Abstract: An information handling system includes a storage and a basic input/output system (BIOS). The BIOS load and boot the base root file system. The BIOS determine a requested capability for the information handling system. The BIOS download an external root file system for the requested capability. The BIOS overlay the external root file system on the base root file system. The BIOS determine a job associated with the requested capability is completed. Based on the job being completed, the BIOS delete the external root file system.

Abstract: Virtual memory pooling, including identifying GPUs of respective IHSs, wherein each of the GPUs is associated with a respective internal memory allocation; partitioning, for each GPU, the internal memory allocation associated with the GPU into a first memory allocation and a second memory allocation; allocating, for each GPU, the first memory allocation of the internal memory allocation associated with the GPU as accessible only by the associated GPU; pooling, for each GPU, the second memory allocation of the internal memory allocation associated with the GPU to define a virtual memory pool, the virtual memory pool accessible by each GPU; processing, at a first GPU, a computational task, including: accessing the first memory allocation associated with the first GPU; determining that processing of the computational task exceeds a capacity of the first memory allocation of the first GPU and in response, requesting access to the virtual memory pool.

Abstract: Systems, apparatuses, methods, and computer program products are provided herein. For example, the method includes identifying production data representative of an object process and an object. In some embodiments, the object process comprises a plurality of subsidiary object processes. In some embodiments, the method includes generating an object process state representation template using the production data. In some embodiments, the method includes, from at least one of the plurality of processing systems, operational data. In some embodiments, the method includes the operational data to determine an object process state. In some embodiments, processing the operational data comprises applying the operational data to an object process state model. In some embodiments, the method includes generating an object process state representation in response to determining the object process state.

Abstract: Embodiments provide for robust data integration. Some embodiments configure at least one computing device to establish at least one connection by any one of a plurality of data intake connection types. Each data intake connection type may be configured to facilitate the connection between the at least one computing device with at least one external computing device to access source data stored via the at least one external computing device via a distinct data access protocol. Some embodiments generate a job data object defining at least one data intake connection type. Some embodiments, access particular source data associated with the job data object on at least one particular external computing device, generate a filtered job data object by applying one or more filter data objects to the job data object, and retrieve relevant data from the source data by executing the filtered job data object.

Abstract: An immersive scene monitoring system presents a monitoring interface providing a virtual reality (VR)/augmented reality (AR) view of a scene associated with production operation(s) for a (e.g., pharmaceutical) product. The VR/AR view of the scene may be displayed with interactable graphical elements representing input fields corresponding to attributes of quality management events to be generated. The system generates the quality management events based on input (e.g., voice, gesture) received via the monitoring interface. The VR and/or AR view of the scene may be displayed with indicators of detected anomalies, and the input fields and/or corresponding attributes may be automatically populated by the system based on recognized objects and/or anomalies depicted in captured image data of the VR/AR view of the scene. The system can be configured for different scenes pertaining to different production operations and/or different products via a configuration interface.

Abstract: An information handling system detects installation of a hardware device that includes software, and transmits a request for a secure boot certificate associated with a hardware identifier of the hardware device and a software version of the software to a remote secure boot service. The secure boot service which maintains a centralized secure boot certificate store queries for the secure boot certificate based on the request and transmits the secure boot certificate to the information handling system. The secure boot service also performs a refinement mapping of the secure boot certificates in the store. Subsequent to receiving the secure boot certificate, the system provisions the secure boot certificate.

Abstract: Denial of dynamic host configuration protocol (DHCP) internet protocol (IP) address allocation to an unauthorized node via cross secure boot verification is presented herein. A system enables storage of a boot storage certificate in a boot data store of a client device, in which the boot storage certificate has been signed by a key exchange key (KEK) that has been stored in a network boot data store of a network switch device of a network; intercepts a DHCP discover packet that has been directed, by the client device, to a DHCP device of the system that assigns respective IP addresses to client devices to facilitate respective accesses, via the client devices using the respective IP addresses, of the network; and in response to determining that the secure boot storage certificate has been signed by the KEK, assigns an IP address of the respective IP addresses to the client device.

