Machine learning method and related device

Abstract

The embodiment of the invention discloses a machine learning method and a related device, and the method comprises the following steps: obtaining a training set and a testing set, enabling the training set to be unlabeled data, and enabling the testing set to be labeled data; mapping all the training samples in the training set to an embedding space through an unsupervised learning algorithm, clustering all the training samples by adopting a preset clustering algorithm to obtain a plurality of categories, and enabling each category to correspond to one pseudo label; configuring a plurality oftarget tasks for the training samples according to the pseudo tags; running a meta-learning algorithm based on the plurality of target tasks to train the training samples corresponding to the plurality of categories to obtain a target neural network model with a target learning mechanism; inputting the test set into a target neural network model for training to obtain updated parameters; optimizing the model parameters of the target neural network model according to the updated parameters to obtain the optimized target neural network model. By adopting the embodiment of the invention, the performance of the neural network model can be improved.

Description

technical field [0001] The present application relates to the technical field of machine learning, in particular to a machine learning method and related devices. Background technique [0002] Traditional supervised learning often uses a large number of labeled samples as a training set, and uses a deep neural network for iterative training to obtain the final model. With the rapid development of data collection and storage technology, it is quite easy to collect a large number of unlabeled samples, but it is relatively difficult to obtain a large number of labeled samples, because labeling these massive samples requires a lot of manpower and material resources. Therefore, how to use a large number of unlabeled samples to improve learning performance when there are few labeled samples has become one of the most concerned issues in current machine learning research. In this context, semi-supervised learning is proposed. [0003] Semi-supervised learning allows the learner t...

AI Technical Summary

Problems solved by technology

[0003] Semi-supervised learning allows the learner to automatically use unlabeled samples to improve learning performance without relying on external interaction. However, the current traditional semi-supervised learning cannot learn the impact of previous features on subsequent tasks, and its performance in various fields of machine learning is not good. Ideal, that is, the current machine learning effect is not good, so the problem of how to improve the performance of the neural network model needs to be solved urgently

Images