Optimization method and device for neural network

A technology of neural network and optimization method, applied in the field of artificial neural network, can solve problems such as occupation, high computational complexity of image data processing, and inability to reduce processing computational complexity, etc.

Inactive Publication Date: 2017-05-24
GUANGZHOU SHIYUAN ELECTRONICS CO LTD
View PDF0 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When using the neural network model to carry out face recognition, the existing problems are as follows: 1. The complexity of image data processing and calculation is high, which affects the operation time (such as processing face images on electronic devices equipped with Core i7 processors It often takes more than 1 second); 2. It needs to take up a lot of memory space or graphics card memory space during the processing; 3. It also needs to take up a lot of storage space to store the entire neural network model
[0003] The exist

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
  • Optimization method and device for neural network
  • Optimization method and device for neural network
  • Optimization method and device for neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] figure 1 A schematic flow diagram of a neural network optimization method provided in Embodiment 1 of the present invention, which is suitable for optimizing a neural network to be optimized that reaches a set accuracy condition after training and learning, and the method can be executed by a neural network optimization device , where the device can be implemented by software and / or hardware, and generally integrated on the terminal device or server platform where the neural network model is located.

[0022] like figure 1 As shown, a neural network optimization method provided in Embodiment 1 of the present invention includes the following operations:

[0023] S101. Acquire a first neural network meeting a set accuracy condition, and process a set training sample set based on the first neural network to obtain a first feature vector of each training sample in the training sample set.

[0024] In this embodiment, setting the accuracy condition may specifically be unde...

Embodiment 2

[0038] figure 2It is a schematic flowchart of a neural network optimization method provided by Embodiment 2 of the present invention. The second embodiment is optimized on the basis of the above embodiments. In this embodiment, "train the second neural network according to the first feature vector and the training sample set, and determine the first neural network that satisfies the set accuracy condition." The second neural network" is further optimized as: initializing the parameter value of the feature extraction parameter; according to the parameter value, the first feature vector, the training sample set and the set optimization function, determine the adjacent two-layer connection nodes in the second neural network target weight parameter value, and determine the second neural network with the target weight parameter as a candidate neural network; update the parameter value of the feature extraction parameter based on the set rule, if the parameter value does not meet t...

Embodiment 3

[0073] image 3 It is a structural block diagram of a neural network optimization device provided in Embodiment 3 of the present invention. The device is suitable for optimizing the neural network to be optimized which reaches the set accuracy condition after training and learning, wherein the device can be realized by software and / or hardware, and is generally integrated on the terminal device or server platform where the neural network model is located . like image 3 As shown, the device includes: an initial information acquisition module 31 , a network model construction module 32 , a network model optimization module 33 and a target network determination module 34 .

[0074] Wherein, the initial information acquisition module 31 is used to obtain the first neural network meeting the set accuracy condition, and based on the training sample set set by the first neural network processing, obtain the first training sample set in the training sample set. Feature vector;

...

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 embodiments of the invention disclose an optimization method and device for a neural network. The method comprises the steps of: acquiring a first neural network satisfying a set precision condition, and processing a training sample set based on the first neural network to obtain a first feature vector of each training sample in the training sample set; constructing second neural networks to be trained based on a set network construction condition; training the second neural networks according to the first feature vectors and the training sample set, and determining a second neural network satisfying the set precision condition; and determining the second neural network as a target neural network of the first neural network. By using the method, another newly-constructed small-scale neural network can be directly trained and learnt according to the optimization condition and then determined as a target optimization network of the neural network to be optimized, so that when feature recognition is performed based on the optimized neural network, the purposes of improving the recognition speed, shortening the recognition time and reducing the spatial occupation of a memory, a running memory, a display memory and the like can be fulfilled.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of artificial neural networks, and in particular to a neural network optimization method and device. Background technique [0002] At present, face recognition is usually performed based on a trained neural network model (such as a deep convolutional neural network model). When using the neural network model to carry out face recognition, the existing problems are as follows: 1. The complexity of the image data processing calculation is high, which affects the operation time (such as processing the face image on an electronic device equipped with a Core i7 processor It often takes more than 1 second); 2. It needs to take up a lot of memory space or video memory space of the graphics card during the processing; 3. It also needs to take up a lot of storage space to store the entire neural network model. [0003] The existing neural network model optimization methods cannot completely sol...

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
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 张玉兵
Owner GUANGZHOU SHIYUAN ELECTRONICS CO LTD
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