FEATURE MAP CACHING METHOD OF CONVOLUTIONAL NEURAL NETWORK AND SYSTEM THEREOF

Patent №

US 11,782,839

Granted

2023-10-10

Filed 2019

Owner

NATIONAL TSING HUA UNIVERSITY

+1 more

Lab

AI components

3

ml · kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16543645

A feature map caching method of a convolutional neural network includes a connection analyzing step and a plurality of layer operation steps. The connection analyzing step is for analyzing a network to establish a convolutional neural network connection list. The convolutional neural network connection list includes a plurality of tensors and a plurality of layer operation coefficients. Each of the layer operation coefficients includes a step index, at least one input operand label and an output operand label. The step index as a processing order for the layer operation step. At least one of the layer operation steps is for flushing at least one of the tensors in a cache according to a distance between the at least one of the layer operation steps and a future layer operation step of the layer operation steps. The distance is calculated according to the convolutional neural network connection list.

Machine learningKnowledge representationAI hardwareG06F 12/0871G06F 5/06G06F 12/0875G06F 12/0893G06N 3/04G06N 3/045G06N 3/0464G06N 3/063+4 more

AI classification

Machine learning1.00
AI hardware0.93
Knowledge representation0.60
Vision0.24
Speech0.00
Planning0.00
Natural language0.00
Evolutionary computation0.00

Ownership

NATIONAL TSING HUA UNIVERSITY

assignment · 500940097

NEUCHIPS CORPORATION

assignment · 524720473

Assignors

CHAO, PING, KAO, CHAO-YANG, LIN, YOUN-LONG

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC