Abstract: Implementations of the present disclosure relate to methods, devices, and computer program products for event processing. In the method, first data associated with a first time window is obtained, the first data comprising a first object and a first group of events that are related to the first object. Second data associated with a second time window is obtained, the second data comprising a second object and a second group of events that are related to the second object, the second time window being different from the first time window. An event model describing an association relationship between an object and an event that is related to the object is determined based on the first and second data. With these implementations, multiple time windows are used in determining the event model, and thus the event model may have better performance in accuracy and immediacy aspects.

Abstract: Various embodiments relate to network capabilities. Devices of a network can have different capabilities. The network can provide artificial intelligence (AI) enabled, machine learning (ML) enabled, deep learning (DL) enabled networked access to these capabilities. The capabilities can share a common AI/ML/DL-enabled open layer-based net-centric logical protocol architecture. Also, different features can be achieved through different layers. As an example, AI enabled access can be achieved through the application layer, ML enabled access and DL enabled access can be achieved through the presentation layer and the session layer, and network access is achieved through the transport layer, the network layer, the link layer, and the physical layer.

Abstract: A user feature value measurement method includes: generating training data of at least one user that by acquiring standard feature values and measurement feature data input multiple times by the user, wherein the training data of each user comprises a standard feature value set and a measurement feature data set; training a data calculation model of each user based on the training data; acquiring current feature data of a target user, and determining a data calculation model of the target user according to the current feature data and the measurement feature data set; and calculating a user feature value of the target user based on the current feature data and the data calculation model of the target user.

Abstract: Systems, computer-implemented methods, and computer program products to facilitate reducing error propagation when combining generative aligners and transition-based aligners are provided. According to an embodiment, a system can comprise a processor that executed components stored in memory. The computer executable components comprise a generative alignment component, an error propagation component, a discriminative parser, and a stochastic oracle policy component. The error propagation component can compute a posterior distribution over one or more hard alignments of parts given a pair of the generative alignment component. The discriminative parser can be trained via the stochastic oracle policy component to reduce error propagation when combining the generative alignment component with the discriminative parser.

Abstract: Apparatuses, systems, and techniques for bounding area planning using a congestion prediction model. Placement data associated with cells of an IC design is identified. A graph based on the identified placement data is generated. The graph is provided as input to a machine learning model. The machine learning model is trained to predict, based on a given graph associated with cells according to a respective IC design, a congestion level for cells at one or more bounding areas of a respective IC design. Outputs of the machine learning model are obtained. The outputs include congestion data indicating a congestion level for a first bounding area of the IC design. Cells are designated for installation at a region, of the IC design, corresponding to the first bounding area.

Abstract: Disclosed is an apparatus for a motor imagery training, which includes a measuring unit that measures a brain signal while a user performs a motor imagery training, a preprocessing unit that performs preprocessing with respect to the brain signal, a feature extraction unit that selects a time period including information related to a motor imagery from the preprocessed brain signal and calculates feature data corresponding to the brain signal of the selected time period, and a classification unit that classifies the brain signal into one of a plurality of classes based on the feature data, and the motor imagery training is any one of a first training in which the user imagines moving a body part and a second training in which the user imagines feeling a somatosensory stimuli of a tangible object using the body part.

Abstract: The subject technology receives first party training data provided by an end-user of a baseline machine learning model. The subject technology determines a first set of common features based on the first party training data. The subject technology receives, from at least one data source. The subject technology determines a second set of common features based on the set of datasets. The subject technology trains, using the first set of common features and the second set of common features, a second machine learning model, the second machine learning model incorporating additional training data from the external data supplier during training compared to the baseline machine learning model. The subject technology generates a boosted machine learning model based at least in part on the training, the boosted machine learning model comprising the trained second machine learning model.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for preparation of a quantum state encoding an approximate normal distribution (QSEAND) in a set of qubits. An example method includes initializing the set of qubits by preparing the set of qubits in an initial quantum state. The example method also includes encoding the approximate normal distribution in the quantum state of the set of qubits, wherein encoding the approximate normal distribution comprises preparing the set of qubits to be in a quantum state representing a plurality of Fourier coefficients, and applying an inverse quantum Fourier transform to the set of qubits in the quantum state representing the plurality of Fourier coefficients to obtain the QSEAND. The example method also includes utilizing the QSEAND, wherein the utilization alters or transfers the QSEAND.

Abstract: A supportive software-based “toolbox” for optimizing finite state machine (FSM)-modeled systems. The optimization may include defining a plurality of alternative models for the FSM-modeled system and iterating one or more of the domain alternative into iterated alternatives. The optimization may include generating a plurality of stateflow representations for the FSM-modeled system according to the iterated alternatives, and based thereon, generating a model score for each of the stateflow representations predictively ranking the stateflow representations based at least in part on one or more of user experience, usability, correctness, transformability, effectiveness, and readiness.

Abstract: Transforming model data, including: applying a transformation to data generated by a machine learning model; and providing the transformed data to a consumer of the transformed data, wherein the consumer is configured to: reverse the transformation applied to the transformed data; and perform one or more operations based on the data.

