METHOD AND DEVICE WITH NEURAL NETWORK MODEL QUANTIZATION

Abstract: a quantization method for a neural network model is provided. the quantization method includes: determining sensitivities corresponding to one candidate max weight error (mwe) among candidate mwes corresponding to the target layer, the sensitivities sensitivity of the neural network model to quantization; determining a target mwe corresponding to the target layer, based on the sensitivities; and based on the determined target mwe, quantizing weights included in the target layer from a first data format to a second data format.

Inventor(s): Gang SUN, Guoqiang HE, Jun-Woo JANG, Penghui WEI

CPC Classification: G06N3/0495 (Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs)

Search for rejections for patent application number 20250232161