Abstract: An auxiliary power case can include a frame; a panel coupled to the frame, where the panel defines at least a portion of a recess; a rechargeable battery disposed at least in part in the recess; and a power interface operatively coupled to the rechargeable battery.

Abstract: An apparatus includes a processor and a memory that stores code executable by the processor. The code is executable by the processor to receive a request at a first device to execute a machine learning workload for the first device, dynamically determine at least one characteristic of the first device that is related to execution of the machine learning workload, dynamically determine at least one characteristic of a second device that is related to execution of the machine learning workload, and select one of the first and second devices to execute the machine learning workload in response to the at least one characteristic of the selected one of the first and second devices being more suitable for execution of the machine learning workload than another of the first and second devices.

Abstract: One embodiment provides a method, including: obtaining a dataset for generation of an outcome using a plurality of artificial intelligence models; classifying, using another artificial intelligence model and before employing the plurality of artificial intelligence models, the dataset into a feature-space; and employing a subset of the plurality of artificial intelligence models on the dataset, wherein the subset is selected based upon the classification of the dataset. Other aspects are described and claimed.

Abstract: A computing device can include a processor; memory accessible by the processor; a housing that includes a surface; and a deployable attachment mechanism for releasable attachment of an object to the surface.

Abstract: Apparatuses, methods, systems, and program products are disclosed for dynamic client/server selection for machine learning execution. An apparatus includes a processor and a memory that stores code executable by the processor. The code is executable by the processor to receive a request at a first device to execute a machine learning workload for the first device, dynamically determine at least one characteristic of the first device that is related to execution of the machine learning workload, dynamically determine at least one characteristic of a second device that is related to execution of the machine learning workload, and select one of the first and second devices to execute the machine learning workload in response to the at least one characteristic of the selected one of the first and second devices being more suitable for execution of the machine learning workload than another of the first and second devices.

Abstract: A computing device can include a processor; memory accessible by the processor; a housing that includes a surface; and a deployable attachment mechanism for releasable attachment of an object to the surface.

Abstract: One embodiment provides a method, including: obtaining a dataset for generation of an outcome using a plurality of artificial intelligence models; classifying, using another artificial intelligence model and before employing the plurality of artificial intelligence models, the dataset into a feature-space; and employing a subset of the plurality of artificial intelligence models on the dataset, wherein the subset is selected based upon the classification of the dataset. Other aspects are described and claimed.