Abstract: A computer-implemented system and method for estimating a Cumulative Distribution Function (CDF) are provided. The method includes: receive input data representing a volume V of a target space indicating a future target event; compute, using the trained neural network, an estimation of a first flux through a boundary of the volume V; compute, using the trained neural network, an estimation of a second flux through a boundary of a volume W of a base space based on the estimation of the first flux through the boundary of the volume V; generate, using the trained neural network, an estimation of a CDF for the volume V based on the second flux through the boundary of the volume W; compute a probability for the future target event based on the estimated CDF for the volume V; and generate a control command based on the probability for the future target event.

Abstract: Recommending machine learning models is provided. The method comprises training machine learning models, wherein each machine learning model is trained with a unique respective dataset. Metadata associated with each machine learning model is extracted, wherein the metadata includes properties of the respective dataset used to train the machine learning model. The machine learning models and metadata are stored in a model catalog. Upon receiving a new dataset, similarity scores are calculated between the new dataset and the machine learning models in the model catalog according to the properties of the datasets in the metadata of the machine learning models. A closest match machine learning model is identified from the model catalog for the new dataset according to similarity score. Responsive to a determination that the closest match machine learning model exceeds a similarity threshold, predictions for the new dataset are generated with the closest match machine learning model.

Abstract: Embodiments of the disclosure provide a method, an apparatus, a device, and a computer-readable storage medium for presenting a session message. The method includes obtaining at least one message in a target session; and presenting, in a session aggregation interface, a target component corresponding to the target session. The target component is configured to present description information of the target session and a visual representation of the at least one message, a representation type of the visual representation is determined based on a message type of the at least one message, and the session aggregation interface is configured to present at least one visual component including the target component. Therefore, according to embodiments of the disclosure, the visual representation of the message received in the session can be conveniently provided on the session aggregation interface, such that the user can conveniently and intuitively obtain the message content in the session.

Abstract: Arrangements for intelligent provisioning of quantum programs to quantum hardware are provided. In some aspects, a quantum program of a plurality of quantum programs to be executed on target quantum hardware may be received from a digital computing device. The quantum program may be scanned and optimized for minimum quantum bit (qubit) consumption using one or more machine learning models. Based on an accuracy requirement of a quantum program output, a criticality level of the quantum program may be identified. In addition, a qubit count associated with the quantum program, indicating a number of qubits used to perform quantum processing of the quantum program, may be identified. Based on the identified criticality level and qubit count, an allocation of qubits together with target quantum hardware may be assigned for deploying the quantum program. The target quantum hardware may ingest the quantum program and perform quantum processing of the quantum program.

Abstract: A building energy management includes building equipment, one or more data platform services, a timeseries database, and an energy management application. The building equipment operate to monitor and control a variable and provide raw data samples of a data point associated with the variable. The timeseries database stores a plurality of timeseries associated with the data point. The plurality of timeseries include a timeseries of the raw data samples and the one or more optimized data timeseries generated by the data platform services based on the raw data timeseries. The energy management application generates an ad hoc dashboard including a widget and associates the widget with the data point. The widget displays a graphical visualization of the plurality of timeseries associated with the data point and includes interactive user interface options for switching between the plurality of timeseries associated with the data point.

Abstract: A method for establishing a defect detection model and an electronic apparatus are provided. A first classification model is established based on a training sample set including a plurality of training samples. The training samples are respectively input to the first classification model to obtain a classification result of each training sample. A plurality of outlier samples that are classified incorrectly are obtained from the training samples based on the classification result. A part of outlier samples that are classified incorrectly is deleted from the training samples, and the remaining training samples are used as an optimal sample set. A second classification model is established based on the optimal sample set so as to perform a defect detection through the second classification model.

Abstract: The disclosed techniques include obtaining sensor data from one or more sensors configured to detect movement related to a user of the one or more sensors, and determining, based on the sensor data, of an occurrence of a gesture-based physical behavior event of the user. The techniques further cause adjustment of a medication dosage for delivery to the user based on determining the occurrence of the gesture-based physical behavior event.

Abstract: The representation learning apparatus acquires M second-type mixed feature representations extracted from M first-type mixed feature representations. The apparatus acquires M mixed labels obtained by mixing N labels. The apparatus calculates the L similarities of L label combinations selected from the M mixed labels. Each of the L label combinations has K mixed labels selected from the M mixed labels, each of the L similarities represents the degree of similarity of the K mixed labels, and the L similarities are formulated based on a qualitative and quantitative constraint condition. The apparatus performs a computation of a loss function based on the M second-type mixed feature representations and the L similarities.

Abstract: A method of Bayesian Variational Inference using Asymmetric Hamiltonian Monte Carlo includes gathering a number of data samples for a Hamiltonian Monte Carlo computation and instantiating an auxiliary distribution on the data samples, the auxiliary distribution being asymmetric. A Hamiltonian Monte Carlo computation is performed with the auxiliary distribution and the plurality of data samples. Upon determining that a metric of the computation outcome does not meet a target metric criterion that is based on a target distribution, the auxiliary distribution is adapted to an output of the computation and the Hamiltonian Monte Carlo computation is re-executed with the adapted auxiliary distribution. A report is generated in response to determining that the target metric is well estimated.

Abstract: Disclosed herein are embodiments of a system, method, and non-transitory computer-readable storage media for generating sampling plans for a selected agriculture area and providing a user interface configured to display sampling plan information to a user to allow for validation and traceability of sample collection in the agriculture area. One or more embodiments allow for sample plan information to be based in part on food safety audit information, some or all of which may have been collected using the system.