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

Neural network model training method and device

A technology of neural network model and training method, applied in the direction of biological neural network model, neural architecture, etc., can solve problems such as failure to meet business needs, low precision, loss of model precision, etc.

Pending Publication Date: 2021-09-07
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the deep neural network, there is a very strong dependency between the parameters of each layer of the model, but the distribution of the parameters of the high-bit-width neural network model may change after quantization, so the parameters of the quantized low-bit-width neural network model The dependency relationship between may be changed, resulting in the loss of accuracy of the quantized model, or even the situation where the accuracy is too low to meet business needs

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 method and device
  • Neural network model training method and device
  • Neural network model training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present disclosure 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 related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

[0024] It should be noted that, in the case of no conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments.

[0025] figure 1 An exemplary system architecture 100 to which the method for training a neural network model or the training device for a neural network model of the present disclosure can be applied is shown.

[0026] Such as figure 1 As shown, the system architectur...

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 the field of artificial intelligence. The embodiment of the invention discloses a neural network model training method and device. The method comprises the steps that a first neural network model is quantized according to a preset quantization bit width, a second neural network model is obtained, and the parameter bit width of the first neural network model is larger than the parameter quantization bit width of the second neural network model; the method also includes determining a distribution difference between the parameter distribution of the first neural network model and the parameter distribution of the quantized neural network model; and constructing a supervision function according to the distribution difference, and training the first neural network model by adopting a preset media data sample based on the supervision function. The method can be used for training to obtain a neural network model suitable for quantification.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, specifically to the field of artificial intelligence technology, and in particular to a training method and device for a neural network model. Background technique [0002] The quantization of the neural network model is to convert the high-bit-width model parameters into low-bit-width model parameters, so as to improve the calculation speed of the model. Quantization is usually performed after the training of a high-bit-width neural network model is completed. In the deep neural network, there is a very strong dependency between the parameters of each layer of the model, but the distribution of the parameters of the high-bit-width neural network model may change after quantization, so the parameters of the quantized low-bit-width neural network model Dependencies between may be changed, resulting in the loss of accuracy of the quantized model, or even the situation ...

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): G06N3/04
CPCG06N3/045
Inventor 希滕张刚温圣召
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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