公开(公告)号：US20240220770A1

公开(公告)日：2024-07-04

申请号：US18387463

申请日：2023-11-07

Applicant: SHANGHAITECH UNIVERSITY

Inventor： Shen ZHANG ,  Xinzhe LIU ,  Yajun HA

IPC: G06N3/04 ,  G06N5/04 ,  G06N7/01

CPC classification number: G06N3/04 ,  G06N5/04 ,  G06N7/01

Abstract: A high-efficient quantization method for a deep probabilistic network achieves good result through hybrid quantization, structure reformulation, and type optimization. Firstly, for a directed acyclic graph (DAG) structure, all nodes in the DAG are clustered, and each node is quantized by a specific arithmetic type based on the clustering category, to obtain a preliminarily quantized deep probabilistic network. Secondly, the multi-in nodes in a preliminarily quantized deep probabilistic network are reformulated based on the input weights, structural reformulation converts a multi-in node into a binary tree network containing only two-input nodes, and parametrical reformulation is performed on the reformulated structure. Finally, arithmetic types of all nodes are optimized by using an arithmetic type search method based on power consumption analysis and network accuracy analysis. The method can significantly reduce computational complexity and energy consumption for computing while maintaining model accuracy of the deep probabilistic network.