Abstract: Systems and method for machine-learning assisted road sign content prediction and machine learning training is disclosed. A sign detector model processes images or video with road signs. A visual attribute prediction model extracts visual attributes of the sign in the image. The visual attribute prediction model can communicate with a knowledge graph reasoner to validate the visual attribute prediction model by applying various rules to the output of the visual attribute prediction model. A plurality of potential sign candidates are retrieved that match the visual attributes of the image subject to the visual attribute prediction model, and the rules help to reduce the list of potential sign candidates and improve accuracy of the model.

Abstract: A multicore computing device includes a memory and a processor coupled to the memory. The processor includes plural cores and a multiple input multiple output (MIMO) block coupled to the cores. The MIMO block receives a halt request from a first core of the cores, transmits a core-halt request to one or more other cores other than the first core, to halt execution of the one or more other cores, and permits the first core to lock with a shared resource.

Abstract: An example apparatus includes: a controller configured to: generate a symbol pattern as a result of placing symbols based on epipolar lines; instruct an SLM to project the symbol pattern; obtain an image of a reflection of the symbol pattern; determine a first location of a symbol in the image; determine a second location of the symbol in the image; and determine a depth of the symbol as based on the first location, the second location, and an essential matrix.

Abstract: Systems and methods for constructing and managing a unique road sign knowledge graph across various countries and regions is disclosed. The system utilizes machine learning methods to assist humans when comparing a new sign template with a plurality of stored sign templates to reduce or eliminate redundancy in the road sign knowledge graph. Such a machine learning method and system is also used in providing visual attributes of road signs such as sign shapes, colors, symbols, and the like. If the machine learning determines that the input road sign template is not found in the road sign knowledge graph, the input sign template can be added to the road sign knowledge graph. The road sign knowledge graph can be maintained to add signs templates that are not already in the knowledge graph but are found in real-world by integrating human annotator's feedback during ground truth generation for machine learning.

Abstract: A device includes a transmitter to transmit serialized data within a differential direct-current (DC) signal over a differential output line, a multiplexer circuit coupled to the transmitter, and a calibration circuit coupled between the differential output line, a multi-phase clock, and the multiplexer circuit. The multiplexer circuit is to select the serialized data from ones of multiple input lines according to a multi-phase clock and pass the selected serialized data to the transmitter. The serialized data includes a calibration bit pattern. The calibration circuit is to capture and digitize the differential DC signal into a digital stream, measure an error value from the digital stream that is associated with distortion based on the calibration bit pattern, convert the error value into a gradient value, and correct one or more phases of the multi-phase clock to compensate for the distortion based on the gradient value.

Abstract: Various embodiments of the present invention provide methods, apparatuses, systems, computing devices, and/or the like that are configured to effectively and efficiently generate one or more abstractive summaries of one or more multi-section documents. For example, certain embodiments of the present invention provide methods, apparatuses, systems, computing devices, and/or the like that are configured to generate an abstractive summary of a multi-section document comprising one or more sections, by generating one or more section summaries, section input batches for each selected section, model outputs created by one or more text summarization machine learning models through the performance of a batch processing operation sequence, abstractive summaries, and then storing the abstractive summaries.

Abstract: The present disclosure provides systems and methods for processing channel structures of substrates that include positioning the substrate in a first processing chamber having a first processing volume being in fluid communication with a plasma source. The substrate can include a channel structure with high aspect ratio features having aspect ratios greater than about 20:1. The method can also include forming an oxide cap layer over a silicon-containing layer of the channel structure and exposing the oxide cap layer to a hydrogen-or-deuterium radical to nucleate the silicon-containing layer of the channel structures of the substrate. Forming the oxide cap layer and exposing the channel structure with the hydrogen radical occurs in the first processing chamber to form a nucleated substrate. The method can also include positioning the nucleated substrate in a second processing chamber with a second processing volume and heating the nucleated substrate in the second processing chamber.

Abstract: A method and system for controlling implementation of dynamic content modification. The disclosure provides for using at least one steganographically-encoded timestamp in a media stream transmitted to a media client as a basis to determine a transmission delay for media-stream transmission to the media client, and for providing the determined transmission delay as a basis to facilitate control over whether to have the media client implement dynamic content modification. In addition, the disclosure provides for receiving respectively from each of various media clients a report indicating transmission delay determined for the media client based on such steganographically-encoded timestamp data, and using the transmission delays for the media clients to establish a dynamic-content-modification footprint that could be used to control whether, where, and to what extent dynamic content modification will be applied.

Abstract: Embodiments of the present disclosure provide an apparatus including a memory array including a plurality of sub-arrays. A plurality of temporary storage units (TSUs) is coupled to the plurality of sub-arrays. Each TSU indicates whether the respective sub-array is undergoing one of a read operation and a write operation. A control circuit is coupled to each of the plurality of sub-arrays through a data bus. The control circuit transmits a read pulse or a write pulse as a first pulse with a delay in response to the sub-array undergoing the read operation or the write operation and transmits, instantaneously, the first pulse to one of the plurality of sub-arrays in response to the sub-array not undergoing the read operation or the write operation.

Abstract: Certain aspects of the present disclosure provide techniques for intelligent grouping of travel data for review through a user interface. In one example, a method for providing grouped travel data to a user interface of an application includes receiving travel data from an application running on a remote device; generating one or more travel data-based features from the travel data thereby creating featurized travel data; applying a pattern mining technique to the featurized travel data to detect a plurality of patterns in the featurized travel data; for each trip record in the featurized travel data: determining a plurality of trip record groups in which the trip record falls based on the plurality of patterns; and adding the trip record to a trip record group of the plurality of trip record groups according to a prioritization scheme; and transmitting the trip record group to the application running on the remote device.

