Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.

Abstract: A computer implemented method detects suspicious domains. A computer system determines a homographic similarity between a target domain and a known domain. The compute system compares first registration information for the target domain and second registration information for the known domain to form a registration comparison in response the homographic similarity being sufficiently similar to be potentially suspicious. The computer system compares a set of first landing page images for the target domain and a set of second landing page images for the known domain to form an image comparison in response to a match between the first ownership information for the target domain and the second ownership information for the known domain being absent. The computer system determines a threat level for the target domain based on the image comparison.

Abstract: A method, computer system, and a computer program product for semantic matching is provided. The present invention may include pre-processing and normalizing a job title. The present invention may include deconstructing the job title based on at least one semantic element. The present invention may include training a machine learning model. The present invention may include creating a contextual word representation of the job title using the at least one semantic element of the job title. The present invention may include computing a similarity score for each of the at least one semantic element of the job title. The present invention may lastly include applying a weight to the computed similarity score before making a final match assessment.

Abstract: A dental cleaning appliance includes a handle and a fluid delivery system. The fluid delivery system includes a nozzle for delivering a burst of working fluid to the teeth of a user, and a moveable fluid conduit which is moveable about an axis relative to the handle. The nozzle is moveable with the fluid conduit, which is biased for movement about the axis in a direction which urges the nozzle against a user's teeth during use of the appliance.

Abstract: A method for crowd-sourced compensation ranging is provided, the method including, at least, inclusion, analysis and application of a wide variety of available compensable factors, including one or more crowd-sourced compensable factors.

Abstract: The techniques described herein relate to methods, apparatus, and computer readable media for editing a graphical program using a graphical programming interface. Editing the graphical program may include displaying, via the graphical programming interface, a plurality of existing graphical components that provide functionality for at least one computer program thread; receiving data indicating a selection of a new graphical component for inserting into the plurality of existing graphical components; determining, based on an associated graphical component of the plurality of existing graphical components, a set of one or more placement locations for inserting the new graphical component; and displaying, on the graphical programming interface, the set of one or more placement locations.

Abstract: A method, computer system, and a computer program product for deploying a plurality of microservices across a service infrastructure having a plurality of resources is provided. The present invention may include determining at least one dependency of the plurality of microservices. The present invention may include for each resource of the plurality of resources, determining an outage distribution descriptive of an availability of the resource with respect to time. The present invention may include based on the outage distribution associated with each resource and the at least one dependency of the plurality of microservices, determining a deployment configuration of the plurality of microservices across the resources of the service infrastructure.

Abstract: A dental cleaning appliance includes a handle and a fluid delivery system for delivering a burst of working fluid to the teeth of a user. Part of the fluid delivery system is moveable relative to the handle as the appliance is moved along the teeth of the user. A sensor provides an output which varies with movement of that part of the fluid delivery system relative to the handle. A control circuit actuates the delivery of working fluid to the teeth of the user depending on the output from the sensor.

Abstract: A fluid delivery system for a dental cleaning appliance includes a nozzle for delivering a burst of working fluid to the teeth of a user, and a fluid conduit for conveying working fluid to the nozzle. A body of the nozzle defines a fluid chamber and a channel for conveying working fluid from the fluid chamber to a fluid outlet from the nozzle. The fluid chamber has a tangential inlet for receiving working fluid from the fluid conduit.

Abstract: A method, computer system, and a computer program product for semantic matching is provided. The present invention may include pre-processing and normalizing a job title. The present invention may include deconstructing the job title based on at least one semantic element. The present invention may include training a machine learning model. The present invention may include creating a contextual word representation of the job title using the at least one semantic element of the job title. The present invention may include computing a similarity score for each of the at least one semantic element of the job title. The present invention may lastly include applying a weight to the computed similarity score before making a final match assessment.

