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

Handwritten data classification method and system based on deep dynamic network

A dynamic network and data classification technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problems of long computer memory usage, low classification accuracy of deep learning models, and long training time, etc., to achieve training model The effect of reducing parameters, realizing self-adaptation, and improving training speed

Pending Publication Date: 2020-02-18
SHANDONG NORMAL UNIV
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In the existing process of classifying handwritten data, a deep learning model will be used, but the existing deep learning model has many parameters, the training time is too long, and the computer memory takes a long time; and the classification accuracy of the existing deep learning model is relatively low

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
  • Handwritten data classification method and system based on deep dynamic network
  • Handwritten data classification method and system based on deep dynamic network
  • Handwritten data classification method and system based on deep dynamic network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Embodiment 1, this embodiment provides a handwriting data classification method based on a deep dynamic network;

[0038] Such as figure 1 As shown, the handwriting data classification method based on deep dynamic network, including:

[0039] Training phase: construct a deep dynamic network; obtain the original training sample set including handwritten data samples and corresponding handwritten category labels; use the original training sample set to train the deep dynamic network to obtain the trained deep dynamic network;

[0040] Application stage: Obtain the handwritten data samples to be classified, input the handwritten data samples to be classified into the trained deep dynamic network, and output the recognition results of the handwritten data samples to be classified.

[0041] Such as image 3 As shown, as one or more embodiments, in the training phase, the specific steps of constructing a deep dynamic network include sequentially connected:

[0042] The inp...

Embodiment 2

[0076] Embodiment 2, this embodiment also provides a handwriting data classification system based on a deep dynamic network;

[0077] In the second aspect, the present disclosure also provides a handwriting data classification system based on a deep dynamic network;

[0078] Handwritten data classification system based on deep dynamic network, including:

[0079] Training module:

[0080] A network construction unit configured to: construct a deep dynamic network;

[0081] A first acquisition unit configured to: acquire an original training sample set including handwriting data samples and corresponding handwriting category labels;

[0082] The training unit is configured to: use the original training sample set to train the deep dynamic network to obtain the trained deep dynamic network;

[0083] Application module:

[0084] The second acquisition unit is configured to: acquire handwritten data samples to be classified;

[0085] The recognition unit is configured to: inp...

Embodiment 3

[0086] Embodiment 3. This embodiment also provides an electronic device, including a memory, a processor, and computer instructions stored in the memory and run on the processor. When the computer instructions are executed by the processor, the computer instructions in Embodiment 1 are completed. steps of the method described above.

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 discloses a handwritten data classification method and system based on a deep dynamic network. The method comprises the following steps: a training stage: constructing the deep dynamic network; obtaining an original training sample set containing handwritten data samples and corresponding handwritten category labels; training the deep dynamic network by using the original training sample set to obtain a trained deep dynamic network; and an application stage: obtaining to-be-classified handwritten data samples, inputting the to-be-classified handwritten data samples into the trained deep dynamic network, and outputting an identification result of the to-be-classified handwritten data samples.

Description

technical field [0001] The present disclosure relates to the technical field of handwritten data classification, in particular to a handwritten data classification method and system based on a deep dynamic network. Background technique [0002] The statements in this section merely mention background art related to the present disclosure and do not necessarily constitute prior art. [0003] The classification problem is a basic problem of artificial intelligence, and the quality of classification performance has an important impact and significance on other problems in the field of artificial intelligence. At present, for the image field, the more successful classification models include the AlexNet model, VGG model, GoogLeNet model, and ResNet model. The classification accuracy of these models on the IMAGENET dataset has reached a high level, but the models are generally There are many parameters (for example, AlexNet model parameters are about 60M, VGG model parameters ar...

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
IPC IPC(8): G06K9/68G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V30/244G06V30/10G06N3/045G06F18/214
Inventor 王强王吉华张化祥孙建德牛奔
Owner SHANDONG NORMAL UNIV