Supercharge Your Innovation With Domain-Expert AI Agents!

A processing device and system for preventing neural network overfitting

A neural network and processing device technology, applied in the computer field, can solve the problems of time-consuming testing of multiple models, time-consuming models, time-consuming training models, etc., and achieve the effect of saving input and input resources and computing resources, and shortening computing time.

Active Publication Date: 2020-11-13
ANHUI CAMBRICON INFORMATION TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At this point, time-consuming training models becomes a big problem, not only time-consuming to train multiple models, but also time-consuming to test multiple models

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 processing device and system for preventing neural network overfitting
  • A processing device and system for preventing neural network overfitting
  • A processing device and system for preventing neural network overfitting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] A convolutional neural network usually consists of the following four layer structures: input layer, convolution layer, pooling layer, and fully connected layer. figure 1 is a schematic diagram showing the four-layer structure of the convolutional neural network 100 .

[0020] The input layer 102 intercepts part of the information from the input image and transforms it into a feature matrix for presentation, which contains features corresponding to the part of the information.

[0021] The convolutional layer 104 is configured to receive the feature matrix from the input layer 102, and perform feature extraction on the input image through a convolution operation. Although figure 1 The convolutional layer 104 only shows one layer of structure, but in actual use, multiple convolutional layers can be built. The first half of the convolutional layer is used to capture the local and detailed information of the image, that is, each pixel of the output image just feels the in...

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

The invention relates to a processing device and system for preventing over-fitting of a neural network, and the system includes: a network computing unit and a processing device. The network operator executes the training operation of the neural network; the processing device receives instructions from the network operator to generate random numbers, and sends input copies and selected neural network data to the network operator for performing the training operation. The invention can calculate random numbers and masks in advance and save them for later use, thereby shortening operation time, saving input and output resources and operation resources.

Description

technical field [0001] The present disclosure relates generally to the field of computing. More specifically, the present disclosure relates to processing devices and systems for preventing overfitting of neural networks. Background technique [0002] In a machine learning model, if the model has too many parameters and too few training samples, the trained model is prone to overfitting. Over-fitting problems are often encountered when training neural networks. Over-fitting is specifically manifested in: the loss function of the model on the training data is small, and the prediction accuracy is high, but the loss function on the test data is relatively large. The accuracy rate is lower. [0003] In order to solve the overfitting problem, the method of model integration is generally adopted, that is, multiple models are trained for combination. At this time, the time-consuming of training the model becomes a big problem. Not only is it time-consuming to train multiple mod...

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 Patents(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 不公告发明人
Owner ANHUI CAMBRICON INFORMATION TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com