Abstract: There is provided a learning processing apparatus comprising: a learning processing unit configured to generate a control model that outputs a manipulated variable corresponding to an indicated variable and a process variable of a predetermined system by means of machine learning; a generation unit configured to generate controlling data that indicates a correspondence relation of a combination of the indicated variable and the process variable to the manipulated variable corresponding to the combination by using the control model; and a supply unit configured to supply the controlling data to a predetermined control apparatus.

Abstract: Target-based schema identification and semantic mapping for robotic process automation (RPA) are disclosed. When looking at a source, such as a document, a web form, a user interface of a software application, a data file, etc., it is often difficult for software to determine which fields are labels and which are values associated with those labels. Since values have not yet been entered for various labels (e.g., first name, company, customer number, etc.), these labels are easier to detect than when the target also includes various values associated with the labels. A selection of an empty target may be received and target-based schema identification may be performed on the empty target, determining labels and a type of the target. Semantic matching may then be performed between a source and the target. These features may be performed at design time or runtime.

Abstract: To keep plant performance constant in a control apparatus for controlling a plant including a plurality of units. The control apparatus (a PCM) controls an automobile including a plurality of units. The control apparatus includes a model controller that generates a target value of a characteristic to be achieved by each unit based on a model set for each unit, a unit specifier (a performance change determinator) that specifies a unit in which performance unique to the unit has changed among the units, and a target value corrector (an FF updater) that corrects the target value for the unit that has been specified by the unit specifier.

Abstract: A method, according to some implementations, includes obtaining trial design simulation results for a set of trial designs and determining a set of Pareto designs in the set of trial designs based at least in part on the trial design simulation results and one or more performance parameters. The method further includes determining a set of convex hull designs in the set of trial designs, determining a set of recommended designs based at least in part on the set of Pareto designs and the set of convex hull designs, and transmitting the set of recommended designs.

Abstract: A fire-protection system and a method for a container-type energy storage device and a storage medium are provided. The system includes at least one detector module, a data prediction apparatus and a fire-protection host of the container-type energy storage device, and the data prediction apparatus is communicatively connected to the at least one detector module and the fire-protection host of the container-type energy storage device, respectively. The current detection data of the detector can be predicted by using the historical detection data in the event of an abnormal communication link between the detector module and the fire-protection host of the container-type energy storage device. The detection data can be sent to the fire-protection host to ensure that data can be continuously provided to the fire-protection host.

Abstract: There are provided systems and methods for determining processing weights of rule variables for rule processing optimization. A service provider, such as an electronic transaction processor for digital transactions, may utilize different decision services that implement rules for decision-making of data including real-time data in production computing environments. Rules may correspond to coded statements that perform an automated decision-making service for the computing services and platforms of the service provider. When writing rules, different variables for data objects may be utilized, where each variable may perform a different operation and/or utilize a different operation for fetching and retrieving data used during rule processing. Each variable may therefore have a different data processing weights based on processing requirements of the data. Thus, optimization of rule authoring may be performed by mapping variables to other similar variables and showing a processing weight of each variable.

Abstract: A process includes: a first casting modelling stage producing resulting casting parameters; a second casting modelling stage performed using the resulting casting parameters of the first casting modelling stage and of higher fidelity than the first casting modelling stage; in parallel with the second casting modelling stage, a casting trial using the resulting casting parameters of the first casting modelling stage; and evaluating the casting trial.

Abstract: A linear motor motion control method, device, equipment and storage medium. The proposed invention uses an extended state observer constructed in advance based on the model parameters of the linear motor, and performs state estimation based on the total control amount of the linear motor and the actual displacement signal to obtain each observation signal. The phase advance controller is used to improve the estimated lag of the disturbance observation signal, and a model prediction controller built in advance based on the mathematical model of the linear motor is used to perform rolling optimization based on each observation signal to obtain the optimal control amount increment; The total control amount is updated based on the improved disturbance observation signal and the optimal control amount increment, and the corresponding drive signal is output to the drive end of the linear motor based on the updated total control amount.

