DDNN training method and DDNN-based multi-view target recognition method and system

A training method and target recognition technology, applied in neural learning methods, climate sustainability, biological neural network models, etc., can solve problems such as difficulty in defining models, different complexity, etc. The effect of maintaining diversity

Active Publication Date: 2020-01-31
HUAZHONG UNIV OF SCI & TECH
View PDF8 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the complexity of different sample images is also different, it is difficult to define a model directly corresponding to it to select the appropriate sample image

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
  • DDNN training method and DDNN-based multi-view target recognition method and system
  • DDNN training method and DDNN-based multi-view target recognition method and system
  • DDNN training method and DDNN-based multi-view target recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.

[0039] The present invention compares the DDNN model to a "teacher-student" network, and the training of DDNN is that the teacher network (cloud-side model) guides the student network (edge-side model) to learn. The cloud-side model predicts the sample image and obtains an evaluation score; then, this score is used to evaluate the difficulty of the training sample image relative to the model. If...

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 DDNN training method and a DDNN-based multi-view target recognition method and system, and belongs to the field of cloud computing. The method comprises the steps of obtaining an information entropy of a distributed deep neural network cloud side model to a sample image; constructing a DDNN target function based on the information entropy of the sample image; and according to the DDNN target function, jointly training an edge side model and a cloud side model of the DDNN. In the knowledge migration method focused on a teacher-student network, under the background of multiple outlets of a DDNN level, the adaptive training method based on sample weighting is provided, scores of samples are obtained from a deep outlet of a DDNN, the samples are weighted through the scores to distinguish simple and complex samples, the weighted samples are used for training a cloud side model and an edge side model at the same time, and the communication traffic is minimum while good classification precision is guaranteed. The cloud side model guides the whole training process of the edge model, and the edge model can learn real labels and cloud side migration knowledge at thesame time.

Description

technical field [0001] The invention belongs to the field of cloud computing, and more specifically, relates to a DDNN training method and a DDNN-based multi-view target recognition method and system. Background technique [0002] Deep Neural Network (DNN) has a multi-layer structure, and its expression learning is also distributed in layers. For the input vector, the layer-by-layer transmission will bring delay to the layer behind the DNN, and as the operation parameters continue to accumulate, the calculation Energy consumption also increases layer by layer, which is not conducive to the real-time control of radio resources in the next generation mobile network. On this basis, a distributed deep neural network (Distributed Deep Neural Network, DDNN) model is proposed, which has a distributed computing hierarchy. DDNN for edge computing refers to mapping a single DNN part to a distributed heterogeneous device. Including cloud, edge and geographically distributed end device...

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): G06N3/04G06N3/08
CPCG06N3/08G06N3/045Y02T10/40
Inventor 肖江文邹颖王燕舞
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap