Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and apparatus for updating a deep learning model

A deep learning and model technology, applied in the computer field, can solve the problem of low update efficiency of deep learning models, and achieve the effect of improving update efficiency

Active Publication Date: 2021-05-25
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, the operation of training and updating the deep learning model is usually manually triggered by the user. Therefore, this leads to the problem of low update efficiency of the deep learning 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
  • Method and apparatus for updating a deep learning model
  • Method and apparatus for updating a deep learning model
  • Method and apparatus for updating a deep learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The application 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.

[0028] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0029] figure 1 It shows an exemplary system architecture 100 to which embodiments of the method for updating a deep learning model or the apparatus for updating a deep learning model of the present application can be applied.

[0030] Such as figure 1 As shown, the system...

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 present application discloses methods and devices for updating deep learning models. A specific implementation of the method includes: performing the following updating steps: obtaining a training data set from a preset path, and training a preset deep learning model based on the training data set to obtain a new deep learning model; The model is updated to the new deep learning model; the number of training times is incremented; it is determined whether the number of training times reaches the threshold value of the number of training times; if the threshold value of the number of training times is reached, the update step is stopped; if the number of training times does not reach the threshold value of the number of training times, Then continue to execute the updating step after a preset time interval. This embodiment improves model update efficiency.

Description

technical field [0001] The present application relates to the field of computer technology, specifically to the field of Internet technology, and in particular to a method and device for updating a deep learning model. Background technique [0002] Model is an important concept in machine learning. Simply put, it refers to the mapping from feature space to output space, and generally consists of the hypothesis function and parameters of the model. Commonly used models in the industry include LR (Logistic Regression, logistic regression), GBDT (full name Gradient Boosting Decision Tree, which is an iterative decision tree algorithm), SVM (Support Vector Machine, support vector machine), DNN (Deep Neural Network , deep neural network), etc. [0003] Deep learning is a branch of machine learning that attempts to use multiple processing layers that contain complex structures or multiple nonlinear transformations to perform high-level abstraction on data. [0004] At present, t...

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
CPCG06N20/00G06F18/217G06F18/214G06F18/22
Inventor 刘岚张发恩周恺王倩刘昆肖远昊徐东泽许天涵孙家元
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD