Abstract: A system receives a configuration request comprising an infrastructure definition that defines a set of resources, to be selected from a set of tenant-managed resources implemented on a tenant's premises, for implementing the compute target entity. The system generates a compute target entity associated with an addressable identifier. The compute target entity corresponds to the set of resources selected from the set of tenant-managed resources. The system receives an execution request for execution of a set of operations, where the execution request specifies the addressable identifier associated with the compute target entity for execution of the set of operations. The system maps the addressable identifier of the compute target entity to the set of resources. The system causes execution of the set of operations on the set of resources on the tenant's premises via the compute target entity.

Abstract: Example compute-in-memory (CIM) or processor-in-memory (PIM) techniques using repurposed or dedicated static random access memory (SRAM) rows of an SRAM sub-array to store look-up-table (LUT) entries for use in a multiply and accumulate (MAC) operation.

Abstract: Systems and methods are provided to aid in planning at least a portion of a total knee arthroplasty procedure. The system and method automatically aligns the implant components and the bones according to a desired clinical alignment goal with minimum user input. The system and method further allows the user to adjust the position and orientation of the femur, tibia, or implant in a clinical direction regardless of a pre-adjusted position and orientation of the femur, tibia, or implant. The graphical user interface is provided that includes a three-dimensional (3-D) view window, a view options window, a patient information window, an implant family window, a workflow-specific tasks window, and a limb and knee alignment measures window.

Abstract: An apparatus has a device representing an endoscope, the device being either an endoscope or a dummy endoscope having shape and feel resembling an endoscope, and includes a tracker adapted to operate with a three-dimensional tracking system to track location and orientation of the device in three dimensions in a simulated operating-room environment. The apparatus also has a physical head model comprising hard and soft components, the device representing an endoscope configured to be inserted into the physical head model to provide a haptic feedback of endoscopic surgery.

Abstract: A machine learning accelerator (MLA) implemented on a semiconductor die includes a computing mesh of interconnected compute elements. The compute elements execute a program of instructions to implement a machine learning network according to a static schedule for execution of the instructions. The compute elements include gap counters. The number of cycles between any two instructions (i.e., the gap count) in a statically scheduled program is known and fixed. A gap counter counts cycles during execution and must reach the expected gap count before the later instruction can be executed. Synchronization between different processing elements may be maintained by suspending counting for a period of time.

Abstract: An apparatus has a device representing an endoscope, the device being either an endoscope or a dummy endoscope having shape and feel resembling an endoscope, and includes a tracker adapted to operate with a three-dimensional tracking system to track location and orientation of the device in three dimensions in a simulated operating-room environment. The apparatus also has a physical head model comprising hard and soft components, the device representing an endoscope configured to be inserted into the physical head model to provide a haptic feedback of endoscopic surgery.

Abstract: A machine learning accelerator (MLA) implemented on a semiconductor die includes a computing mesh of interconnected compute elements that includes storage elements (SEs) and processing elements (PEs). The compute elements execute a program of instructions to implement a machine learning network according to a static schedule for execution of the instructions. A compiler determines allowable time windows for the transfer of instructions and/or data from off-chip memory to the compute elements in order to fulfill the static schedule. If instructions/data are available before the time window opens, they are held until the window opens. If the window is about to close and the transfer of instructions/data is not yet complete, the execution of statically scheduled instructions is suspended to allow the transfer to complete within the window.

Abstract: A machine learning accelerator (MLA) implemented on a semiconductor die includes a computing mesh of interconnected compute elements that includes storage elements (SEs) and processing elements (PEs). The compute elements execute a program of instructions to implement a machine learning network according to a static schedule for execution of the instructions. A compiler determines allowable time windows for the transfer of instructions and/or data from off-chip memory to the compute elements in order to fulfill the static schedule. If instructions/data are available before the time window opens, they are held until the window opens. If the window is about to close and the transfer of instructions/data is not yet complete, the execution of statically scheduled instructions is suspended to allow the transfer to complete within the window.

Abstract: Methods for performing user authentication based on a multi-representation eye model for devices such as head-mounted display devices are disclosed. The multi-representation eye model may be generated and updated based on feature representations of an identified eye. The user authentication process may be initiated by causing an image to be captured of a current eye under a first set of conditions that may then be transformed into a current feature representation. The current feature representation may be applied to the multi-representation eye model to determine whether the current eye is a match for the identified eye.

Abstract: An optical beam intensity modulator comprising a modulator element arranged to transmit an optical beam along a first path in a first modulator state as a first beam and along a second, deviated path in a second modulator state as a second beam, and a beam return element arranged to return a transmitted beam to the modulator element.

