Method and device for operating a neural network in a memory-efficient manner

US11715019B2 · kind B2 · utility

Assignee

• Robert Bosch GmbH · DE

Inventors

• Andre Guntoro · Weil der Stadt, DE
• Armin Runge · Heidingsfeld, DE
• Christoph Schorn · Leonberg, DE
• Jaroslaw Topp
• Sebastian Vogel · Schaidt, DE
• Juergen Schirmer · Heidelberg, DE

Key dates

• Filing date: Mar 11, 2019
• Grant date: Aug 1, 2023
• Expiry date: Feb 11, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/063
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A method for operating a calculation system including a neural network, in particular a convolutional neural network, the calculation system including a processing unit for the sequential calculation of the neural network and a memory external thereto for buffering intermediate results of the calculations in the processing unit, including: incrementally calculating data sections, which each represent a group of intermediate results, with the aid of a neural network; lossy compression of one or multiple of the data sections to obtain compressed intermediate results; and transmitting the compressed intermediate results to the external memory.