Abstract: A method for computing possibly optimal policies in reinforcement learning with multiple objectives and tradeoffs includes receiving a dataset comprising state, action, and reward information for objectives in a multiple objective environment. Tradeoff information indicating that a first vector comprising first values of the objectives in the multiple objective environment is preferred to a second vector comprising second values of the objectives in the multiple objective environment is received. A set of possibly optimal policies for the multiple objective environment is produced based on the dataset and the tradeoff information, where the set of possibly optimal policies indicates actions for an intelligent agent operating in the multiple objective environment to take.

Abstract: Aspects of the present disclosure allow for improving E2E mesh throughput by applying transmission (TX) biasing on the Wi-Fi mesh backhaul. Aspects of the disclosure are directed to solutions for reducing traffic load in Wi-Fi mesh networks by applying TX biasing on the Wi-Fi mesh backhaul. Certain aspects are directed to selectively transmitting or preventing transmission of data over the first backhaul link to the first MLD based at least in part on a fronthaul airtime utilization, a first backhaul airtime utilization, or a second backhaul airtime utilization. Doing so allows a root access point or a network controller to apply TX biasing between multi-link operation links towards each repeater so that traffic load on a backhaul-link would not overly occupy the front-haul link because of common channel use by selectively transmitting or preventing transmission of data on the backhaul links.

Abstract: The present invention relates to nimbolide analogs useful as anti-cancer agents and preparation thereof. Particularly the present invention relates to nimbolide analogs of general formula I. wherein, ring M is any ring selected from the group consisting of substituted or unsubstituted aryl, heteroaryl, cycloalkyl and heterocyclic; A and B are selected from the group consisting of C, O, N, S and H; R1, R2, R3, R4, R5 and R6 are selected from the group consisting of C1-C6 alkyl, aryl, heteroaryl, C1-C7 cycloalkyl, heteroalkyl, hydrogen, hydroxy, alkoxy, nitro, halogen, amino, alkylamino, aryl amino and cyano; wherein each of these groups may be further substituted with one or more substituents selected from the group consisting of hydrogen, hydroxy, halogen, cyano, alkyl amino, aryl amino, alkoxy, amino, nitro, aldehyde, carboxylic acid and ester.

Abstract: Methods to compute glycemia tests and applications thereof are described. Additional methods to compute risk of atherosclerotic cardiovascular disease and applications thereof are described. Generally, systems utilize analyte measurements to determine a glycemic status or cardiovascular disease risk, which can be used as a basis to treat individuals.

Abstract: An input model can be received, along with a set of requirements. The set of requirements may describe an output model to be trained. The output model can then be trained. The training of the output model can be based on the input model and based further on at least one intermediate model.

Abstract: A check valve assembly for a supply pipe. The check valve assembly includes a hinge pin, a first flapper, and a second flapper. The first flapper is pivotally coupled to the second flapper with the hinge pin. The check valve assembly also includes a stopper located between the first flapper and the second flapper. The stopper is configured to limit movement of the first flapper and the second flapper. The check valve assembly further includes a plate assembly located downstream of the stopper. The plate assembly is configured to break vortices formed in a fluid flow across the first flapper and the second flapper.

Abstract: According to one embodiment, a method, computer system, and computer program product for reinforcement learning is provided. The present invention may include training, using an offline dataset, a plurality of diverse reward models, and creating a policy based on an output of the reward models and a robustness operator of the reward models.

Abstract: An output layer is removed from a pre-trained neural network model and a neural capacitance probe unit with multiple layers is incorporated on top of one or more bottom layers of the pre-trained neural network model. The neural capacitance probe unit is randomly initialized and a modified neural network model is trained by fine-tuning the one or more bottom layers on a target dataset for a maximum number of epochs, the modified neural network model comprising the neural capacitance probe unit incorporated with multiple layers on top of the one or more bottom layers of the pre-trained neural network model. An adjacency matrix is obtained from the initialized neural capacitance probe unit and a neural capacitance metric is computed using the adjacency matrix. An active model is selected using the neural capacitance metric and a machine learning system is configured using the active model.

Abstract: A method, a neural network, and a computer program product are provided that provide training of neural networks with continued fractions architectures. The method includes receiving, as input to a neural network, input data and training the input data through a plurality of continued fractions layers of the neural network to generate output data. The input data is provided to each of the continued fractions layers as well as output data from a previous layer. The method further includes outputting, from the neural network, the output data. Each continued fractions layer of the continued fractions layers is configured to calculate one or more linear functions of its respective input and to generate an output that is used as the input for a subsequent continued fractions layer, each continued fractions layer configured to generate an output that is used as the input for a subsequent layer.

Abstract: The present invention concerns a new method and system for representation, measurement, and analysis of visual-cognitive function, more specifically, visual processing, motor, and neuropsychological integration; as well as non-verbal and non-auditory intelligence in humans. This invention seeks to provide a comprehensive and cost-effective process to screen users for the said functions and offer valuable insight into their thought process to identify and design remedies for visual-cognitive and neurodevelopmental deficiencies, especially in children. This new method offers a technologically advanced alternative to commonly used VMI assessments by enabling the collection of a new, more comprehensive set of data points using a digital medium.

