Machine learning method, electronic equipment and related products

Abstract

The embodiment of the invention discloses a machine learning method, electronic equipment and a related product. The method comprises the following steps: acquiring first input data, an actual tag corresponding to the first input data and N neural network models; respectively inputting the first input data into the N neural network models to obtain N output data; determining the KL divergence of each neural network model in N neural network models relative to the neural network models except for each neural network model for each neural network model based on the N output data, constructing a first loss function based on the original loss function of at least one neural network model in the N neural network models and the corresponding KL divergence to obtain at least one first loss function, and calculating the corresponding neural network model based on at least one first loss function and the actual label to obtain a second loss function; and obtaining at least one neural network model after operation. According to the embodiment of the invention, the expression capability of the neural network model can be improved.

Description

technical field [0001] This application relates to the technical field of image processing, in particular to a machine learning method, electronic equipment and related products. Background technique [0002] In the existing technology, the deep neural network has a very strong expressive ability and the effect is very good, but this is based on the fact that you have huge data. When you cannot obtain enough data, or the obtained data is unbalanced, the effect of deep learning is Very limited, and possibly not as good as traditional machine learning methods. Or when the task is very complex, it is difficult for the neural network to learn satisfactory results. Therefore, the problem of how to improve the expressive ability of the neural network model needs to be solved urgently. Contents of the invention [0003] Embodiments of the present application provide a machine learning method, electronic equipment, and related products, which can improve the expression ability of...

AI Technical Summary

Problems solved by technology

[0002] In the existing technology, the deep neural network has a very strong expressive ability and the effect is very good, but this is based on the fact that you have huge data. When you cannot obtain enough data, or the obtained data is unbalanced, the effect of deep learning is Very limited, and possibly not as good as traditional machine learning methods

Or when the task is very complex, it is difficult for the neural network to learn satisfactory results. Therefore, the problem of how to improve the expressive ability of the neural network model needs to be solved urgently.

Images