Unlock instant, AI-driven research and patent intelligence for your innovation.

Systems and methods for providing machine-learned model with adjustable computational demand

A machine learning model, computer technology, applied in the direction of neural learning methods, computing, biological neural network models, etc., can solve problems such as poor performance, increased delay or delay

Pending Publication Date: 2021-05-28
GOOGLE LLC
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As a result, on-device machine learning models may exhibit poor performance, such as increased latency or latency, and / or require sub-optimal allocation of device resources

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Systems and methods for providing machine-learned model with adjustable computational demand
  • Systems and methods for providing machine-learned model with adjustable computational demand
  • Systems and methods for providing machine-learned model with adjustable computational demand

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] overview

[0027] In general, the present disclosure is directed to systems and methods for providing machine learning models with adjustable computational requirements. Example aspects of the present disclosure are directed to computing systems and related methods that include or otherwise utilize machine learning models that can be tuned to accommodate the computational demands of executing the machine learning models on computing devices. In some implementations, a machine learning model may be stored and / or executed on a computing device (such as an "edge" device). Example devices include smartphones, "smart" devices, embedded devices, and any computing device that may have limited computing capabilities and / or may have access to cloud computing. Prior to inference time, the computing device may select a subset of the machine learning model (e.g., a set of one or more layers and / or blocks of layers) based on resource allocation parameters that correspond to Desi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A computing device is disclosed that includes at least one processor and a machine-learned model. The machine-learned model can include a plurality of blocks and one or more residual connections between two or more of the plurality of blocks. The machine-learned model can be configured to receive a model input and, in response to receipt of the model input, output a model output. The machine-learned model can be configured to perform operations including determining a resource allocation parameter that corresponds to a desired allocation of system resources to the machine-learned model at an inference time; deactivating a subset of the plurality of blocks of the machine-learned model based on the resource allocation parameter; inputting the model input into the machine-learned model with the subset of the plurality of blocks deactivated; and receiving, as an output of the machine-learned model, the model output.

Description

[0001] related application [0002] This application claims priority to and the benefit of U.S. Provisional Patent Application No. 62 / 739,584, filed October 1, 2018. US Provisional Patent Application No. 62 / 739,584 is hereby incorporated by reference in its entirety. technical field [0003] The present disclosure generally relates to machine learning models. More specifically, the present disclosure relates to systems and methods for providing machine learning models with adjustable computational requirements. Background technique [0004] On-device machine learning models have become more common. For example, deep neural networks have been deployed on "edge" devices such as mobile phones, embedded devices, other "smart" devices, or other resource-constrained environments. Such on-device models may offer benefits including reduced latency and improved privacy when compared to cloud-based configurations in which machine learning models are stored and accessed remotely, e....

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06F9/50G06N3/08
CPCG06F9/5005G06N3/082G06N3/045G06N3/04G06N3/08
Inventor M.沙里夫A.沙马A.莫德文特西夫
Owner GOOGLE LLC