Abstract: A predictive control system includes controllable equipment and a controller. The controller is configured to use a neural network model to predict values of controlled variables predicted to result from operating the controllable equipment in accordance with corresponding values of manipulated variables, use the values of the controlled variables predicted by the neural network model to evaluate an objective function that defines a control objective as a function of at least the controlled variables, perform a predictive optimization process to generate optimal values of the manipulated variables for a plurality of time steps in an optimization period using the neural network model and the objective function, and operate the controllable equipment by providing the controllable equipment with control signals based on the optimal values of the manipulated variables generated by performing the predictive optimization process.

Abstract: This disclosure relates to optimizing an operation of an equipment by a neural network based optimizer is provided. The method include receiving, information associated with at least one equipment instance (j) as an input at a predefined sequence of timestamps; training, a plurality of simulation models for each equipment instance to obtain a function (fj); processing, the external input parameters (et) to obtain a fixed-dimensional vector and passed as an input to obtain an vector (it); generating, a modified (it) from the output vector (it) based on a domain constraint value; computing, a reward (rt) based on (i) the function (fj), (ii) the modified (it), (iii) the external input parameters (et), and (iv) a reward function (Rj); and iteratively performing the steps of processing, generating, and computing reward (rt) for a series of subsequent equipment instances after expiry of the predefined sequence of timestamps associated with a first equipment instance.

Abstract: A method and a device for simulating a machining process of a workpiece on an NC-controlled machine tool by means of a self-learning artificial neural network. Process parameters both from a machining process on a real machine tool located in a manufacturing section and a digital machine model implemented in a simulation section are provided to the artificial neural network to learn the behavior of the machine tool including the tools and workpieces used and are reformatted into input parameters by means of mathematical transformation. By learning the behavior of the machining process, the artificial neural network ca, send output files back to the simulation software of the simulation section and optimally adapt the behavior of the digital machine model to the conditions of the real machine tool by adapting the simulation parameters and make it more efficient in order to optimize the machining process on the machine tool.

Abstract: A device for simulating a controlled machine or installation includes a process simulation apparatus designed to perform simulation steps that simulate a physical process of the machine or installation, and a controller simulation apparatus designed to perform simulation steps that simulate a controller of the machine or installation. The process simulation apparatus and the controller simulation apparatus exchange particular output values so as to simulate the controlled machine or installation in the respective simulation steps. The controller simulation apparatus transmits an item of information to the process simulation apparatus, which item of information describes a result time for an end of a simulation step performed by the controller simulation apparatus, while the process simulation apparatus is designed to adjust a duration of at least one of the simulation steps depending on the result time.

Abstract: An apparatus for treating a substrate includes a housing having a treatment space therein, a heating plate that supports the substrate in the treatment space and that has a plurality of heating members inside, and a temperature control unit that controls the plurality of heating members to heat the substrate supported on the heating plate, in which the temperature control unit controls the plurality of heating members using a plurality of control signals with different control periods.

Abstract: A method, apparatus and computer-readable instructions are described including obtaining a plurality of sets of training and test data packages (wherein: each of the plurality of sets comprises test data and training data, wherein the test data comprises a subset of a first plurality of data items and the training data comprises a remainder of the first plurality of data items; each data item of the first plurality of data items is allocated as test data for only one of the plurality of sets of training and test data packages; and each data item comprises a classification identifier); receiving a new data item having a classification identifier; and adding the new data item to one of the plurality of sets of training and test data packages as test data and adding the new data item to the other of the plurality of sets of training and test data packages as training data, wherein the one of the plurality of sets of training and test data packages to which the new data item is added as test data is selected depe

Abstract: A method and a device for the computer-assisted simulation of a modular technical system, wherein for each real module of the modular technical system, a corresponding virtual module is generated, is provided. The virtual module includes a controller for controlling a module-specific process and at least one module-specific simulation model, to which model type information is assigned, for simulating the model-specific process. The virtual module is designed to simulate the module-specific process that is controlled by the controller by means of the module-specific simulation model and/or the controller of the real module, and is provided for a computer-assisted simulation of the modular technical system as a data container. In particular, the following allows a virtual start-up of modular process systems.