Abstract: A computer implemented method, apparatus, and computer program product for a sound system. Speech recognition is performed on input audio data comprising speech input to a sound system. Speech recognition is additionally performed on at least one instance of output audio data comprising speech reproduced by one or more audio speakers of the sound system. A difference between a result of speech recognition performed on the input audio data and a result of speech recognition performed on an instance of corresponding output audio data is determined. The quality of the reproduced speech is determined as unsatisfactory when the difference is greater than or equal to a threshold. A corrective action may be performed, to improve the quality of the speech reproduced by the sound system, if it is determined that the speech quality of the reproduced sound is unsatisfactory.

Abstract: A fluid delivery system of a dental cleaning appliance includes a fluid inlet, a pump for drawing a working fluid through the fluid inlet, a hydraulic accumulator for receiving working fluid from the pump, a nozzle having a fluid outlet, and a valve located between the accumulator and the nozzle. The valve has an open position for enabling the accumulator to deliver a burst of working fluid to the nozzle, and a closed position for enabling the accumulator to be replenished under the action of the pump. A control circuit actuates the pump and controls the position of the valve.

Abstract: An approach is provided in which the approach captures usage data corresponding to multiple users accessing a codebase that includes multiple code lines. The approach uses the captured usage data to compute a code line usage weighting for at least one of the code lines. The approach also computes a code line test coverage score for at least one code line based on at least one current software test program that tests the codebase. The approach compares the code line usage weighting against the code line test coverage score and flags the code line based on the comparison.

Abstract: A computer implemented method, apparatus, and computer program product for a sound system. Speech recognition is performed on input audio data comprising speech input to a sound system. Speech recognition is additionally performed on at least one instance of output audio data comprising speech reproduced by one or more audio speakers of the sound system. A difference between a result of speech recognition performed on the input audio data and a result of speech recognition performed on an instance of corresponding output audio data is determined. The quality of the reproduced speech is determined as unsatisfactory when the difference is greater than or equal to a threshold. A corrective action may be performed, to improve the quality of the speech reproduced by the sound system, if it is determined that the speech quality of the reproduced sound is unsatisfactory.

Abstract: A computer-implemented method for configuring deployment of a distributed system across a plurality of machines of a network. The method may include obtaining network information describing network communication characteristics between a plurality of machines of a network. The method may also include obtaining inter-container communication information describing at least one characteristic of communication between pairs of machines of the plurality of machines for a predetermined time period. The method may also include determining a cost function, the cost function mapping a potential container deployment configuration to an expected communication time, based on the network information and the inter-container communication. The method may also include processing the cost function with an optimization algorithm. The method may also include, in response to the processing, identifying a container deployment configuration having an associated cost that meets a cost requirement.

Abstract: A method, computer system, and a computer program product for deploying a plurality of microservices across a service infrastructure having a plurality of resources is provided. The present invention may include determining at least one dependency of the plurality of microservices. The present invention may include for each resource of the plurality of resources, determining an outage distribution descriptive of an availability of the resource with respect to time. The present invention may include based on the outage distribution associated with each resource and the at least one dependency of the plurality of microservices, determining a deployment configuration of the plurality of microservices across the resources of the service infrastructure.

Abstract: An approach is provided in which the approach captures usage data corresponding to multiple users accessing a codebase that includes multiple code lines. The approach uses the captured usage data to compute a code line usage weighting for at least one of the code lines. The approach also computes a code line test coverage score for at least one code line based on at least one current software test program that tests the codebase. The approach compares the code line usage weighting against the code line test coverage score and flags the code line based on the comparison.

Abstract: A computer-implemented method for configuring deployment of a distributed system across a plurality of machines of a network. The method may include obtaining network information describing network communication characteristics between a plurality of machines of a network. The method may also include obtaining inter-container communication information describing at least one characteristic of communication between pairs of machines of the plurality of machines for a predetermined time period. The method may also include determining a cost function, the cost function mapping a potential container deployment configuration to an expected communication time, based on the network information and the inter-container communication. The method may also include processing the cost function with an optimization algorithm. The method may also include, in response to the processing, identifying a container deployment configuration having an associated cost that meets a cost requirement.