Abstract: Methods, apparatus, and processor-readable storage media for localized anomaly detection in digital documents are provided herein. An example computer-implemented method includes identifying at least one image in a digital document; processing the identified at least one image using at least an image compression algorithm; applying a first machine learning model to the at least one processed image, wherein the first machine learning model is trained to detect whether the at least one image comprises one or more modifications; in response to detecting that the at least one image comprises at least one modification, applying a second machine learning model to identify a location in the at least one image corresponding to the at least one modification; and generating an indication that identifies the location of the at least one modification in the at least one image.

Abstract: A method for automatically improving the legibility of text within graphic designs is implemented via a computing system including a processor. The method includes executing a graphics application and causing surfacing of a graphic design GUI on a display. The method includes generating a templatized image including text responsive to the user-initiated insertion of a desired image into a design template surfaced via the graphic design GUI. The method also includes assigning a legibility score to the text within the templatized image and, responsive to a determination that the legibility score is less than a predetermined threshold, generating a bounding box around the text area. The method further includes generating an improved templatized image with improved text legibility by selectively blurring the image portion that falls within the bounding box, as well as causing surfacing of the second templatized image via the graphic design GUI.

Abstract: Techniques are provided for an object file system for an object store. Data, maintained by a computing device, is stored into slots of an object. The data within the slots of the object is represented as a data structure comprising a plurality of nodes comprising cloud block numbers used to identify the object and particular slots of the object. A mapping metafile is maintained to map block numbers used to store the data by the computing device to cloud block numbers of nodes representing portion of the data stored within slots of the object. The object is stored into the object store, and the mapping metafile and the data structure are used to provide access through the object file system to portions of data within the object.

Abstract: Methods, apparatus, and processor-readable storage media for character-based representation learning for table data extraction using artificial intelligence techniques are provided herein.

Abstract: Embodiments of a vehicle interior system are disclosed. In one or more embodiments, the system includes a base with a curved surface, and a display or touch panel disposed on the curved surface. The display includes a cold-bent glass substrate with a thickness of 1.5 mm or less and a first radius of curvature of 20 mm or greater, and a display module and/or touch panel attached to the glass substrate having a second radius of curvature that is within 10% of the first radius of curvature. Methods for forming such systems are also disclosed.

Abstract: The method for creating an optical fiber ribbon of the present disclosure includes a first step of arranging a plurality of optical fibers in parallel to each other for creating the optical fiber ribbon. In addition, the method includes a second step of intermittently bonding the plurality of optical fibers partially at specific intervals using a matrix material. Further, intermittent bonding of the plurality of optical fibers is in pattern of text. Furthermore, intermittent bonding of the plurality of optical fibers allows the optical fiber ribbon to bend along preferential axis. Moreover, intermittent bonding of the plurality of optical fibers is in pattern of text.

Abstract: A booming cell start distance and recommended electronic tilt is identified by retrieving a list of cells served by a first base station. A plurality of grids is generated from the first base station to a predetermined threshold distance. A plurality of selected grids is identified between an acceptable coverage limit and a threshold distance. An evaluation is made regarding whether the first base station is not the dominant cell in each of the selected grids based. The number of grids where the first base station is not the dominant cell site is determined based on a dominant carrier threshold. A column of grids where the first base station is no longer the dominant cell site is determined based on the dominant carrier threshold. A bad booming distance of the cell is determined based on the distance from the first base station and the determined column of grids.

Abstract: A method and system are provided to infer and use machine learning algorithms that is applied to financial data and also to determine: (i) compliance with the applied algorithms, and (ii) whether any exceptions to and/or variations from the algorithms are within an organization's norms. A method includes: receiving financial data; applying a set of dynamic or interdependent algorithms to the received financial data to obtain a set of outcomes; and using a machine learning classifier to classify the outcomes as: (i) algorithm compliant, (ii) potentially algorithm non-compliant, or (iii) algorithm non-compliant. Additionally, the method includes generating controllership persona based actionable triggers, which on acceptance corrects the anomalies in financial data, enabling the method and system to perform as a comprehensive, contextual, consistent & machine learning powered, persona based real time controllership engine leading to reduced misstatements in reported financial data.

Abstract: Connection modification based on traffic pattern is described. In accordance with the described techniques, a traffic pattern of memory operations across a set of connections between at least one device and at least one memory is monitored. The traffic pattern is then compared to a threshold traffic pattern condition, such as an amount of data traffic in different directions across the connections. A traffic direction of at least one connection of the set of connections is modified based on the traffic pattern corresponding to the threshold traffic pattern condition.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method, and computer program product embodiments for adapting an automated speech recognition system to provide more accurate suggestions to voice queries involving media content including recently created or recently available content. An example computer-implemented method includes transcribing the voice query, identifying respective components of the query such as the media content being requested and the action to be performed, and generating fuzzy candidates that potentially match the media content based on phonetic representations of the identified components. Phonetic representations of domain specific candidates are stored in a domain entities index and is continuously updated with new entries so as to maintain the accuracy of the speech recognition of voice queries for recently created or recently available content.

Abstract: In described examples, a digital-to-analog converter (DAC) includes an output, a ground, a reference voltage terminal, an input code terminal, multiple switches, multiple resistors, and a controller. The switches couple to the reference voltage terminal when activated and to the ground when deactivated. The resistors are variously coupled between corresponding ones of the switches and the output, so that activating the switches causes the DAC to output an output voltage. The controller is coupled to the input code terminal and coupled to control the switches. The controller generates an output code based on an input code in response to at least one differential nonlinearity error greater than one least significant bit voltage. The input code corresponds to a first ideal output voltage, the output code corresponds to a second, different ideal output voltage. The controller generates an output voltage by controlling the switches using the output code.

