Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Deep Neural Network Structure Design Method Inspired by Optimization Algorithms

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 time-saving and computing resources, high-efficiency neural network structures, and low classification error rates Effect

Active Publication Date: 2021-11-19
PEKING UNIV
View PDF3 Cites 0 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 Optimization Algorithms
  • A Deep Neural Network Structure Design Method Inspired by Optimization Algorithms
  • A Deep Neural Network Structure Design Method Inspired by Optimization Algorithms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention is further described below with reference to the accompanying drawings, but will not limit the scope of the invention in any way.

[0037] The present invention is applicable to any case using deep neural networks, such as image classification, object detection, character recognition, etc., to name but one embodiment herein, i.e. the present invention is applied to face recognition. Face recognition system mainly comprises four components, each image capture and a human face is detected, face image pre-processing, feature extraction and face image building classifiers to identify facial features. Depth convolutional neural network contains feature extraction and feature recognition process, based on the feature and superior to the face, the other face recognition support vector machine, line Hausdorff distance.

[0038] The present embodiment includes the following steps:

[0039] Step 1, the face data collection;

[0040] Is acquired by the imaging le...

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 a classical feedforward network structure in which all layers share the same linear and nonlinear transformations, the forward process in the feedforward network is equivalent to using The gradient descent method minimizes the iterative process of a function F(x); further adopts the re-ball method with faster convergence speed and the Nesterov acceleration algorithm to minimize the function F(x), thus obtaining a new network structure with better performance ; Can be used in artificial intelligence, computer vision and other application fields. Adopting the technical scheme of the present invention and designing the neural network structure based on the optimization algorithm can improve the traditional design method of relying on experience and experimental search, and obtain a more efficient neural network structure, thereby saving a lot of time and computing resources.

Description

Technical field [0001] The present invention relates to the field of network architecture design depth nerve, and particularly to a depth of neural network design method inspired by the optimization algorithm. Background technique [0002] With the rapid development in recent years, an image processor (GPU) computing power, as well as the amount of data that people can get more and more, the depth of the neural network has been widely used in computer vision, image processing and natural language processing and other fields. Since 2012, the depth of the neural network to achieve a breakthrough on ImageNet classification tasks, researchers have proposed a variety of different networks, and its structure is not limited to classical feedforward neural network architecture. Feeding network structure in the front, and each neuron is connected to the subsequent neuron only. Typical examples include the literature [1] (He, K., Zhang, X., Ren, S., and Sun, J.Deep residual learning for im...

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 Patents(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 Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com