Abstract: Autonomous vehicle model training and validation using low-discrepancy sequences may include: generating a low-discrepancy sequence in a multidimensional space comprising a plurality of multidimensional points; mapping each sample of a plurality of samples of a data corpus to a corresponding entry in the low-discrepancy sequence, wherein each sample of the plurality of samples comprises one or more environmental descriptors for an environment relative to a vehicle and one or more state descriptors describing a state of the vehicle; selecting, from the data corpus, a training data set by selecting, for each multidimensional point of the low-discrepancy sequence having one or more mapped samples, a mapped sample for inclusion in the training data set; and training one or more models used to generate autonomous driving decisions of an autonomous vehicle based on the selected training data set.

Abstract: Autonomous vehicle model training and validation using low-discrepancy sequences may include: generating a low-discrepancy sequence in a multidimensional space comprising a plurality of multidimensional points; mapping each sample of a plurality of samples of a data corpus to a corresponding entry in the low-discrepancy sequence, wherein each sample of the plurality of samples comprises one or more environmental descriptors for an environment relative to a vehicle and one or more state descriptors describing a state of the vehicle; selecting, from the data corpus, a training data set by selecting, for each multidimensional point of the low-discrepancy sequence having one or more mapped samples, a mapped sample for inclusion in the training data set; and training one or more models used to generate autonomous driving decisions of an autonomous vehicle based on the selected training data set.

Abstract: Methods, systems, and computer storage media for providing an optimal control configuration for a material processing system are provided. In operation, a material processing engine accesses causal graph input data. Causal graph input data includes input data of a continuous flow process. Based on the causal graph and the input data, a causal graph that aligns with do-calculus manipulations—associated with determining identifiable causal relationships corresponding to input materials of the continuous flow process—is generated. The causal graph is parsed based on the do-calculus manipulations to determine valid conditioning sets associated with estimating a causal impact on an optimization target. Based on the valid conditioning sets, an optimal control configuration comprising optimal control variable values is generated.

Abstract: A hover-capable flying machine such as a drone includes a robotic arm extending from the body, and an instrumentality for balancing the machine in response to disturbances such as those caused by picking up and dropping of the payload by the extended robotic arm. In embodiments, the end of the arm is equipped with a balancing rotor assembly that may provide lift sufficient to counteract the weight of the payload and/or of the arm. In embodiments, the machine's power pack is shifted in response to the disturbances. The power pack may be moved, for example, on a rail within and/or extending beyond the machine in a direction generally opposite to the extended arm. The power pack may also be built into a bandolier-like device that can be rolled-in and rolled out, thus changing the center of gravity of the machine.

Abstract: An execution environment for executing an event-oriented control program of a programmable logic controller, wherein the control program comprises a plurality of functional modules to be successively executed, is configured to execute the functional modules in an event-controlled manner on the occurrence of activation events that are each associated with the individual functional modules. In this respect, the individual activation events of the functional modules to be successively executed form an event chain. The execution environment comprises a monitoring module for monitoring an execution duration of the functional modules of the event chain, wherein the monitoring module is configured to check the execution duration for an exceeding of a predefined time duration.

Abstract: A method, computer system, and a computer program product for anomaly detection is provided. The present invention may include converting business process logs into a graphical data structure. The present invention may include generating an optimized graph encoding for anomaly detection using an unsupervised machine learning model. The present invention may include computing an anomaly score for each activity of the business process log using a process aware metric based on feature representation. The present invention may include labeling each of the one or more data points with a high anomaly score.