Abstract: A method for training a machine learning model includes receiving a randomly-initialized first version of a machine learning model, conducting first training on the machine learning model first version using first training data, the first training data comprising a first type of information respective of a plurality of documents, adding a layer to the machine learning model first version after conducting the first training to create a machine learning model second version, and conducting second training on the machine learning model second version using second training data, the second training data comprising a second type of information respective of the plurality of documents.

Abstract: Network request data is collected over a time window. The network request data is filtered to generate bypass network traffic records. Network performance categories are generated from the bypass network traffic records. Sufficient statistics of network optimization parameters are calculated for the network performance categories. The sufficient statistics of the network optimization parameters are used to generate network optimization parameters to determine data download performances of web applications.

Abstract: Systems, computer-implemented methods, and computer program products to facilitate inter-operator backpropagation in AutoML frameworks are provided. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components comprise a selection component that selects a subset of deep learning and non-deep learning operators. The computer executable components further comprise a training component which trains the subset of deep learning and non-deep learning operators, wherein deep learning operators in the subset of deep learning and non-deep learning operators are trained using backpropagation across at least two deep learning operators of the subset of deep learning and non-deep learning operators.

Abstract: Bypass network traffic records are generated for a web application. Sufficient statistics of network optimization parameters are calculated for network performance categories. The bypass network traffic records are partitioned for the network performance categories into network traffic buckets. Sufficient statistics and the network traffic buckets are used to generate network quality mappings. The network quality mappings are used as training instances to train a machine learner for generating network optimization policies to be implemented by user devices.

Abstract: Sensor part for installation in medium-voltage cable compartments, which sensor part comprises a voltage divider based on the capacitive divider principle, which voltage divider comprises: —a first capacitor, comprising an elongate primary conductor wrapped in a dielectric material and an elongate conducting shield arranged around the dielectric material, which first capacitor has a first capacitance rating; —a second capacitor, having a second capacitance rating, which second capacitor further comprises a first lead conductively connected with the conducting shield of the first capacitor and a second lead conductively connected to a common reference, such as earth; —a voltage output line, conductively connected with the conducting shield of the first capacitor; wherein the second capacitance rating is larger than the first capacitance rating, so that when during use the primary conductor is conductively connected with a live circuit carrying an alternating current, a measurement of a voltage between the comm

Abstract: A check valve assembly for a supply pipe. The check valve assembly includes a hinge pin, a first flapper, and a second flapper. The first flapper is pivotally coupled to the second flapper with the hinge pin. The check valve assembly also includes a stopper located between the first flapper and the second flapper. The stopper is configured to limit movement of the first flapper and the second flapper. The check valve assembly further includes a plate assembly located downstream of the stopper. The plate assembly is configured to break vortices formed in a fluid flow across the first flapper and the second flapper.

Abstract: A method, system, and computer program product, including generating a contrastive explanation for a decision of a classifier trained on structured data, highlighting an important feature that justifies the decision, and determining a minimal set of new values for features that alter the decision.

Abstract: A system for managing dataset quality in a computing environment is disclosed. The plurality of subsystems includes a data receiving subsystem, configured to receive a dataset. The plurality of subsystems includes a data analysis subsystem configured to compute data metrics for each field of the received dataset based on type of the dataset. The data analysis subsystem assigns a domain label for each of the received dataset based on the computed data metrics. Further, the data analysis subsystem compares the computed data metrics and the assigned domain label for each field of the received dataset with stored values of data metrics and domain label for pre-processed non-anomalous datasets to determine a one or more deviations. The data analysis subsystem is configured to determine a statistical difference between the values of received dataset and non-anomalous historical dataset.

Abstract: Network traffic data associated with data requests to computer applications based on static policies is collected. An optimization order is established among network parameters. A first network parameter of a higher rank in the optimization order is estimated based on the collected network traffic data before one or more other network parameters of lower ranks are estimated. Optimal values for the other network parameters are estimated based at least in part on the estimated first optimal value for the first network parameter. The estimated first optimal value of the first network parameter and the estimated optimal values for the other network parameters are propagated to be used by user devices to make new data requests to the computer applications.

Abstract: Storage devices are capable of utilizing receiver devices with native devices configured to support lower voltage supplies for higher read performances. The receiver device may include a current source circuit, first and second stage circuits, and a duty cycle balancer circuit. The first stage circuit may utilize first and second native devices with a threshold voltage (VTH) that enables proper lower voltage operations in saturation at high speeds. The current source stage circuit may utilize a third native device to track a transconductance and provide a reference current that becomes proportional to VTH to maintain tighter gain across process, variation, and temperature (PVT). The second stage circuit may utilize a current folding stage to provide a high gain for faster conversion of intermediate signals. The duty cycle balancer may utilize a fourth native device to balance a rise and fall delay skew across the PVT to maintain tighter duty cycle.