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

A computer-implemented method for training a neural network and an electronic system

An electronic system, computer technology used in the field of training neural networks

Pending Publication Date: 2021-09-24
SAMSUNG ELECTRONICS CO LTD
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The benefit of overparameterization is empirically shown to be a key factor for the great success of deep learning, but once a well-trained high-accuracy model is found, its deployment on various inference platforms faces different requirements and challenges

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
  • A computer-implemented method for training a neural network and an electronic system
  • A computer-implemented method for training a neural network and an electronic system
  • A computer-implemented method for training a neural network and an electronic system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Hereinafter, embodiments of the present disclosure are described in detail with reference to the accompanying drawings. It should be noted that the same elements will be denoted by the same reference numerals even though they are shown in different drawings. In the following description, specific details such as detailed configuration and components are merely provided to help a comprehensive understanding of the embodiments of the present disclosure. Accordingly, it should be apparent to those skilled in the art that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted for clarity and conciseness. Terms described below are terms defined in consideration of functions in the present disclosure, and may vary according to a user, user's intention, or custom. Therefore, definitions of terms should be determined b...

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 computer-implemented method for training a neural network and an electronic system are provided. The method includes receiving a random image at a generator, generating a composite image of the received random image at the generator, receiving the composite image at a teacher network, receiving the composite image at a student network, executing the teacher network and the student network with the composite image as an input, adjusting parameters of the student network so that the maximum value of the distance between the output of the teacher network and the output of the student network is minimized to train the student network, and restraining the generator.

Description

[0001] This application is based upon and claims priority to U.S. Provisional Patent Application Serial No. 62 / 993,258, filed March 23, 2020, and assigned Serial No. 62 / 993,258, which is hereby incorporated by reference in its entirety. technical field [0002] The present disclosure generally relates to computer-implemented methods and electronic systems for training neural networks. Background technique [0003] Deep learning is now leading to many performance breakthroughs in various computer vision tasks. The state-of-the-art performance of deep learning comes from over-parameterized deep neural networks, which enable the automatic extraction of useful representations (features) of data for target tasks when trained on very large datasets. Optimization frameworks for deep neural networks with stochastic gradient descent have recently become very fast and efficient with backpropagation techniques using hardware units dedicated to matrix / tensor computations, such as graphi...

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): G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06N3/047G06N3/04G06N5/022G06N3/088
Inventor 崔志焕李正元穆斯塔法·艾尔可哈米崔裕镇
Owner SAMSUNG ELECTRONICS CO LTD