Abstract: The present disclosure provides a method for anomaly classification for an industrial control system (ICS) communication network based on statistical learning and deep learning. This method designs LSTM deep learning structure parameters and performs modeling analysis based on a large amount of traffic data during normal operation of the ICS communication network; based on real-time communication traffic data thresholds generated by a SARIMA online statistical learning model, designs correlated algorithms to analyze a numerical relationship between background traffic and real-time traffic; and classifies ICS communication network anomalies according to an ICS network anomaly classification algorithm.

Abstract: A virtual metrology method using a convolutional neural network (CNN) is provided. In this method, a dynamic time warping (DTW) algorithm is used to delete unsimilar sets of process data, and adjust the sets of process data to be of the same length, thereby enabling the CNN to be used for virtual metrology. A virtual metrology model of the embodiments of the present invention includes several CNN models and a conjecture model, in which plural inputs of the CNN model are sets of time sequence data of respective parameters, and plural outputs of the CNN models are inputs to the conjecture model.

Abstract: The present invention describes a method for gauging energy used for producing a unit of mass or volume of compressed gas (Specific Energy Consumption) in relation to a common output flow in a multiple compressor system, said method comprising: —from a first compressor, constructing an ideal specific energy consumption curve in the first compressor as a function of the output flow of the first compressor; and —from a first compressor and a second compressor, constructing a combined ideal specific energy consumption specific energy consumption curve in the first compressor and the second compressor as a function of the combined output flow of the first compressor and the second compressor, wherein the method involves constructing one or several ideal specific energy consumption curve(s) for multiple combined compressors, in any combination(s), and wherein the method involves creating a theoretical operation model for the multiple compressor system.

Abstract: A control system configured to serve one or more energy loads in a building comprises equipment configured to consume, produce, or store one or more resources including electricity, water, natural gas, steam, hot thermal energy, cold thermal energy, or electrical energy. The control system includes an asset allocator configured to receive an input model that describes a physical layout of the equipment and create a net list that defines connections between the equipment using the input model. The asset allocator is configured to discover one or more systems of interconnected equipment and one or more groups of equipment using the net list, formulate an optimization problem using the systems and groups of equipment, and operate the equipment according to the optimization problem.

Abstract: A computer-implemented method for monitoring a communication system includes identifying a set of signals that need to be transmitted over the communication system for proper functioning of the control and/or surveillance; for each signal from the identified set of signals, identifying one or more resources of the communication system that are needed for transmission of this signal; obtaining information that is indicative of the operational state of the identified resources; and evaluating, from the obtained information, at least one remedial activity which, when performed on at least one resource, and/or on the control and/or surveillance, is likely to improve, and/or to restore, the reliability of the control and/or surveillance.

Abstract: A system for commissioning a model, comprising one or more processing circuits configured to identify a first plurality of data points in the building, automatically tag at least a portion of the first plurality of data points with one or more first tags using context data extracted from and/or associated with the data points, the one or more entities comprising one or more of building equipment, building spaces, people, or events, identify at least one of the first plurality of data points for manual review and generate one or more suggested tags for the at least one data point, receive feedback from the manual review, and receive a second plurality of data points in the building and automatically tag at least a portion of the second plurality of data points with one or more second tags using the feedback from the manual review.

Abstract: Methods and systems for assessing, detecting, and responding to malfunctions involving components of autonomous vehicles and/or smart homes are described herein. Autonomous operation features and related components can be assessed using direct or indirect data regarding operation. Such assessment may be performed to determine the robustness of autonomous systems, including the use of virtual assessment of software components within a simulated environment. To this end, a server may retrieve one or more routines associated with autonomous operation. The server may also generate a set of test data associated with test conditions. The server may also execute an emulator that virtually simulates autonomous environment. The test data may be presented to the routines executing in the emulator to generate output data. The server may then analyze the output data to determine a quality metric.

Abstract: A system that includes artificial intelligence (AI) configured to identify text and images within an industrial reference. Example industrial references include electrical drawings and P&IDs. The system includes a method for training artificial intelligence model to recognize text characters and strings in addition to industrial images using a limited sample set. The use of a limited sample set improves computer performance by relying on a smaller dataset to train the model.

