Supervised learning method and device, label prediction method and device, electronic equipment and storage medium

Abstract

The invention relates to a supervised learning method and device, a label prediction method and device, electronic equipment and a storage medium. The method comprises the steps of acquiring trainingsamples and a corresponding same-class reference set, wherein the same-class reference set comprises a plurality of reference samples, labels corresponding to the reference samples are the same as labels corresponding to the training samples, and the labels of the reference samples are noiseless clean labels; determining the weight of the training sample according to the similarity between the training sample and the same class reference set; and weighting the loss of the training sample by adopting the weight of the training sample, and updating the parameters of the to-be-trained classification model based on the weighted loss. According to the embodiment of the invention, computing resources can be saved, and the accuracy of the classification model can be improved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to a method and device for supervised learning, label prediction, electronic equipment, and a storage medium. Background technique [0002] In machine learning, the method of training a neural network using labeled training data is called supervised learning. In supervised learning, the label quality of training data is crucial to the learning effect. Due to the huge cost of manually labeling large-scale data, data resources can be obtained from the network as training data. Because the labels of the data resources obtained from the network may have errors, that is, the labels of the data resources obtained from the network are noise labels, so the neural network trained by using these data resources will overfit to the training data containing noise labels, resulting in the Neural networks do not perform well on cleanly labeled test data. Contents of the inventio...

AI Technical Summary

Problems solved by technology

Because the labels of the data resources obtained from the network may have errors, that is, the labels of the data resources obtained from the network are noise labels, so the neural network trained by using these data resources will overfit to the training data containing noise labels, resulting in the Neural networks perform poorly on cleanly labeled test data

Images