Lenovo (singapore) Pte. Ltd.

Xiaohua Xu

Rod D Waltermann

Timothy Winthrop Kingsbury

Bradley Park Strazisar

Saba Shah

Carolyne Rose Sealy

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.

Dynamic client/server selection for machine learning execution based on current performance characteristics

In one aspect, a device includes a processor and storage accessible to the processor. The storage bears instructions executable by the processor to receive an image of an area from a camera, and to execute image recognition on the first image to identify a dirty region in the area. Based on the identification of the dirty region, the instructions are executable to generate a command for a robotic cleaning device to move to the dirty region for facilitating cleaning of the dirty region by the robotic cleaning device.

Growing community of inventors

Raleigh, NC, United States of America

Xiaohua Xu