Abstract: A system to characterize a film layer within a measurement box is disclosed. The system obtains a first mixing fraction corresponding to a first X-ray beam, the mixing fraction represents a fraction of the first X-ray beam inside a measurement box of a wafer sample, the measurement box represents a bore structure disposed over a substrate and having a film layer disposed inside the bore structure. The system obtains a contribution value for the measurement box corresponding to the first X-ray beam, the contribution value representing a species signal outside the measurement box that contributes to a same species signal inside the measurement box. The system obtains a first measurement detection signal corresponding to a measurement of the measurement box using the first X-ray beam. The system determines a measurement value of the film layer based on the first measurement detection signal, the contribution value, and the first mixing fraction.

Abstract: A method of detecting a defect in a connecting member of a radio unit in a radio site includes applying an artificial radio traffic load to a first radio unit and at least a second radio unit, such that the radio traffic load experienced by the first and the second radio unit is at a same level, measuring power supplied to the first radio unit via a first connecting member and power supplied to the second radio unit via a second connecting member at an end of each connecting member terminating at a device configured to supply power to the radio units, and determining from the measured power and an expected nominal power loss of the first and the second connecting member if there is power loss in at least one of the first and the second connecting member indicating a defect.

Abstract: The present disclosure relates to circuitry for providing an output voltage. The circuitry comprises: voltage generator circuitry configured to provide an output voltage to an output node of the circuitry; current limiter circuitry operable to perform current limiting so as to limit a current supplied at the output node of the circuitry; detection circuitry configured to output a detection signal when a load voltage across a load coupled to the output node of the circuitry reaches a target voltage; and delay circuitry configured to receive the detection signal and to output a control signal to deactivate current limiting by the current limiter circuitry after a predetermined delay period after receiving the detection signal.

Abstract: Example aspects of the present disclosure are directed to systems and methods that learn a compressed representation of a machine-learned model (e.g., neural network) via representation of the model parameters within a reparameterization space during training of the model. In particular, the present disclosure describes an end-to-end model weight compression approach that employs a latent-variable data compression method. The model parameters (e.g., weights and biases) are represented in a “latent” or “reparameterization” space, amounting to a reparameterization. In some implementations, this space can be equipped with a learned probability model, which is used first to impose an entropy penalty on the parameter representation during training, and second to compress the representation using arithmetic coding after training. The proposed approach can thus maximize accuracy and model compressibility jointly, in an end-to-end fashion, with the rate-error trade-off specified by a hyperparameter.

Abstract: Provided are system, method, and device for managing capacity thresholds in a network. According to embodiments, the system may include: a memory storage storing computer-executable instructions; and at least one processor communicatively coupled to the memory storage, wherein the at least one processor may be configured to execute the instructions to: obtain information associated with load of a network; and manage, based on the obtained information, user plane of the network.

Abstract: A method of detecting a defect in a connecting member of a radio unit in a radio site includes applying an artificial radio traffic load to a first radio unit and at least a second radio unit, such that the radio traffic load experienced by the first and the second radio unit is at a same level, measuring power supplied to the first radio unit via a first connecting member and power supplied to the second radio unit via a second connecting member at an end of each connecting member terminating at a device configured to supply power to the radio units, and determining from the measured power and an expected nominal power loss of the first and the second connecting member if there is power loss in at least one of the first and the second connecting member indicating a defect.

Abstract: A method and system for generating and optimizing test cases for an engineering program based on a constraint satisfaction problem is provided. In one embodiment, the method includes generating a plurality of tripartite graphs for the engineering program. Each of the generated plurality of tripartite graphs include a constraint satisfaction problem associated with a specific code statement of the plurality of code statements. Furthermore, the method includes generating a plurality of test cases for the engineering program based on the plurality of tripartite graphs such that the generated plurality of test cases are limited by the generated test case constraints. Moreover, the method includes optimizing the generated plurality of test cases based on an analysis of the engineering program.

Abstract: A method performed by a central server node in a distributed machine learning environment is provided. The method includes: managing distributed machine learning for a plurality of local client nodes, such that a first set of the plurality of local client nodes are assigned to assist training of a first central model and a second set of the plurality of local client nodes are assigned to assist training of a second central model; obtaining information regarding network conditions for the plurality of local client nodes; clustering the plurality of local client nodes into one or more clusters based at least in part on the information regarding network conditions; re-assigning a local client node in the first set to the second set based on the clustering; and sending to the local client node a message including model weights for the second central model.

Abstract: Example aspects include techniques for implementing a rapid incident management system. These techniques include determining coverage information indicating a relationship between an incident and a plurality of incident assignment groups, and determining a plurality of incident features based on the coverage information and an incident description corresponding to the incident. In addition, the techniques include generating assignment likelihood information for each of the plurality of incident assignment groups based on the plurality of incident features, assigning the incident to an incident assignment group having a highest assignment likelihood value within the assignment likelihood information, and transmitting a notification to a device associated with the incident assignment group.

Abstract: A system to characterize a film layer within a measurement box is disclosed. The system obtains a first mixing fraction corresponding to a first X-ray beam, the mixing fraction represents a fraction of the first X-ray beam inside a measurement box of a wafer sample, the measurement box represents a bore structure disposed over a substrate and having a film layer disposed inside the bore structure. The system obtains a contribution value for the measurement box corresponding to the first X-ray beam, the contribution value representing a species signal outside the measurement box that contributes to a same species signal inside the measurement box. The system obtains a first measurement detection signal corresponding to a measurement of the measurement box using the first X-ray beam. The system determines a measurement value of the film layer based on the first measurement detection signal, the contribution value, and the first mixing fraction.

