US Patent Application 18446294. MODEL TRAINING METHOD AND APPARATUS simplified abstract
Contents
MODEL TRAINING METHOD AND APPARATUS
Organization Name
Huawei Technologies Co., Ltd.==Inventor(s)==
[[Category:Yucong Zhou of Shenzhen (CN)]]
[[Category:Zhao Zhong of Beijing (CN)]]
MODEL TRAINING METHOD AND APPARATUS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18446294 titled 'MODEL TRAINING METHOD AND APPARATUS
Simplified Explanation
- This patent application describes a method for training neural network models in the field of artificial intelligence. - The method involves obtaining an initial neural network model and replacing a convolutional layer in the model with a linear operation. - This replacement results in multiple new neural network models. - The method then involves training these new models and selecting the one with the highest precision as the final trained model. - By replacing the convolutional layer with a linear operation, the method aims to improve the precision of the trained model. - The application suggests that this approach can be used to enhance the performance of neural networks in various AI applications.
Original Abstract Submitted
This application discloses a model training method, which may be applied to the field of artificial intelligence. The method includes: obtaining a first neural network model; replacing a first convolutional layer in the first neural network model with a linear operation to obtain a plurality of second neural network models; and performing model training on a plurality of second neural network models, to obtain a neural network model with a highest model precision in a plurality of trained second neural network models. In this application, a convolutional layer in a to-be-trained neural network is replaced with a linear operation equivalent to a convolutional layer. A manner with highest precision is selected from a plurality of replacement manners, to improve precision of a trained model.
