Model processing method and device

Abstract

The embodiment of the invention provides a model processing method and device, and the method comprises the steps: obtaining a plurality of training samples, and each training sample comprises feature data and a tag value; calculating the weight of each parameter in a neural network model based on the plurality of training samples, the weight being used for indicating the importance of the parameter; and attenuating partial parameters in the neural network model based on the weight of each parameter. According to the model processing scheme provided by the embodiment of the invention, the parameters in the model are attenuated based on the importance of each parameter in the neural network model, and the model performance is improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a model processing method and device. Background technique [0002] Artificial intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Artificial intelligence is a branch of computer science, which attempts to understand the essence of intelligence and enable machines to have the functions of perception, reasoning and decision-making. [0003] With the development of AI technology, the neural network model as an AI model has become more and more complex, which makes the neural network model unable to be deployed in many scenarios. To overcome this problem, a large number of neural network compression methods have been prop...

AI Technical Summary

Problems solved by technology

However, if the evaluation of the importance of parameters is inaccurate, some important parameters will be clipped, which will reduce the performance of the clipped model.

Images