Abstract: A generalized pattern recognition is used to identify faults in machine condition monitoring. Pattern clusters are identified in operating data. A classifier is trained using the pattern clusters in addition to annotated training data. The operating data is also used to cluster the signals in the operating data into signal clusters. Monitored data samples are then classified by evaluating confidence vectors that include substitutions of signals contained in the training data by signals in the same signal clusters as the signals contained in the training data.

Abstract: According to a technique, an electronic device is configured to correspond to characteristic features of a biological synapse. The electronic device includes multiple bipolar resistors arranged in parallel to form an electronic synapse, an axonal connection connected to one end of the electronic synapse and to a first electronic neuron, and a dendritic connection connected to another end of the electronic synapse and to a second electronic neuron. An increase and decrease of synaptic conduction in the electronic synapse is based on a probability of switching the plurality of bipolar resistors between a low resistance state and a high resistance state.

Abstract: According to a technique, an electronic device is configured to correspond to characteristic features of a biological synapse. The electronic device includes multiple bipolar resistors arranged in parallel to form an electronic synapse, an axonal connection connected to one end of the electronic synapse and to a first electronic neuron, and a dendritic connection connected to another end of the electronic synapse and to a second electronic neuron. An increase and decrease of synaptic conduction in the electronic synapse is based on a probability of switching the plurality of bipolar resistors between a low resistance state and a high resistance state.

Abstract: The present invention relates to a system for mapping external inputs and internal goals toward actions that solve problems or elicit external rewards. The present invention allows an instructor to test and train an agent to perform dynamic task selection (executive control) by using a schema that computes the agent's emotional and motivational states from reward/punishment inputs and sensory inputs (visual, auditory, kinematic, tactile, olfactory, somatosensory, and motor inputs). Specifically, the invention transforms the sensory inputs into unimodal and bimodal spatio-temporal schemas that are combined with the reward/punishment inputs and with the emotional and motivation states to create an external/internal schema (EXIN schema), that provides a compressed representation assessing the agent's emotions, motivations, and rewards. The invention uses the EXIN schema to create a motor schema to be executed by the agent to dynamically perform the task selected by the instructor.

Abstract: Disclosed herein are methods and systems for advising and operating a power plant and related devices. In an embodiment, a power plant operator via a client 135 requests from a server 115 advisory information regarding a current power plant startup. The client 135 may receive custom advisory information based on data of an initial state of the power plant and data from past power plant startups.

Abstract: An automated facilities management system has the ability to predict occupant behavior by identifying recurring patterns in the way that people use buildings and comparing them with environmental characteristics. This technology is not limited to human behavior patterns, but extends to any mechanical systems or data points that tend to vary in recurring patterns. The data processing is carried out by rules engines triggered by relational database modifications.

Abstract: This document discusses, among other things, a system capable of resolving interactions between programmable parameters for operation of a medical device. Programming these devices is a difficult task when many parameters are involved. The disclosed systems and methods attempt to reduce and minimize constraint violations between interdependent parameters using an initial set of parameter values supplied by user (typically a physician) input or calculated automatically, and constraint violations describing invalid parameter values. If possible, a set of parameter values with less egregious constraint violations is generated and may be displayed to the user. A user is prompted to accept the set of parameter values and program the medical device.

Abstract: A method is described for semantic classification in human-machine dialog applications, for example, call routing. Utterances in a new training corpus of a new semantic classification application are tagged using a pre-existing semantic classifier and associated pre-existing classification tags trained for an earlier semantic classification application.

Abstract: A method to build, manage, and analyze a safety instrumented model in software of safety instrumented system architecture for a safety instrumented system in a facility, with test plans. The safety instrumented system architecture comprises at least one instrumented protective function and the non-transitory computer instructions that use a software model in support of process safety lifecycle management.

Abstract: Non-transitory computer instructions to computer generate, manage, and analyze a safety instrumented model in software of safety instrumented system architecture for a safety instrumented system in a facility, with test plans. The safety instrumented system architecture comprises at least one instrumented protective function and the non-transitory computer instructions that use a software model in support of process safety lifecycle management.

Abstract: A method of emulating the human brain with its thought and rationalization processes is presented here, as well as a method of storing human-like thought. The invention provides for inclusion of psychological profiles, experience and societal position in an electronic emulation of the human brain. This permits a realistic human-like response by that emulation to the people and the interactive environment around it.

