A data prediction method, device and neural network system based on neural network
A neural network and data prediction technology, applied in the field of neural networks, can solve problems such as low classification accuracy and image classification model prediction errors, and achieve model optimization and improve prediction accuracy.
Active Publication Date: 2019-08-20
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The technical problem to be solved by the embodiments of the present invention is to provide a neural network-based data prediction method to solve the problems of a large number of wrongly predicted samples and low classification accuracy in existing image classification 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 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 make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0054] refer to figure 1 , shows a structural block diagram of an embodiment of a neural network system according to an embodiment of the present invention. The neural network system 10 may at least include: a backbone network 101 and at least two branch networks 102 .
[0055] In the embodiment of the present invention, the backbone network 101 is used to extract features of the target image, obtain a feature set, and output the feature set to the at least two branch networks 102 .
[0056] Wherein, the depths of the two branch networks 102 are the same, and each branch network 102 has independent model parameters. Each branch network 102 is used to perform task processing according to the input features, and output correspondin...
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
An embodiment of the present invention provides a neural network-based data prediction method, device, and neural network system, wherein the neural network system includes a backbone network, at least two branch networks, and a voting unit, wherein the at least two branch networks The depth is the same, and each branch network has independent model parameters; the backbone network is used to extract features from the target image, obtain a feature set, and output the feature set to the at least two branch networks; the branch The network is used to perform task processing according to the input features, and output corresponding prediction results; the voting unit is used to fuse the prediction results output by the at least two branch networks to determine the final output result. The embodiment of the present invention can realize the optimization of the neural network model and improve the prediction accuracy of the neural network.
Description
technical field [0001] The present invention relates to the technical field of neural networks, in particular to a neural network-based data prediction method, a neural network-based data prediction device, a neural network system, an electronic device, and one or more machine-readable media . Background technique [0002] Image classification is to distinguish different types of images according to the semantic information of images. It is an important basic problem in computer vision and the basis of other high-level visual tasks such as image detection, image segmentation, object tracking, and behavior analysis. [0003] In recent years, deep learning has been widely used in video images, speech recognition, natural language processing and other related fields. As an important branch of deep learning, convolutional neural network (CNN) has greatly improved the prediction accuracy of image classification tasks due to its strong fitting ability and end-to-end global optimi...
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 Patents(China)
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/045G06F18/254G06F18/259
Inventor 张志伟吴丽军赵伟阳
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD