Neural network data set storage method based on block chain
A neural network and block chain technology, applied in the direction of neural learning methods, biological neural network models, neural architecture, etc., can solve the problems of little correlation, affect the training speed of neural network, reduce the accuracy of neural network, etc., and achieve the characteristic Strong extraction ability, improved calculation accuracy, and avoid over-fitting and under-fitting effects
Pending Publication Date: 2021-12-03
郑州颂和礼致信息科技有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The existing method of data storage based on blockchain is to randomly store data in blocks. Then, when performing neural network training based on the data in the blockchain, if you want to train a neural network with strong feature extraction capabilities, It is necessary to extract more data from the blockchain, but these data may be stored in blocks that are relatively far away or have little correlation, which seriously affects the training speed of the neural network, and over-fitting and under-fitting may also occur. The problem of fitting reduces the accuracy of the neural network
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0053] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following describes a method for storing neural network data sets based on blockchain according to the present invention with reference to the accompanying drawings and preferred embodiments. The specific embodiments, structures, features and effects thereof are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" are not necessarily referring to the same embodiment. Furthermore, the particular features, structures, or characteristics in one or more embodiments may be combined in any suitable form.
[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0055] The embodiment of the present invention provides a specific...
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
Login to View More Abstract
The invention relates to the technical field of block chains, in particular to a neural network data set storage method based on a block chain. The method comprises the following steps: firstly, acquiring source domain feature distribution and target feature distribution corresponding to each end according to stored data and to-be-stored data of each end in a block chain; according to the feature space where the source domain feature distribution of any two ends is located, performing mapping alignment on the two source domain feature distributions of different feature spaces; acquiring the rationality of each target feature vector in the target feature distribution corresponding to the two source domain feature distributions and the rationality of the target feature distribution according to the obtained mapping alignment result; and determining a target end capable of storing the to-be-stored data in the block chain according to a preset judgment condition. The optimal storage data is obtained by acquiring the reasonable degree of the to-be-stored data, the diversity and completeness of the storage data on the block chain are improved, and the purpose of training the neural network with higher accuracy and feature extraction capability is achieved.
Description
technical field [0001] The invention relates to the technical field of blockchain, in particular to a method for storing neural network data sets based on blockchain. Background technique [0002] With the rapid development of society, all walks of life need to record a large amount of data that is continuously generated. These data can assist the construction and development of society. For example, traffic image data can be used to assist the construction of urban transportation; financial foreign trade data can help customers and transaction data. It is used for big data analysis for financial risk warning, etc.; medical image data in the medical and health field can be used for disease diagnosis and so on. [0003] The existing method of data storage based on blockchain is to store data in blocks randomly. Then, when training a neural network based on the data in the blockchain, if you want to train a neural network with strong feature extraction ability, It is necessar...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/27G06N3/04G06N3/08
CPCG06F16/27G06N3/08G06N3/045Y02D10/00
Inventor 朱永恒朱登超
Owner 郑州颂和礼致信息科技有限公司