Abstract: An active element machine is a new kind of computing machine. When implemented in hardware, the active element machine can execute multiple instructions simultaneously, because every one of its computing elements is active. This greatly enhances the computing speed. By executing a meta program whose instructions change the connections in a dynamic active element machine, the active element machine can perform tasks that a digital computer are unable to compute. In an embodiment, instructions in a computer language are translated into instructions in a register machine language. The instructions in the register machine language are translated into active element machine instructions. In an embodiment, an active element machine may be programmed using instructions for a register machine. The active element machine is not limited to these embodiments.

Abstract: Certain embodiments of the present disclosure support techniques for power efficient implementation of neuron synapses with positive and/or negative synaptic weights.

Abstract: In some embodiments, there is provided a technique for detecting a consumer's skipping habits at a given time and determining the consumer's current preferences based at least in part on those skipping habits. Skipping habits are determined by detecting which content is skipped (or not skipped) during presentation of content. Skipping habits, indicating trends in the consumer's consuming or skipping of content, that are detected during presentation of content may be used to determine a consumer's current preferences. Selection of content for presentation may be based on current preferences of the consumer. In this way, a consumer's interactions with the content, including the consumer's skipping habits, can be used to alter a selection of content to be presented to the consumer.

Abstract: Methods of analyzing solutions to a failure of a product are provided. A method comprises evaluating the fitness of solutions associated with a plurality of individuals in a population for the failure. Each of the plurality of individuals comprises a dominant genotype and a recessive genotype. Each genotype represents a solution for addressing a potential failure of the product. A fitness function is applied to the dominant genotype of each individual. The fitness function is configured to determine a confidence value for one or more of the solutions based on historical data regarding the solutions that is stored in a database. The method further comprises storing previously encountered genotypes in the recessive genotypes of the individuals and determining a proposed solution for addressing the failure of the product based on the fitness evaluation.

Abstract: A knowledge storage system is described. A specific embodiment is a computer system comprising a knowledge base of general knowledge in structured form which can be added to and queried by untrained users. Various embodiments include the facility for remote computers to access the knowledge stored in the system, natural language questions to be answered, profile screens giving general knowledge about an object in the system, and methods for distinguishing between reliable and unreliable facts.

Abstract: Methods for discovery of local causes/effects and of Markov blankets enable discovery of causal relationships from large data sets and provide principled solutions to the variable/feature selection problem, an integral part of predictive modeling. The present invention provides a generative method for learning local causal structure around target variables of interest in the form of direct causes/effects and Markov blankets applicable to very large real world datasets even with small samples. The selected feature sets can be used for causal discovery, classification, and regression. The generative method GLL can be instantiated in many ways giving rise to novel method variants. The method transforms a dataset with many variables into either a minimal reduced dataset where all variables are needed for optimal prediction of the response variable, or a dataset where all variables are direct causes and direct effects or the Markov blanket of the response variable.

Abstract: A questionnaire generation process presents a first subset from a set of questions of the questionnaire and receives first answers from a user. The first answers are used to determine whether the first answers are sufficient to give definite values to conditions of first rules, wherein the first rules have conditions for providing output. When the first answers are not sufficient, the conditions of the first rules can be used to identify a second subset of the questions, wherein the second subset of questions has second answers such that a combination of the first and second answers is sufficient to give definite values to the respective conditions of the first rules, and the second subset of questions can be presented to the user.

Abstract: A neuro-fuzzy controller is provided. The neuro-fuzzy controller includes a predictor that receives inputs and makes prediction inputs. The prediction inputs are passed to a fuzzy cluster module that includes a neural network fuzzifing said prediction inputs and passing the result to an inference engine. The output of the inference engine is defuzzified and provided as an output of the controller. The fuzzifier and defuzzifier preferably represent a neural network employing a trigonometrical series. The inference engine preferably employs rules that are determined using genetic programming.

Abstract: A system to build, manage, and analyze a computer generated risk assessment model and perform a layer of protection analysis. The system uses a computer generated safety instrumented system model for managing a process safety lifecycle for a safety instrumented system in a facility. The computer generated safety instrumented system model has at least one instrumented protective function.