Classification model training method combining active learning and transfer learning

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...

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

Images