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

Method and device for training computer-implemented model

A computer and model technology, applied in computer parts, computing, neural learning methods, etc., can solve problems such as difficulty, large amount of calculation and memory access, etc.

Pending Publication Date: 2021-10-12
SAMSUNG ELECTRONICS CO LTD +1
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the learning process based on the gradient descent algorithm, such a technique may require a lot of computation and memory access, thus, it may not be easy to use the technique directly at the edge device

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
  • Method and device for training computer-implemented model
  • Method and device for training computer-implemented model
  • Method and device for training computer-implemented model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The following detailed description is provided to assist the reader in gaining an overall understanding of the methods, devices and / or systems described herein. However, various changes, modifications and equivalents of the methods, apparatus and / or systems described herein will be apparent after understanding the disclosure of the present application. For example, the order of operations described herein are examples only, are not limited to those orders set forth herein, and, except for operations that must occur in a particular order, can be manipulated as will become apparent after understanding the disclosure of this application. Change. Also, descriptions of features that are known after understanding the disclosure of the present application may be omitted for increased clarity and conciseness.

[0049] The features described herein may be implemented in different forms and should not be construed as limited to the examples described herein. Rather, the example...

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 method and device for training a computer-implemented model are disclosed. The method includes acquiring a first training data set; pre-training the computer-implemented model based on the first training data set to obtain a pretrained model; acquiring a second training data set; setting a searching range of mask weights based on either one or both of a distribution of mask weights of a binary mask corresponding to a filter of the pretrained model and a learning rate-related parameter set in the computer-implemented model; identifying a targeted mask weight in the searching range of the mask weights; training the pretrained model with the second training data set, and updating the targeted mask weight based on the binary mask and the pretrained model; and updating a portion of the binary mask based on the updated targeted mask weight and a preset reference value.

Description

[0001] This application claims Korean Patent Application No. 10-2020-0041638 filed with the Korean Intellectual Property Office on April 6, 2020 and Korean Patent Application No. 10-2020-0090452 filed with the Korean Intellectual Property Office on July 21, 2020 Interest in Patent Application, the entire disclosure of which is hereby incorporated by reference for all purposes. technical field [0002] The following description relates to methods and apparatus for training computer-implemented models. Background technique [0003] Computer vision aims to extract useful information from images. With the emergence of convolutional neural networks (CNNs) as an algorithm for computer vision tasks, a large number of accelerators have been developed to build fast and effective artificial intelligence (AI) systems in edge devices. However, the servable tasks of the system greatly depend on the learning model (e.g., computer-implemented model, computer vision model) pre-trained usin...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/044G06N3/045G06F18/214G06N3/082G06N3/048G06N3/08G06N3/098G06N3/0895G06N3/09G06N3/0985
Inventor 权桐赫金利燮申载康崔胜圭
Owner SAMSUNG ELECTRONICS CO LTD