter is implemented by adaptive model predictive control using a neural network. An improved method and apparatus provides for sampling plant output and control input at a first sampling rate to provide control inputs at the fast rate. The MPC system is, however, provided with a network state vector that is constructed at a second, slower rate so that the input control values used by the MPC system are averaged over a gapped time period. Another improvement is a provision for on-line training that may include difference training, curvature training, and basis center adjustment to maintain the weights and basis centers of the neural in an updated state that can follow changes in the plant operation apart from initial off-line training data.

Abstract: A controller for directing the actions of an autonomous device in response to the existence or actions of objects in the physical world comprises program means for fusing physical world data and inferred property confidence factors into a plurality of representational instances, at least one representational instance having an inferred behavior interface property for soliciting a response of the autonomous device, program means stored in a random access memory for implementing a plurality of independent behavior instances for carrying out response tasks, program means stored in the random access memory for implementing a mission control task by generating a task list of behavior instances to be performed and program means stored in the random access memory for implementing an execution engine for executing the behavior instance at the head of the task list.

Abstract: In a multilayered neural network for recognizing and processing characteristic data of images and the like by carrying out network arithmetical operations, characteristic data memories store the characteristic data of the layers. Coefficient memories store respective coupling coefficients of the layers other than the last layer. A weight memory stores weights of neurons of the last layer. Address converters carry out arithmetical operations to find out addresses of nets of the network whose coupling coefficients are significant. A table memory outputs a total coupling coefficient obtained by inter-multiplying the significant coupling coefficients read out from the coefficient memories of the layers. A cumulative operation unit performs cumulative additions of the product of the total coupling coefficient times the weight of the weight memory. Arithmetical operations are carried out only on particular nets with a significant coupling coefficient value. The speed of operation and recognition can be improved.