A deep neural network structure design method inspired by an optimization algorithm

A deep neural network and network structure technology, applied in neural learning methods, biological neural network models, etc., can solve problems such as the inability to design network structures, and achieve the effects of saving time and computing resources, low classification error rate, and efficient design

Active Publication Date: 2018-12-11
PEKING UNIV
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, search-based methods need to search for the optimal strategy in a huge search space. When the search space is huge and the computing power is limited, the existing search-based methods cannot design an effective network structure.

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 deep neural network structure design method inspired by an optimization algorithm
  • A deep neural network structure design method inspired by an optimization algorithm
  • A deep neural network structure design method inspired by an optimization algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0038] The present invention can be applied to any occasion using a deep neural network, such as image classification, object detection, text recognition, etc., but here is only one embodiment, that is, the present invention is applied to face recognition. The face recognition system mainly includes four components, which are face image acquisition and detection, face image preprocessing, face image feature extraction and building a classifier to recognize face features. The deep convolutional neural network includes both feature extraction and feature recognition processes, and its performance is superior to other face recognition methods based on eigenfaces, support vector machines, and line segment Hausdorff distance.

[0039] This embodiment specifically includes the following steps:

[0040] St...

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 deep neural network structure design method inspired by an optimization algorithm. For all layers share the same linear and non-linear transformation classic feedforward network structure, the forward process in the feedforward network is equivalent to an iterative process of minimizing a function F (x) using a gradient descent method. Furthermore, the function F (x) is minimized by using the double sphere method and the Nesterov acceleration algorithm with a faster convergence rate, and a new network structure with better performance is obtained. The method can be used in artificial intelligence, computer vision and other application fields. Through adoption of the technical scheme of the invention, the neural network structure is designed from the optimization algorithm, a traditional design mode depending on experience and experimenting to search can be improved, the more efficient neural network structure can be obtained, and a large amount of time and compute resources can be saved.

Description

technical field [0001] The invention relates to the technical field of deep neural network structure design, in particular to a deep neural network structure design method inspired by an optimization algorithm. Background technique [0002] With the rapid development of image processor (GPU) computing power in recent years and the increasing amount of data that people can obtain, deep neural networks have been widely used in computer vision, image processing, and natural language processing. Since the breakthrough of the deep neural network on the ImageNet classification task in 2012, researchers have proposed a variety of different networks, and their structures are not limited to the classic feedforward neural network structure. In a feedforward network structure, each neuron is only connected to the neurons that follow it. Typical examples include ResNet and literature [2] ( Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. Densely connected convolutional net...

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 林宙辰李欢杨一博
Owner PEKING UNIV
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