Incremental learning method and system based on small number of labeled samples

Abstract

The invention belongs to the technical field of big data intelligent analysis, and particularly relates to an incremental learning method and system based on a small number of labeled samples. Expanding and enhancing a small number of labeled samples to obtain a reliable label data set, and learning the network by using the reliable label data set to obtain a pre-training model; based on a networkpre-training model, performing prediction classification on a large number of unlabeled samples, and constructing an incremental learning candidate data set; combining the reliable label data set andthe incremental learning candidate data set to obtain an incremental learning data set, performing incremental learning on the network pre-training model, and performing calibration learning on the incremental learning model by using the reliable label data set; and carrying out prediction classification on the unlabeled data by utilizing the pre-training model after calibration learning, and judging return and re-execution by setting loop iteration conditions. According to the method, reliable sample data used for classification and recognition are obtained through incremental learning underthe condition that only a small number of labeled samples exist, and the classification and recognition performance and accuracy are improved.

Description

technical field [0001] The invention belongs to the technical field of big data intelligent analysis, and in particular relates to an incremental learning method and system based on a small number of labeled samples. Background technique [0002] IDC pointed out in the white paper "Data Age 2025" that the global data volume will reach 163ZB in 2025, and about 20% of it will be life-threatening data, and about 10% will reach a super-critical level. The big data explosion has promoted the transition from the information age to the data age, and induced the emergence of the fourth paradigm of scientific research—data-intensive scientific research, but it has also brought new problems. How to mine high-value information and knowledge from multi-source, heterogeneous, diverse, and modal big data has long been beyond the capabilities of traditional manual means. The development of artificial intelligence technology, especially deep learning technology, has become an important fact...

AI Technical Summary

Problems solved by technology

Although the above research can improve the classification and recognition performance in the case of a small number of labeled samples to a certain extent, the applicability and accuracy of the method need to be further improved.

Images