Neural Network Parameter Quantization Method and Apparatus

Organization Name

huawei technologies co., ltd.

Inventor(s)

Ying Nie of Beijing CN

Kai Han of Beijing CN

Chuanjian Liu of Beijing CN

Junhui Ma of Shenzhen CN

Yunhe Wang of Beijing CN

Neural Network Parameter Quantization Method and Apparatus

This abstract first appeared for US patent application 20250117637 titled 'Neural Network Parameter Quantization Method and Apparatus

Original Abstract Submitted

a neural network parameter quantization method includes obtaining a parameter of each neuron in a to-be-quantized model to obtain a parameter set, clustering parameters in the parameter set to obtain types of classified data, and quantizing each type of classified data in the types of classified data to obtain at least one type of quantization parameter, where the at least one type of quantization parameter is used to obtain a compression model, and precision of the at least one type of quantization parameter is lower than precision of a parameter in the to-be-quantized model.