Abstract: Embodiments provide for intelligent report configuration. Some embodiments aggregate historical configuration data based at least in part on a plurality of historical reports, receive a signal indicative of a configuration request for a report having a hierarchical data structure, identify at least one configuration node of a report configuration workflow for configuring the report. The report configuration workflow may be defined by a hierarchical arrangement of a plurality of configuration nodes. Some embodiments generate, based at least in part on the historical configuration data and using one or more models, one or more data objects for the at least one configuration node. The one or more data objects may be indicative of at least a portion of the configuration data for one or more portions of the report. Some embodiments cause display of the one or more data objects on a configuration user interface rendered on a user device.

Abstract: A system and method is disclosed for automatically triggering a quality event filing in a monitored area, comprising: receiving incoming data from a plurality of connected devices in the monitored area, the incoming data including environmental data of the monitored area and user data of at least one user in the monitored area; determining, by the at least one processor, whether the incoming data is indicative of the occurrence of at least one quality event in the monitored area; and upon a determination that the incoming data is indicative of at least one quality event, generating, by the at least one processor, a quality event form with form data pre-filled, and transmitting the quality event form to a graphical user interface of a user device of at least one user in the monitored area.

Abstract: A system of energy transfer comprises rotatable drive input shafts (108) of an input side, each having a drive receiving end (110) and a second end (112). The drive receiving end (110) is operatively connected to multiple drive sources (102). The system further comprises a rotatable drive output shaft (120) of the input side that is coupled to a continuous variable transmission (122) and a planetary gear and is operatively coupled to a pinion (116). The second end (112) is coupled to rolling friction gears (114) that houses a freewheeling clutch (118) acting upon the pinion (116). The rolling friction gears (114) have circular gear teeth that mesh with circular gear teeth of the pinion (116) for transferring rotating movements of the multiple rotatable drive input shafts (108) of the input side into the rotating movement of the rotatable drive output shaft (120) of the input side.

Abstract: Systems, computer program products, and methods are described herein for intelligent database modelling. The present invention is configured to capture, using the augmented reality application, a drawing made by the user on a medium; initiate a first machine learning model on the drawing; determine that the user is attempting to design a database model; extract at least a first entity from the drawing; determine, using the first machine learning model, one or more attributes for the first entity; initiate, via the augmented reality application, a first push notification for display on the computing device of the user; electronically receive, via the augmented reality application, a user selection of a subset of attributes from the one or more attributes; generate, using the augmented reality application, a conceptual database model based on at least the first entity and the subset of attributes.

Abstract: Systems and methods for low bias negative sampling of classes according to the sampled softmax method are described herein. The systems and methods can include training a machine-learned model for classifying inputs into one or more classes of a plurality of classes, each of the plurality of classes having an associated class embedding in a plurality of class embeddings. The systems and methods can include selecting, by the one or more computing devices, one or more negative classes from the plurality of classes based at least in part on a probability distribution approximating a softmax distribution, wherein the probability distribution is determined based at least in part on a Random Fourier Features map.

Abstract: Virtual memory pooling, including identifying GPUs of respective IHSs, wherein each of the GPUs is associated with a respective internal memory allocation; partitioning, for each GPU, the internal memory allocation associated with the GPU into a first memory allocation and a second memory allocation; allocating, for each GPU, the first memory allocation of the internal memory allocation associated with the GPU as accessible only by the associated GPU; pooling, for each GPU, the second memory allocation of the internal memory allocation associated with the GPU to define a virtual memory pool, the virtual memory pool accessible by each GPU; processing, at a first GPU, a computational task, including: accessing the first memory allocation associated with the first GPU; determining that processing of the computational task exceeds a capacity of the first memory allocation of the first GPU and in response, requesting access to the virtual memory pool.