Abstract: A machine learning accelerator (MLA) implemented on a semiconductor die includes a computing mesh of interconnected compute elements that includes storage elements (SEs) and processing elements (PEs). The compute elements execute a program of instructions to implement a machine learning network according to a static schedule for execution of the instructions. The instructions include data transfer instructions and compute instructions. The MLA includes a memory interface to off-chip memory. The MLA fetches instructions for the PEs from the off-chip memory, and the MLA transfers data between the SEs and the off-chip memory. A sync detector determines, for each compute element, whether sufficient data and instructions are available for continued operation of the compute element according to the static schedule. It generates a sync request if sufficient data and/or instructions are not available. A sync controller suspends operation of the computing mesh in response to the sync request.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve in-memory multiply and accumulate operations. An example apparatus includes a first multiplexer in a subarray of memory, the first multiplexer to receive first values representative of a column of a lookup table (LUT) including entries to represent products of four-bit numbers and return second values from an intersection of a row and the column of the LUT based on a first element of a first operand; shift and adder logic in the subarray, the shift and adder logic to shift the second values based on at least one of the first element of the first operand or a first element of a second operand; and accumulation storage in the subarray, the accumulation storage to store at least the shifted second values.

Abstract: Systems and methods to mask Personally Identifiable Information (“PII”) without masking proximate context are provided. The system may create a raw data set using at least one data file including PII through an ingestion pipeline. The system may identify and categorize the type of PII to be masked and record the type of PII in a data field. The system may selectively mask the PII by analyzing at least one location to determine a context proximate to the PII and masking only the PII. The system may output a masked data set including the at least one data file with the PII selectively masked and the data field containing a record of the type of PII selectively masked.

Abstract: A method for manufacturing a recyclable article from municipal solid waste (MSW) without addition of binders is disclosed. The method includes aspects of processing, a proportionate quantity of biodegradable waste and non-biodegradable waste to form a mixture. The processed mixture is loaded into a mould placed in a melter (9). The processed mixture is subsequently melted in the melter (9) at a pre-determined temperature and pre-determined pressure, where the non-biodegradable waste circumscribes and form a bond with the biodegradable waste during melting. The melted mixture is compressed in a compression moulding device (10) at a pressure ranging from 0.1 Kg/cm2 to 3.0 Kg/cm2. Further, the compression of the melted mixture is carried out under supply of a coolant for solidifying and forming the article.

Abstract: A cell logic structure for a battery-indifferent or pure energy harvesting multi-mode system, a battery-indifferent or pure energy harvesting multi-mode system, a method of operating a cell logic structure for a battery-indifferent or pure energy harvesting multi-mode system, and a method of operating battery-indifferent or pure energy harvesting multi-mode system.

Abstract: A system for optimizing routes for time-critical messages in a mesh network is provided. For example, a child node in a mesh network can communicate with the root node through any of its parent nodes. The child node is configured to transmit regular data to the root node through a primary route associated with its primary parent. When there is a time-critical message to be transmitted to the root node, the child node estimates a round trip time (RTT) for each route between the child node and the root node. The child node selects, among its parent nodes, a parent node whose associated route has the lowest RTT and transmits the time-critical message to the root node through the selected parent node. After the transmission of the time-critical message, the child node switches back to the primary route to transmit additional regular data to the root node.

Abstract: A system and method for providing a robust and effective solution for forecasting inventory for a warehouse/fulfilment centre (FC) at a product batch level. The method includes calculating a demand forecast data based on a forecast algorithm, correcting the calculated demand forecast data based on one or more exogenous variable, categorizing the inventory into different buckets at a product batch level, forecasting a warehouse level inventory demand for a predefined time based on the categorization, and sending an alert to one or more users based on the categorization. The method further includes predicting a demand forecast data for one or more upcoming weeks.

Abstract: A training system uses a physical model of a head and neck with a first tracker, a second tracker on a physical laryngoscope model, a third tracker on a physical endotracheal tube model, and a fourth tracker on a VR goggle; the system uses the trackers to determine positions of the physical models. A simulation system has corresponding digital 3D models of a laryngoscope, an endotracheal tube, and an airway, the airway including 3D models of surfaces of tongue, epiglottis, larynx, pharynx, and trachea. The physical model locations are registered to the digital models. In embodiments, the physical laryngoscope model has sensors measure strain or pressure along its blade and the simulation system has instructions to distort the digital 3D model of the airway according to readings of the sensors. The system can render the digital 3D model viewed from the VR goggle or a camera of the laryngoscope.

Abstract: Systems and methods are provided to aid in planning at least a portion of a total knee arthroplasty procedure. The system and method automatically aligns the implant components and the bones according to a desired clinical alignment goal with minimum user input. The system and method further allows the user to adjust the position and orientation of the femur, tibia, or implant in a clinical direction regardless of a pre-adjusted position and orientation of the femur, tibia, or implant. The graphical user interface is provided that includes a three-dimensional (3-D) view window, a view options window, a patient information window, an implant family window, a workflow-specific tasks window, and a limb and knee alignment measures window.

Abstract: In some implementations, formation of loops between nodes in an RPL network may be avoided. A node that receives a neighbor-discovery message may determine, based on a parent-child status, whether the neighbor-discovery message was received from a parent of the node. If the neighbor-discovery message was received from the parent, the node may transmit an error code to the parent. In addition, the node may determine, based on a comparison of reliability rankings, whether the neighbor-discovery message was received from a node with relatively high reliability, such as a potential grandparent node. If the neighbor-discovery message was received from a high-reliability node, the node may transmit an error code to the high-reliability node. Furthermore, the node may reduce network traffic by withholding a neighbor-detection message from a child node. The node may transmit a response to neighbor-detection messages received from the child node.