Abstract: Embodiments provide methods and systems for merchant data cleansing in payment network. Method performed by server system includes accessing electronic payment transaction records from transaction database. Each electronic payment transaction record includes merchant data fields. Method includes determining set of electronic payment transaction records with ambiguous merchant data fields having matching probability scores less than predetermined threshold value computed by probabilistic matching model and identifying at least one issue for non-matching of each of set of electronic payment transaction records. Method includes determining data model based on at least one issue of each of set of electronic payment transaction records. Data model is one of: phone-to-city model, payment aggregator model, and merchant name normalization model.

Abstract: A system may include a historical managed software system data store that contains electronic records associated with controllers and deployed workloads (each electronic record may include time series data representing performance metrics). An entropy calculation system, coupled to the historical managed software system data store, may calculate at least one historical entropy value based on information in the historical managed software system data store. A detection engine, coupled to a monitored system currently executing a deployed workload in the cloud computing environment, may collect time series data representing current performance metrics associated with the monitored system. The detection engine may then calculate a current monitored entropy value (based on the collected time series data representing current performance metrics) and (iii) compare the current monitored entropy value with a threshold value (based on the historical entropy value).

Abstract: According to an aspect of the present disclosure, a computer-implemented includes creating a plurality of basic skill functions for a controllable physical device of an autonomous system. Each basic skill function includes a functional description for using the controllable physical device to interact with a physical environment to perform a defined objective. The method further includes selecting one or more basic skill functions to configure the controllable physical device to perform a defined task. The method also includes determining a decorator skill function specifying at least one constraint. The decorator skill function is configured to impose, at run-time, the at least one constraint, on the one or more basic skill functions. The method further includes generating executable code by applying the decorator skill function to the one or more basic skill functions, and actuating the controllable physical device using the executable code.

Abstract: In some embodiments, a camera actuator includes an actuator base, an autofocus voice coil motor, and an optical image stabilization voice coil motor. In some embodiments, the autofocus voice coil motor includes a lens carrier mounting attachment moveably mounted to the actuator base, a plurality of shared magnets mounted to the base, and an autofocus coil fixedly mounted to the lens carrier mounting attachment for producing forces for moving a lens carrier in a direction of an optical axis of one or more lenses of the lens carrier. In some embodiments, the optical image stabilization voice coil motor includes an image sensor carrier moveably mounted to the actuator base, and optical image stabilization coils moveably mounted to the image sensor carrier within the magnetic fields of the shared magnets, for producing forces for moving the image sensor carrier in a plurality of directions orthogonal to the optical axis.

Abstract: An apparatus, related devices and methods, having a memory element operable to store instructions; and a processor operable to execute the instructions, such that the apparatus is configured to identify, on an electronic device, a phone number of an incoming caller device; request, via an out-of-band control channel, a digital certificate for the phone number from the incoming caller device; receive, via the out-of-band control channel, the digital certificate for the phone number from the incoming caller device; determine whether the digital certificate for the phone number is authentic; and indicate, on the electronic device, based on a determination that the digital certificate for the phone number is authentic or not authentic, whether the phone number is authentic or not authentic.

Abstract: A system may include a historical time series data store that contains electronic records associated with Software-as-a-Service (“SaaS”) applications in a multi-tenant cloud computing environment (including time series data representing execution of the SaaS applications). A monitoring platform may retrieve time series data for the monitored SaaS application from the historical time series data store and create tenant vector representations associated with the retrieved time series data. The monitoring platform may then provide the retrieved time series data and tenant vector representations together as final input vectors to an autoencoder to produce an output including at least one of a tenant-specific loss reconstruction and tenant-specific thresholds for the monitored SaaS application. The monitoring platform may utilize the output of the autoencoder to automatically detect an anomaly associated with the monitored SaaS application.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to automatically answer a call. In some implementations, a method includes receiving a call from a caller device at a client device. The method further includes determining, based on an identifier associated with the call, whether the call matches auto answer criteria, and yin response to determining that the call matches the auto answer criteria, answering the call without user input and without alerting a user of the client device. The method further includes generating a call embedding for the call based on received audio of the call, comparing the call embedding with spam embeddings to determine whether the call is a spam call, and in response to determining that the call is a spam call, terminating the call.

Abstract: Examples described herein relate to a decompression engine that can request compressed data to be transferred over a memory bus. In some cases, the memory bus is a width that requires multiple data transfers to transfer the requested data. In a case that requested data is to be presented in-order to the decompression engine, a re-order buffer can be used to store entries of data. When a head-of-line entry is received, the entry can be provided to the decompression engine. When a last entry in a group of one or more entries is received, all entries in the group are presented in-order to the decompression engine. In some examples, a decompression engine can borrow memory resources allocated for use by another memory client to expand a size of re-order buffer available for use. For example, a memory client with excess capacity and a slowest growth rate can be chosen to borrow memory resources from.

Abstract: Some embodiments address unique challenges of provisioning RPA software to airgapped hosts, and in particular, provisioning RPA machine learning components and training corpora of substantial size, and provisioning to multiple airgapped hosts having distinct hardware and/or software specifications. To reduce costs associated with data traffic and manipulation, some embodiments bundle together multiple RPA components and/or training corpora into an aggregate package comprising a deduplicated collection of software libraries. Individual RPA components are then automatically reconstructed from the aggregate package and distributed to airgapped hosts.

Abstract: Multiple windows can be simultaneously shared via a collaboration application. A multiple window sharing controller can be employed on an end user device to enable the user to create an aggregated window that includes windows of multiple applications running on the end user device. The multiple window sharing controller can cause this aggregated window to appear as an active window on the end user device. Therefore, when a collaboration application presents windows that the user can select to be shared during a meeting, the aggregated window will be included.