Supercharge Your Innovation With Domain-Expert AI Agents!

Model training method and related device

A model training and network model technology, applied in the field of data processing, can solve problems such as high error rate of network models

Pending Publication Date: 2020-04-03
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the network model determined according to this multi-processing node parallel training method may have over-fitting problems in some cases, resulting in a high error rate for the network model

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
  • Model training method and related device
  • Model training method and related device
  • Model training method and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Embodiments of the present application are described below in conjunction with the accompanying drawings.

[0031] In order to improve the training speed of the complex model, a method of parallel training with multiple processing nodes can be adopted in related technologies. In order to reduce the training differences between multiple processing nodes, the model parameters of the models trained by all processing nodes are often synthesized at the end of one or more training iterations, and the synthesized model parameters are used as each processing in the next training stage. The initial parameters of the model trained by the node.

[0032] Such as figure 1 as shown, figure 1 Including a parameter server (parameter server) and multiple processing nodes (for example, 5 processing nodes), the parameter server is used as the central processing node to obtain the model parameters of all processing nodes at the end of a certain training iteration for synthesis, and obtai...

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 embodiment of the invention discloses a model training method and a related device. The model training method comprises the following steps: performing parallel training on a network model throughN processing nodes; determining M processing nodes in the N processing nodes when the ith training iteration is finished, wherein M is less than N; and obtaining model parameters of a network model trained by the M processing nodes as to-be-fused parameters, and determining initial model parameters of a network model trained by a target processing node at the beginning of (i + 1) th training iteration according to the to-be-fused parameters, wherein the target processing node is a processing node except M processing nodes in the N processing nodes. As the M processing nodes are local processing nodes in the N processing nodes, the initial model parameters can reflect the training characteristics of the local processing nodes, and the diversity of the initial model parameters is enhanced,and the over-fitting problem of the network model when the training is finally completed is reduced, and the model quality is ensured on the premise of improving the training efficiency.

Description

technical field [0001] The present application relates to the field of data processing, in particular to a model training method and related devices. Background technique [0002] With the development of artificial intelligence technology, various services can be provided to users through neural network models, such as speech recognition, image recognition, search, etc. A high-quality neural network model can only be obtained after training with a large amount of training data. When the magnitude of the training data is large, the time required to complete the training is very considerable, and it is difficult to meet the growing service needs. [0003] To solve the problem of high training time consumption, some related technologies have proposed a solution for parallel training of multi-processing nodes. For data sets that include massive training data, the same initial model is trained in parallel through multiple processing nodes. The training process will include multi...

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): G06N3/08G06N3/04G06K9/62
CPCG06N3/08G06N3/044G06N3/045G06F18/25
Inventor 黄羿衡田晋川
Owner TENCENT TECH (SHENZHEN) CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More