Abstract: A method for testing an updated version of an application for vehicles. In the method, input data for the application, which are used for a present version of the application on at least one vehicle, and output data of the present version of the application are received by a vehicle-external computing system, from the at least one vehicle via a wireless data link. The updated version of the application is executed on the vehicle-external computing system using the received input data. Output data of the updated version of the application are compared with the received output data of the present version of the application. An evaluation of the updated version of the application being carried out, based on the comparison.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for performing interactive digital image editing operations utilizing machine learning models and a feature backpropagation refinement layer. For example, the disclosed systems perform interactive digital image editing operations by incorporating a feature backpropagation refinement layer within a non-interactive machine learning model that utilizes a consistency loss to adjust the feature backpropagation refinement layer according to one or more user interactions. In some embodiments, the disclosed systems utilize a feature backpropagation refinement layer that includes a bias sublayer for localizing changes to a digital image and a convolutional sublayer for channel-wise scale and feature combinations across channels. In some cases, the disclosed systems utilize a consistency loss that facilitates localized modifications to a digital image based on distances of various pixels or features from a user interaction.

Abstract: A system and method for crowd-sourced environmental system control and building maintenance includes a server for providing selective access to building occupants and managers. Users are permitted to generate building reports in the form of (i) thermal reports using a thermal report module, and/or (ii) maintenance reports using a maintenance report module. The reports are each geo-located to locations within the building, and are then captured, stored, and aggregated at the server. The aggregated reports are sorted according to their geo-locations and comfort rules are used to (i) permit a manager at a client computer to access the server to respond, and/or (ii) automatically respond and assign a response status to particular reports. An inspection checklist interface is generated and populated to display a list of preventative maintenance tasks, each of the tasks being user-selectable to designate completion, with the updated status of the reports being stored at the server.

Abstract: A hover-capable flying machine such as a drone includes a robotic arm extending from the body, and an instrumentality for balancing the machine in response to disturbances such as those caused by picking up and dropping of the payload by the extended robotic arm. In embodiments, the end of the arm is equipped with a balancing rotor assembly that may provide lift sufficient to counteract the weight of the payload and/or of the arm. In embodiments, the machine's power pack is shifted in response to the disturbances. The power pack may be moved, for example, on a rail within and/or extending beyond the machine in a direction generally opposite to the extended arm. The power pack may also be built into a bandolier-like device that can be rolled-in and rolled out, thus changing the center of gravity of the machine.

Abstract: The disclosure provides an environment in which it is possible to switch an algorithm involved in an abnormality detection process. A control device: calculates a feature quantity from a state value acquired from a monitored object; uses a learning model on the basis of the calculated feature quantity to execute one of a plurality of types of algorithms for calculating a value indicating the probability that an abnormality is occurring in the monitored object; determines, on the basis of the calculated value, whether the abnormality is occurring; and switches, in accordance with a condition defined in advance, the one algorithm that is executed.

Abstract: A method for maintaining a physical asset based on recommendations generated by analyzing operational data and a composite model of a plurality of models representing the physical asset includes constructing, by a computing device, using a port-reduced static condensation reduced basis element approximation of at least a portion of a partial differential equation, the composite model. The computing device analyzes an error indicator associated with at least one model within the composite model to determine that the error indicator exceeds a tolerance level and increases a number of basis functions in the port-reduced static condensation reduced basis element approximation accordingly. The computing device receives first operational data associated with at least one region of the physical asset and updates the composite model. The computing device provides a recommendation for maintaining the physical asset, based upon the updated composite model.

Abstract: Provided is a method for the computer-assisted control of a technical system, in particular in a plant for generating energy, to achieve a predetermined technical behavior of the technical system, wherein an operating data set for controlling the system is provided. A system model for describing the mode of operation of the technical system is provided, wherein on the basis of the operating data set and on the basis of the system model, an optimization data set is determined by an optimization method. Based on the optimization data set, relevant parameters of the technical system that allow a more advantageous control of the technical system than other parameters of the technical system are selected using a selection method, wherein with the selected relevant parameters, a control method for the technical system is determined, wherein the technical system is controlled with the aid of the control method.

