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

Classification model training method combining active learning and transfer learning

A technology of transfer learning and classification models, which is applied in the field of efficient training of classification models by combining transfer learning and active learning, and can solve problems in areas where it is difficult to apply security and privacy, so as to avoid data security and privacy issues, learn efficiently, and avoid The effect of negative transfer

Pending Publication Date: 2022-01-14
GUIZHOU NORMAL UNIVERSITY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This is only suitable for situations where the source task is very similar to the target task, and is difficult to apply to areas involving security and privacy

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
  • Classification model training method combining active learning and transfer learning
  • Classification model training method combining active learning and transfer learning
  • Classification model training method combining active learning and transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] In this embodiment, the technical solution provided by the present invention is applied to quickly train a personalized epileptic seizure detection model for an epileptic patient. The application background is as follows: the EEG signals of epileptic seizures vary greatly among different patients, and even the different seizure times of the same patient also vary greatly. The accumulation time and labeling cost of epileptic seizure labeling data are very high, and due to privacy protection reasons, it is difficult to obtain a large amount of other patient data from other hospitals or institutions. These two main reasons make it very difficult to train a general-purpose seizure detection model, and a more feasible solution is to train a personalized seizure detection model for each patient.

[0073] Preparation and instructions before implementing the program:

[0074] Source task: Onset and non-seizure binary classification of the epilepsy EEG dataset NEO.

[0075] So...

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 discloses a classification model training method combining active learning and transfer learning. The classification model training method mainly comprises the following important steps: 1) transmitting source task knowledge to a target task model in a mode of selecting training samples for the target task model by adopting a source task model; 2) the source task model and the target task model actively select a certain proportion of samples for training the target task model; and (3) the source task model selects samples with high certainty, the target task model selects samples with high uncertainty, and the relative proportion of the number of the samples selected by the source task model and the number of the samples selected by the target task model is dynamically determined by the relative advantages and disadvantages of the classification performance of the two models. According to the method, negative migration is avoided, the method is suitable for the field needing data safety / privacy protection, the collected target task training sample set is high in quality, and learning is more efficient. Meanwhile, the number of training samples needed for training the target task model is reduced, the problem of imbalance of the training samples is relieved, and knowledge migration between heterogeneous models can be achieved.

Description

technical field [0001] The present invention relates to classification model training, transfer learning and active learning in the fields of machine learning and artificial intelligence, and in particular to a method for efficiently training classification models by combining transfer learning and active learning. Background technique [0002] Rapid advances in machine learning and artificial intelligence are turning classification models into a product for pattern classification / recognition services. [0003] For example, in the Chinese patent literature, the invention patent (publication number CN107729908A) applied by Alibaba Group Holding Co., Ltd. discloses a method, device and system for establishing a machine learning classification model, wherein the method includes: detecting Including the labeling frame of the product body; using a segmentation method based on the labeling frame to segment the product body in the labeling frame to obtain a first segmentation resul...

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): G16H50/20G16H50/50G06V10/70G06V10/764G06V10/774G06K9/62G06N20/00
CPCG16H50/20G16H50/50G06N20/00G06F18/24G06F18/214
Inventor 曹永锋马顺
Owner GUIZHOU NORMAL UNIVERSITY
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