Huawei Technologies Co., Limited

Mohan Liu

Li Zhou

Renzhi Yang

Jiyong Jiang

Qinghua Yu

Zhicheng Sui

Tao Fan

Hongrui Jiang

Lei Zhao

Xiyong Wang

Kang Sun

Lixun Bai

This application relates to the field of artificial intelligence technologies, and discloses a machine learning model search method, a related apparatus, and a device. In the method, before model search and quantization, a plurality of single bit models are generated based on a to-be-quantized model, and evaluation parameters of layer structures in the plurality of single bit models are obtained. Further, after a candidate model selected from a candidate set is trained and tested, to obtain a target model, a quantization weight of each layer structure in the target model may be determined based on a network structure of the target model and evaluation parameters of all layer structures in the target model, a layer structure with a maximum quantization weight in the target model is quantized, and a model obtained through quantization is added to the candidate set.

Machine learning model search method, related apparatus, and device

A neural network model processing method includes obtaining a first low-bit neural network model through training, where the model includes a first operation layer and a second operation layer. Each operation layer includes at least one operation. Values/a value of a parameter and/or data used for the operation are/is represented by using N bits, and N is a positive integer less than 8. The neural network model processing method further includes compressing the model to obtain a second low-bit neural network model, where the compressed model includes a third operation layer. The third operation layer is equivalent to the first operation layer and the second operation layer, and an operation layer other than the third operation layer in the at least one operation layer is the same as an operation layer other than the first operation layer and the second operation layer in the at least two operation layers.

Neural network model processing method and apparatus

This application discloses a notification display method. The method comprises: when there is a to-be-notified event, displaying, by a terminal, a notification by classification based on a notification type of the notification corresponding to the to-be-notified event; and displaying, by the terminal, in different display modes based on a priority of the notification, wherein the different display modes comprise: displaying in expanded form or displaying in collapsed form in the corresponding display pane, or the different display modes comprise: displaying in a first mode or displaying in a second mode in the corresponding display pane, and content displayed in the first mode is more than content displayed in the second mode.

Notification display method and terminal

A recommendation method applied to a terminal includes a rule platform with system-level permission, the rule platform is configured to save system resources and remind a user of a function of an application. The rule platform obtains a first event and a first rule related to the first event from a rule base. The rule platform includes the rule base including a rule and each rule includes a condition. The rule platform updates a matching status of a first condition corresponding to the first event in the first rule The terminal displays a recommendation result corresponding to the first rule when a matching status of each condition in the first rule indicates that the matching is successful. The first rule is one of the rule related to the first event.

Recommendation method and terminal

Growing community of inventors

Shanghai, China

Mohan Liu