Abstract: The novel use of separate programs to control a parallel execution of a plurality of large scale linear program solvers executing sequentially on separate cores is disclosed. An embodiment detailing the system's use in optimizing a utility company's assets is also disclosed. As upgrades or better programs become available, in some embodiments each program in the system can be replaced without affecting the structure of the other programs. In some embodiments, the use of cloud based architecture allows for improved data collection and system execution as all that is needed to process data at a faster speed is to “rent” the additional physical or virtual cores from the provider.

Abstract: A continuous-time recurrent neural network (CTRNN) is described that exploits the nonlinear dynamics of micro-electro-mechanical system (MEMS) devices to model a neuron in accordance with a neuron rate model that is the basis for dynamic field theory. Each MEMS device in the CTRNN is configured to simulate a neuron population by exploiting the characteristics of bi-stability and hysteresis inherent in certain MEMS device structures. In an embodiment, the MEMS device is a microbeam or cantilevered microbeam device that is excited with an alternating current (AC) voltage at or near an electrical resonance frequency associated with the MEMS device. In another embodiment, the MEMS device is an arched microbeam device that is excited with a direct current voltage and exhibits snap-through behavior due to the physical design of the structure. A CTRNN can be implemented using a number of MEMS devices that are interconnected, the connections associated with varying connection coefficients.

Abstract: Systems and methods are provided to move the solving of multi-physics engineering simulations away from specific CAE, or combination CAD and CAE, applications. In one embodiment, an Application Programming Interface (API) is provided that can be integrated into any device, system, application, or software workflow. The API exposes a series of functions or modules that a user can use to create a simulation file that includes parameters such as a model for the simulation, physics for the simulation, timings for the simulation, and other parameters. The simulation file may then be executed on one or more nodes of a cloud-based computer cluster, and the results of executing the simulation can be provided back to the user. The user may then visualize the results using their preferred device, software, application, or workflow.

Abstract: The invention relates to a method for generating a control system for a target system, wherein: operational data is received; a first neural model component is trained with the received operational data for generating a prediction on a state of the target system based on the received operational data; a second neural model component is trained with the operational data for generating a regularizer for use in inverting the first neural model component; and the control system is generated by inverting the first neural model component by optimization and arranging to apply the regularizer generated with the second neural model component in the optimization. The invention relates also to a system and a computer program product.

Abstract: A system and a method of managing a manufacturing process includes receiving production data relating to the manufacturing process and determining an operational mode associated with the manufacturing process using historical, multivariate senor data. The method may further determine a recommended action to affect production based on the determined operational mode. The operational mode may be based on at least one of: a level of operation in a continuous flow process relating to a joint set of process variables, a representation of a joint dynamic of the set of process variables over a predefined length, and a joint configuration of an uptime/downtime of a plurality of units comprising a process flow.

Abstract: Methods and systems for assessing, detecting, and responding to malfunctions involving components of autonomous vehicles and/or smart homes are described herein. Autonomous operation features and related components can be assessed using direct or indirect data regarding operation. Such assessment may be performed to determine the robustness of autonomous systems, including the use of virtual assessment of software components within a simulated environment. To this end, a server may retrieve one or more routines associated with autonomous operation. The server may also generate a set of test data associated with test conditions. The server may also execute an emulator that virtually simulates autonomous environment. The test data may be presented to the routines executing in the emulator to generate output data. The server may then analyze the output data to determine a quality metric.

Abstract: A system, method, and apparatus is provided for production processes to coordinate the utilization of the operational zone for process variables and automate the execution of the target settings to maximize the production goals without requiring human intervention.

