US 11,537,436 B2 · Method of configuring a memory block allocation of a machine learning network

Abstract

Methods, systems, and devices for configuring a machine learning network are described. A device, which may be otherwise known as user equipment (UE), may support ultra-low power sensor applications. More specifically, the device may support memory block allocation of a machine learning network based on performance levels associated with the applications. For example, the device may identify a performance level associated with an application on the device. The device may determine that the performance level satisfies a condition, and subsequently determine a memory block allocation of a machine learning network of the device based on the performance level satisfying the condition. The memory block allocation may correspond to one or more connections of the machine learning network. Based on the memory block allocation, the device may adjust a quantity of memory blocks available for the machine learning network and process the application.

Claims20

Dependent claims

A method comprising:

identifying a performance level associated with an application on a device;
determining, based at least in part on identifying the performance level, that the performance level satisfies a condition;
determining a memory block allocation of a machine learning network of the device based at least in part on the performance level satisfying the condition, the memory block allocation corresponding to one or more connections of the machine learning network;
adjusting a quantity of memory blocks available for the machine learning network of the device based at least in part on the memory block allocation, the machine learning network comprising one or more cross-layer identity connections, each cross-layer identity connection of the one or more cross-layer identity connections including an identity function;
and
processing the application by the device including bypassing one or more intermediate layers of the machine learning network using the one or more cross-layer identity connections based at least in part on the adjusted quantity of memory blocks available for the machine learning network.

3 more elements

An apparatus comprising:

a processor,
memory coupled with the processor;
and
instructions stored in the memory and executable by the processor to cause the apparatus to:
identify a performance level associated with an application on the apparatus;
determine, based at least in part on identifying the performance level, that the performance level satisfies a condition;
determine a memory block allocation of a machine learning network of the apparatus based at least in part on the performance level satisfying the condition, the memory block allocation corresponding to one or more connections of the machine learning network, the machine learning network comprising one or more cross-layer identity connections, each cross-layer identity connection of the one or more cross-layer identity connections including an identity function;
adjust a quantity of memory blocks available for the machine learning network of the apparatus based at least in part on the memory block allocation;
and
process the application by the apparatus including bypass one or more intermediate layers of the machine learning network using the one or more cross-layer identity connections based at least in part on the adjusted quantity of memory blocks available for the machine learning network.

7 more elements

Dependencies are inferred from the claim text.

Method of configuring a memory block allocation of a machine learning network

Life of this patent

Method of configuring a memory block allocation of a machine learning network

Life of this patent

Abstract

Claims20