Neural network model training system and method

A technology of neural network model and training system, applied in biological neural network models, neural learning methods, etc., to prevent calculation errors and improve reliability

Active Publication Date: 2015-10-14
SHENZHEN TENCENT COMP SYST CO LTD
View PDF4 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Based on this, it is necessary to provide a neural network model training system and method for the technical problems that limit the size of the neural network model due to the limitations of current physical equipment.

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
  • Neural network model training system and method
  • Neural network model training system and method
  • Neural network model training system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] 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.

[0022] Before describing the specific embodiments of the present invention, an example is given to illustrate the training process of the neural network model. refer to figure 1 , figure 1 A relatively simple neural network model is shown. The neural network model includes an input layer, two hidden layers and an output layer. The input layer has three nodes, respectively, node A0, node A1 and node A2; the first hidden layer includes two nodes, respectively, node B0 and node B1; the second hidden layer includes two nodes, respectively Node C0 and Node C1. The output layer includes a node D0. ...

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 relates to a neural network model training system and method. The system comprises a coordination device and a preset number of computation devices, wherein the coordination device is used for performing synchronous control on the computation devices according to the layers of a neural network model; each computation device is used for processing a node distributed to each computation device in the corresponding layer of the neural network model according to a training sequence of the neural network model and a training sample input to the neural network model under the synchronous control of the coordination device according to the layers of the neural network model, and sending data generated by node processing to a model storage device or the computation device which the next-layer node connected with the node of current device is located at until the training of the input training sample is ended. The neural network model training system and method provided by the invention solve the problem of scale limitation of the neural network model caused by limitation of a single physical device.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a neural network model training system and method. Background technique [0002] A neural network model is a machine learning model that mimics the structure of the brain. In the field of machine learning, neural networks are often used to model more complex tasks. The scale of the neural network, including depth and width, can be adjusted, depending on the application field and the scale of the problem. Because of the super expressive ability of the neural network, it is widely used in speech recognition, image classification, face recognition, natural language processing, advertising and other application fields. [0003] The structure of the neural network model includes multiple layers, the first layer is the input layer, the top layer is the output layer, the middle includes zero or more hidden layers, and each layer includes one or more nodes. The size of the in...

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
Inventor 郭志懋邹永强金涬李毅
Owner SHENZHEN TENCENT COMP SYST 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