Abstract: The inhibition device includes a micro-controller configured with a triggering condition including a number of intervals and, for each interval, a corresponding duration and a corresponding threshold. Each interval is a range specifying how much the vehicle's acceleration pedal has changed its position in terms of percentages of a pedal stroke. Each duration specifies the fastest time duration allowable for the acceleration pedal to attain a corresponding interval of pedal position change. The micro-controller converts progress signals of the acceleration pedal to corresponding percentages, obtains a difference DEF between the successive percentages, records a time duration RES between successive progress signals, and calculates DEF/RES=X. When X is greater than or equal to a threshold of a corresponding interval, the micro-controller sends an idle signal to the vehicle's engine control unit or intercepts the progress signals to prevent them from reaching the engine control unit.

Abstract: Method for transferring data from a device to a data management means, switching unit, device and system The invention relates to a method for transferring data (16) from a device (6) to a data management means (4). In order to reduce the amount of data transferred and according to the method of the invention, using modeling data (26, 42) present in the device (6) a model (30, 44) described by the modeling data (26, 42) is determined. Using the model (30, 44), the data that is actually to be transferred to the data management means (4) is selected from a volume of data (40) provided for transfer. The device (6) transfers the selected data to the data management means (4).

Abstract: A plurality of evaluation functions and a machine learning result of each of the evaluation functions are output so that a relation between the evaluation function and the learning result can be ascertained. An output device includes: an output unit that outputs a plurality of evaluation functions used by a machine learning device that performs machine learning of parameters of components of a servo control device that controls a servo motor that drives an axis of a machine tool, a robot, or an industrial machine and a machine learning result of each of the evaluation functions; and an information acquisition unit that acquires the machine learning result from at least one of the servo control device and the machine learning device.

Abstract: Aspects of the disclosure include, for example, obtaining input data. Further embodiments include a determination of a fast path prediction for a first time period according to the input data based on a fast path model. Embodiments include providing instructions to deliver information to a user device according to the fast path prediction. Additional embodiments include obtaining additional input data. Embodiments include a determination of a slow path prediction for the first time period according to the input data and the additional input data based on a slow path model, retraining the fast path model according to the input data and the fast path prediction, and training the slow path model according to the slow path prediction. Embodiments include a determination of a fast path negative impact metric and determination of a slow path negative impact metric. Other embodiments are disclosed.

Abstract: A controller for controlling a vapor compression system is provided. The controller is configured to control an operation of the VCS with different combinations of setpoints for different actuators of the VCS to estimate a cost of operation of the VCS for each of the different combinations of setpoints, and compute, using a Bayesian optimization of the combinations of setpoints and their corresponding estimated costs of operation, a probabilistic surrogate model, wherein the probabilistic surrogate model defines at least first two order moments of the cost of operation in the probabilistic mapping. The controller is further configured to select an optimal combination of setpoints having the largest likelihood of being a global minimum at the surrogate model according to an acquisition function of the first two order moments of the cost of operation.

Abstract: A computer-implemented method for learning a policy for selection of an associative topic, which can be used in a dialog system, is described. The method includes obtaining a policy base that indicates a topic transition from a source topic to a destination topic and a short-term reward for the topic transition, by analyzing data from a corpus. The short-term reward may be defined as probability of associating a positive response. The method also includes calculating an expected long-term reward for the topic transition using the short-term reward for the topic transition with taking into account a discounted reward for a subsequent topic transition. The method further includes generating a policy using the policy base and the expected long-term reward for the topic transition. The policy indicates selection of the destination topic for the source topic as an associative topic for a current topic.

Abstract: Autonomous vehicle operational management may include traversing, by an autonomous vehicle, a vehicle transportation network. Traversing the vehicle transportation network may include operating a scenario-specific operational control evaluation module instance, wherein the scenario-specific operational control evaluation module instance is an instance of a scenario-specific operational control evaluation module, wherein the scenario-specific operational control evaluation module implements a partially observable Markov decision process. Traversing the vehicle transportation network may include receiving a candidate vehicle control action from the scenario-specific operational control evaluation module instance, and traversing a portion of the vehicle transportation network based on the candidate vehicle control action.