ACCELERATION OF NEURAL NETWORKS USING DEPTH-FIRST PROCESSING

Patent №

US 11,429,855

Granted

2022-08-30

Filed 2018

Owner

NEC LABORATORIES EUROPE GMBH

+1 more

Lab

AI components

3

ml · kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

15889275

A method for accelerating a neural network includes identifying neural network layers that meet a locality constraint. Code is generated to implement depth-first processing for different hardware based on the identified neural network layers. The generated code is used to perform the depth-first processing on the neural network based on the generated code.

AI classification

AI hardware1.00
Machine learning1.00
Knowledge representation0.98
Vision0.17
Planning0.01
Natural language0.01
Speech0.00
Evolutionary computation0.00

Ownership

NEC LABORATORIES EUROPE GMBH

assignment · 449840219

NEC CORPORATION

assignment · 605410807

Assignors

WEBER, NICOLAS, HUICI, FELIPE, NIEPERT, MATHIAS

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

© 2026 NYSGPT2525 LLC