Abstract: A cell range determination is made by determining a sector straddling an azimuth line of a first base station with a center at the coordinates of a first base station. The sector is divided into a plurality of subsectors. A nearest neighbor base station is determined in each of the plurality of subsectors. A set of coordinates is determined for the nearest neighbor base station. An average distance between the nearest neighbor base stations is determined. A bearing angle difference between the nearest neighbor base station and the first base station is determined based on the set of coordinates of the nearest neighbor base station. A gain is determined for each of the plurality of subsectors based on the bearing angle difference. A cell range is determined for the first base station based on the gain.

Abstract: Systems and methods are provided for controlling a wake-up operation of a memory circuit. The memory circuit is configured to precharge the bit lines of a memory array sequentially during wakeup. A sleep signal is received by the first bit line of a memory cell and then a designed delay occurs prior to the precharge of a second complementary bit line. The sleep signal may then precharge the bit lines of a second memory cell with further delay between the precharge of each bit line. The memory circuit is configured to precharge both bit lines of a memory cell at the same time when an operation associated with that cell is designated.

Abstract: First images that are screenshots from a first version of a software component are obtained. Second images that are screenshots from a second version are obtained. A collection of image deviations that includes pair-wise image deviations between pairs of images are identified. A pair of images includes a first image from the first images and a corresponding second image from the second images. An image deviation indicates a portion of the second image identified as differing from a spatially corresponding portion of the first image. The image deviations are grouped into deviation groups. At least some of the second images are associated with at least some of the deviation groups. A subset of the second images corresponding to a deviation group is output responsive to a selection of an indication of the deviation group.

Abstract: Disclosed herein are related to reducing power consumption of a memory device when transitioning from a sleep state to an operational state. In one aspect, the memory device includes a memory cell to store data. In one aspect, the memory device includes an output driver configured to: generate an output signal indicating the stored data, in response to a sleep tracking signal indicating that the memory cell is in the operational state, and generate the output signal having a predetermined voltage irrespective of the stored data, in response to the sleep tracking signal indicating that the memory cell is in the sleep state. In one aspect, the sleep tracking signal is delayed from a sleep control signal causing the memory cell to operate in the sleep state or the operational state.

Abstract: A temperature sensor includes a sensing element and a load. Multiple different currents pass through the sensing element in a sequential manner. Based on each current that passes through the sensing element, the sensing element outputs a complementary-to-absolute-temperature (CTAT) voltage and another current. Further, the currents that pass through the sensing element and the currents that the sensing element output separately pass through the load and result in the generation of multiple load voltages across the load. A current density ratio of the temperature sensor is determined based on the load voltages generated across the load. Further, a temperature value indicative of a temperature sensed by the temperature sensor is generated based on the current density ratio and the CTAT voltages outputted by the sensing element based on the different currents that pass therethrough.

Abstract: A memory circuit includes a global control circuit, a first local control circuit, and a first set of word line post-decoder circuits coupled to a first set of memory cells that is configured to store a first set of data. The global control circuit is configured to generate a first and second set of global pre-decoder signals, and a first set of local address signals. The first local control circuit includes a first set of repeater circuits and a first clock pre-decoder circuit. The first set of repeater circuits is configured to generate a first and second set of local pre-decoder signals in response to the corresponding first and second set of global pre-decoder signals. The first clock pre-decoder circuit is configured to generate a first and second set of clock signals in response to the first set of local address signals and the first clock signal.

Abstract: Embodiments of a curved vehicle display including a display module having a display surface, a curved glass substrate disposed on the display surface having a first major surface, a second major surface having a second surface area, and a thickness in a range from 0.05 mm to 2 mm, wherein the second major surface comprises a first radius of curvature of 200 mm or greater, wherein, when the display module emits a light, the light transmitted through the glass substrate has a substantially uniform color along 75% or more of the second surface area, when viewed at a viewing angle at a distance of 0.5 meters from the second surface. Methods of forming a curved vehicle display are also disclosed.

Abstract: Embodiments of a vehicle interior system are disclosed. In one or more embodiments, the system includes a base with a curved surface, and a display or touch panel disposed on the curved surface. The display includes a cold-bent glass substrate with a thickness of 1.5 mm or less and a first radius of curvature of 20 mm or greater, and a display module and/or touch panel attached to the glass substrate having a second radius of curvature that is within 10% of the first radius of curvature. Methods for forming such systems are also disclosed.

Abstract: The present disclosure relates to the field Quantum Key distribution (QKD) and discloses an apparatus (100) and method (300) for adjusting the phase modulator's modulating signal time reference in a phase-based QKD system. The QKD system comprises a pulse generator (10) that generates optical pulses and a phase modulator (20) that modulates the phase of each of the pulses. The apparatus (100) comprises abeam splitter/tap (112), a 1-bit delay interferometer (110), two photodetectors (106,108), and a processing device (104). The splitter feeds the phase modulated optical pulses to the interferometer (110). Two photo detectors are connected to the constructive and destructive output legs (110a,110b) of the interferometer (110). The photo detectors' output are then converted to digital signals and fed to the processing device (104).