Network model training method and device

Abstract

The embodiment of the invention provides a network model training method and device. The network model training method comprises the following steps: respectively inputting training samples in a preset training sample set into each sub-network model contained in a target network model, obtaining the value of the loss function of each sub-network model, and a value of the original loss function, wherein the loss function of one sub-network model is used for representing a difference value between an actual output result and an expected output result of the sub-network model, and the original loss function is used for representing a difference value between an actual output result and an expected output result of the target network model; and according to the value of the loss function of each sub-network model and the value of the original loss function, adjusting the model parameters of the target network model, and when a preset training stopping condition is met, stopping model training to obtain a trained target network model. Based on the above processing, the effectiveness of the trained network model can be improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a network model training method and device. Background technique [0002] With the rapid development of artificial intelligence technology, neural network models (which can be referred to as network models for short) have broad application prospects in the fields of system identification, pattern recognition, and intelligent control. Usually, based on the training sample set, the preset network model can be trained to obtain a trained network model. Then, the sample to be tested can be input into the trained network model to obtain the actual output of the network model. The actual output is The prediction result of predicting the sample to be tested. [0003] In one implementation, the network model has initial model parameters. In the process of training the network model, the model parameters of the network model can be adjusted according to the loss function....

AI Technical Summary

Problems solved by technology

[0005] For a target network model that contains multiple sub-network models, due to the differences in the structure and characteristics of each sub-network model, when the target network model is trained according to the loss function of the target network model, when the training of the target network model is stopped , some sub-network models reach a better convergence state, while other sub-network models may not reach a convergent state, which will lead to low effectiveness of the trained target network model

Images