Abstract: Managing devices at an information handling system, including coupling a non-standard device list (SDL) device with an information handling system, the non-SDL device associated with a first communication protocol; establishing a communication channel between the non-SDL device and a remote access controller (RAC) of a private cloud server, the RAC associated with a second communication protocol; identifying a metadata template associated with the non-SDL device, the metadata template indicating one or more parameters associated with the non-SDL device; converting, based on the parameters of the metadata template of the non-SDL device, a request from the second communication protocol to the first communication protocol; and providing, using the first communication protocol, the converted request to the non-SDL device.

Abstract: Virtual machine memory management, including assigning, for each virtual machine operating at a compute node, respective first memory modules to the virtual machine operating at a storage node; accessing, by the virtual machines and over a first communication channel between the compute node and the storage node, the respective first memory modules; detecting, for a particular virtual machine, a loss of connectivity of the particular virtual machine with respective first memory modules assigned to the particular virtual machine, and in response: assigning, for the particular virtual machine, second memory modules to the particular virtual machine operating at the compute node; establishing a second communication channel between a BMC of the storage node and a RAC of the computing node; transferring, over the second communication channel, data stored at the respective first memory modules assigned to the particular virtual machine to the second memory modules assigned to the particular virtual machine.

Abstract: A multi-class classification system performs multi-class classification using an adapted, multi-level binary classification model in conjunction with pre-classification and post-classification processing. Original, multi-class training data is transformed into coarse-level adapted training data and fine-level adapted training data. In the coarse-level adapted training data, objects from the original training set are classified into either a majority classification set (representing the largest original classification set) or a non-majority classification set representing a combination of the remaining classification sets from the original training data. In the fine-level adapted training data, objects from the non-majority classification set retain their original classifications from the original training data.

Abstract: Systems, apparatuses, methods, and computer program products are provided. For example, a method provided herein may include identifying operational data representative of an activity amount associated with a computing account. In some embodiments, the method may include determining that the computing account is associated with a deactivated status based at least in part on the operational data. In some embodiments, the method may include parsing a computing account dataset associated with the computing account to identify a plurality of computing account objects. In some embodiments, the method may include applying the plurality of computing account objects to a computing account objects classification model. In some embodiments, the method may include generating a plurality of computing account representation requests.

Abstract: Systems, apparatuses, methods, and computer program products are provided. For example, a computer-implemented method provided herein may include receiving a system architecture. In some embodiments, the system architecture is representative of a plurality of services and a plurality of services metadata datasets. In some embodiments, the computer-implemented method may include parsing the system architecture to generate a plurality of services resource consumption representation requests. In some embodiments, the computer-implemented method may include processing the plurality of services resource consumption representation requests using a plurality of services resource consumption utilization tools. In some embodiments, the computer-implemented method may include receiving a plurality of services resource consumption responses from the plurality of services resource consumption utilization tools.

Abstract: A multi-label classification system performs multi-label classification using an adapted multi-class classification model in conjunction with pre-classification and post-classification processing and data transformation. An original, multi-label training data set in which objects are classified into at least one but possibly multiple original classification sets is transformed into an adapted, multi-class training data set in which the same objects are each classified into a combined classification set representing a combination of all of the individual, original classification sets into which the object is classified in the original training data set. The adapted training data set is used to train a multi-class classification model, which trained model is used to generate a multi-class classification of objects with respect to an input data set. The multi-class classification is transformed into a multi-label classification.

Abstract: A multi-class classification system performs multi-class classification using an adapted, multi-level binary classification model in conjunction with pre-classification and post-classification processing. Original, multi-class training data is transformed into coarse-level adapted training data and fine-level adapted training data. In the coarse-level adapted training data, objects from the original training set are classified into either a majority classification set (representing the largest original classification set) or a non-majority classification set representing a combination of the remaining classification sets from the original training data. In the fine-level adapted training data, objects from the non-majority classification set retain their original classifications from the original training data.