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

Sample training method for novel convolutional neural network

A convolutional neural network and sample training technology, applied in the field of neural network algorithms, can solve problems such as time consumption of neural networks, achieve the effects of improving intelligence and generalization, promoting the scope of use, and improving adaptability

Inactive Publication Date: 2016-05-04
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a fast neural network sample training method to solve the problem that the existing neural network consumes a lot of time in the sample collection and training process in the whole structure design and calculation process

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
  • Sample training method for novel convolutional neural network
  • Sample training method for novel convolutional neural network
  • Sample training method for novel convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The technical solution of the present invention will be further described in detail below.

[0015] In order to solve the problem that the existing neural network consumes a lot of time in the sample collection and training process in the whole structure design and calculation process, the present invention provides a new convolutional neural network sample training method, the method includes the following steps :

[0016] Determine a certain number of sample sets as the benchmark data set for training, moderately distort the training weights, and set the initial learning rate and final learning rate for training;

[0017] Based on the initial learning rate, the sample set is trained using the second-order backpropagation learning algorithm, and the training ends when the learning rate reaches the final learning rate.

[0018] In the process of using the second-order backpropagation algorithm, an error will be generated. The partial derivative of the error is equal to...

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 neural network algorithm, and aims to solve the problem that sample training and collecting consumes a lot of time in the whole structure design and calculation process of the existing neural network. The invention provides a sample training method for a novel convolutional neural network. The method comprises the following steps: determining a certain number of sample sets as benchmark data sets of training, moderately distorting the training weight, and setting the initial learning rate and the final learning rate of training; and using a second-order back propagation learning algorithm to train the sample sets based on the initial learning rate, and ending training when the learning rate reaches the final learning rate. The sample training method of the invention is applicable to sample training of neural network models.

Description

technical field [0001] The invention relates to a neural network algorithm, in particular to a sample training method of a novel convolutional neural network. Background technique [0002] Convolutional neural network is an important research field of computer vision and pattern recognition. It refers to the information processing system similar to human beings for specific objects inspired by the thinking of biological brain. It is widely used, fast and accurate object detection and recognition technology is an important part of modern information processing technology. Due to the rapid increase in the amount of information in recent years, we also urgently need suitable object detection and recognition technologies that allow people to find the information they need from a large amount of information. Image retrieval and text recognition belong to this category, and text detection and recognition systems are the basic conditions for information retrieval. Detection and r...

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): G06N3/08
CPCG06N3/08
Inventor 游萌
Owner SICHUAN CHANGHONG ELECTRIC CO LTD