Classification method based on correlation entropy and transfer learning

Abstract

The invention discloses a classification method based on correlation entropy and transfer learning, in the Machine learning technology field, The method is used for solving the problems that in the prior art, dilution assumption needs to be conducted on unpredictable noise, and samples marked by a target data set are insufficient. Label information of a source data set is fully utilized, knowledgein the source data set is robustly migrated to a target data set in a severe noise environment through joint learning of the source data set and the target data set, and therefore the classificationrecognition effect on the target data set is remarkably improved.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and in particular relates to a classification method based on correlation entropy and migration learning. Background technique [0002] Under the traditional machine learning framework, the task of supervised learning is to use labeled training samples to learn a classification model, and use this model to classify and predict test samples. There is a basic assumption in these traditional supervised learning models, that is, a large number of labeled training samples and test samples obey the same probability distribution. However, in many current research fields, due to the expensive manual labeling costs, training samples and test samples usually come from two different domains, the source domain and the target domain, and thus obey different probability distributions. In this case, traditional classification models cannot be extended to the target domain where the test samples are lo...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the above problems, the present invention proposes a classification method based on correlation entropy and transfer learning, which makes full use of the label information of the source data set, and effectively solves the problem of insufficient labeled samples in the target data set through joint learning of the source data set and the target data set. question

Images