Abstract: Methods and apparatuses are described for provisioning and managing data orchestration platforms in a cloud computing environment. A server provisions in a first region a first data orchestration platform comprising (i) a first data transformation instance, (ii) first endpoints, and (iii) a first data integration instance. The server provisions in a second region a second data orchestration platform comprising (i) a second data transformation instance, (ii) second endpoints, and (iii) a second data integration instance. The server integrates the first data integration instance and the second data integration instance with an identity authentication service. The server monitors operational status of the first orchestration platform and the second orchestration platform using a monitoring service. The server refreshes virtual computing resources in each of the first orchestration platform and the second orchestration platform using a rehydration service.

Abstract: There is provided a method for consolidating explanations associated with actions proposed based on a current state of a system and an intent. The method includes acquiring first and second explanations, the first and second explanations being associated with a proposed action or with different actions, wherein each of the first and second explanations includes one or more constraints, combining constraints from the first and second explanations to form a set of constraints D, generating a planning problem P=<K, A, I, G, Cost>, wherein K consists of a set of predicates F and the set of constraints D, wherein A represents a set of possible actions, I represents an initial state of the system, G represents a goal state of the system, and Cost represents cost values associated with each constraint, and determining a solution for the planning problem.

Abstract: A storage device ensures erasure of a first memory device even when the storage device is in an unrecoverable state. The storage device includes the first memory device and a controller. The controller executes operations on the first memory device in response to instructions received from a host coupled to the storage device. The controller may detect when an unrecoverable error occurs when executing instructions and enter an exception handling mode. The controller may also determine if the storage device enters an unrecoverable state and may move into a restricted firmware mode when the storage device enters the unrecoverable state. When in the restricted firmware mode, the controller may load firmware into a second memory device and, upon receiving a sanitize instruction from the host, the controller may execute the firmware in the second memory device to delete data in the first memory device.

Abstract: A computer implemented method performed by a node in a communications network for matching parameters in a target network configuration with corresponding key performance indicators, KPIs, in the communications network. The method comprises obtaining (202) a first set of connections between a first subset of the parameters and a first subset of the KPIs. The method further comprises representing (204) the parameters as a first knowledge graph, representing (206) the KPIs as a second knowledge graph, and using (208) a graph-based machine learning process on the first knowledge graph and the second knowledge graph to match a second parameter to a second KPI.

Abstract: A computing system is configured to receive raw transaction data from a database. The computing system performs a multipattern substring matching operation on the raw transaction data using an expert system model. The computing system identifies one or more predefined keywords within one or more of description and memo data fields for each transaction data piece of a set of transaction data pieces. The computing system filters one or more predefined rules based on the identified one or more predefined keywords and assign a category label to each transaction data piece. The assigned category label is based on a highest priority rule determined to be true for the respective transaction data piece.

Abstract: A computing system receives rules and transaction data from a database. The system creates a potential rule list and stores the rules in the list on the database. The system creates an ordered rule list, a rule-to-transaction lookup table, and a transaction-to-rule lookup table. The system applies each rule to each transaction and identifies each transaction for which each rule is true. The system adds each rule and the identified transactions to the lookup tables and generates a priority-ordered list of the rules iteratively until all rules have been removed from the potential rule list. In each iteration, the system calculates an accuracy of each rule based on all transactions for which the rule is true, appends the highest accuracy rules to the ordered rule list, removes the rules from the potential rule list, and removes the transactions from all entries in the rule-to-transaction lookup table.

Abstract: A computing system is configured to receive a plurality of predefined rules from a database. The rules include a first set of predefined rules that includes a hardcoded priority value for each respective predefined rule and a second set of predefined rules that do not have a hardcoded priority value. Furthermore, each rule is associated with a keyword. The computing system determines, for the first set of predefined rules, that each respective predefined rule includes the hardcoded priority value and orders the first set of predefined rules in order of priority based on the hardcoded priority values. The computing system performs a super rule/subrule prioritization operation on the second set of predefined rules, which includes prioritizing one or more super rules over its associated one or more subrules. The computing system then performs an accuracy-based prioritization operation on the second set of predefined rules after the super rule/subrule prioritization operation.

Abstract: Methods and apparatuses are described for provisioning and managing data orchestration platforms in a cloud computing environment. A server provisions in a first region a first data orchestration platform comprising (i) a first data transformation instance, (ii) first endpoints, and (iii) a first data integration instance. The server provisions in a second region a second data orchestration platform comprising (i) a second data transformation instance, (ii) second endpoints, and (iii) a second data integration instance. The server integrates the first data integration instance and the second data integration instance with an identity authentication service. The server monitors operational status of the first orchestration platform and the second orchestration platform using a monitoring service. The server refreshes virtual computing resources in each of the first orchestration platform and the second orchestration platform using a rehydration service.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.

Abstract: Example aspects of the present disclosure are directed to systems and methods that learn a compressed representation of a machine-learned model (e.g., neural network) via representation of the model parameters within a reparameterization space during training of the model. In particular, the present disclosure describes an end-to-end model weight compression approach that employs a latent-variable data compression method. The model parameters (e.g., weights and biases) are represented in a “latent” or “reparameterization” space, amounting to a reparameterization. In some implementations, this space can be equipped with a learned probability model, which is used first to impose an entropy penalty on the parameter representation during training, and second to compress the representation using arithmetic coding after training. The proposed approach can thus maximize accuracy and model compressibility jointly, in an end-to-end fashion, with the rate-error trade-off specified by a hyperparameter.