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

A training set optimization method and system of a neural network model

A technology of neural network model and optimization method, applied in biological neural network model, neural architecture, character and pattern recognition, etc., can solve problems such as loss of high-dimensional training features, poor overall quality of training sets, and loss of data sets, etc. The effect of optimizing the training set and improving the prediction accuracy

Inactive Publication Date: 2018-12-11
PHICOMM (SHANGHAI) CO LTD
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, using this traditional feature extraction technique will actually lose some high-dimensional training features and some representative data sets, and finally the overall quality of the training set is not optimistic.

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 training set optimization method and system of a neural network model
  • A training set optimization method and system of a neural network model
  • A training set optimization method and system of a neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation manners of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention, and those skilled in the art can also obtain other accompanying drawings based on these drawings and obtain other implementations.

[0038] In order to make the drawing concise, each drawing only schematically shows the parts related to the present invention, and they do not represent the actual structure of the product. In addition, to make the drawings concise and easy to understand, in some drawings, only one of the components having the same structure or function is schematically shown, or only one of them is marked. Herein, "a" not only means "only one", but also means "more than one".

[0039] In on...

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 training set optimization method and system of a neural network model. The method comprises the following steps: dividing collected original data into a test set and a training set according to a preset proportion; preprocessing the test set to obtain the processed file set; normalizing each file in the processed file set; predicting a classification probability of each normalized file using a neural network model trained according to the training set; according to the classification probability of each file and according to the preset condition to be optimized, obtaining a corresponding file set to be optimized; augmenting each to-be-optimized file in the to-be-optimized file set to obtain an augmented data set as an optimized training set. The invention uses theprediction result of the test set which is homologous to the training set to expand and optimize the training set, thereby improving the prediction accuracy rate of the neural network model.

Description

technical field [0001] The invention relates to the field of neural networks, in particular to a method and system for optimizing a training set of a neural network model. Background technique [0002] During the training and debugging process of the neural network, the quality of the training set can directly affect the performance of the neural network. The higher the quality of the training set, the better the performance of the neural network. [0003] For the optimization of the training set, the existing schemes include: corresponding analysis of the characteristics of the training set, and then corresponding evaluation; and then corresponding optimization according to the score. Its essence is actually a comparison of the similarity of the training set features, which will give higher scores to similar pictures, and lower scores to less similar pictures. The features used are all feature extraction in traditional image processing. technology. [0004] However, using...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/22G06F18/214
Inventor 罗培元
Owner PHICOMM (SHANGHAI) CO LTD