NEURAL ARCHITECTURE SEARCH METHOD AND APPARATUS

WIPO Patent Application WO/2022/063247

A1

A neural architecture search method and apparatus, which relate to the field of AI and can use a small amount of computing resources to determine, in a short time, a neural network architecture with an excellent performance, while the consistency between a theoretical time delay and a true time delay is ensured. The method comprises: obtaining a super-network according to a target task; obtaining a time delay of each deep learning operator in the super-network running on an electronic device; determining a time-delay loss function according to the time delay of each deep learning operator running on the electronic device; executing a training operation on the super-network, and updating a model parameter of the super-network according to the time-delay loss function and a network loss function until an updated super-network satisfies a condition for the target task to run on the electronic device; and determining a target neural network architecture according to an updated framework parameter of each network layer, wherein the super-network comprises a plurality of network layers, each network layer comprises a plurality of nodes, any two nodes of a network layer are connected to each other by means of a deep learning operator, and the model parameter comprises a framework parameter of each network layer.

LI MINGYANG (CN)
ZHOU ZHENKUN (CN)
XU YUQIONG (CN)

PCT/CN2021/120434

March 31, 2022

September 24, 2021

Click for automatic bibliography generation  

HUAWEI TECH CO LTD (CN)

G06N3/08

WO2020188658A1

2020-09-24

CN111428854A	2020-07-17
CN111353601A	2020-06-30
CN111325338A	2020-06-23

BEIJING ZBSD PATENT&TRADEMARK AGENT LTD. (CN)

View/Download PDF      PDF Help

Previous Patent: POSITION ASSURANCE APPARATUS, CONNECTOR ASSEMBLY, BATTERY, AND ELECTRICAL APPARATUS

Next Patent: A DETECTOR BOX