Verfahren und Vorrichtung zur Komprimierung eines Neuronalen Netzwerks, Elektronische Vorrichtung und Flugzeug

Details

Veröffentlichungs-Nr.

EP4783071

Anmeldetag

23. Januar 2025

Veröffentlichung

29. Juli 2026

Rechtsraum

EP

Abstract

Proposed is a method and an apparatus (100) for compressing a neural network. The processing circuitry (110) is configured to receive a neural network comprising a set of parameters being in at least one floating-point number format of a first precision. Further, the processing circuitry (110) is configured to apply at least one mathematical model on the neural network to determine errors introduced by using arithmetic of a second precision lower than the first precision and propagation through network layers of the neural network due to using the arithmetic of the second precision instead of the first precision. The processing circuitry (110) is further configured to apply a solver to an optimization problem formulated based on the errors determined by the at least one mathematical model to determine a set of optimized parameters. Further, the processing circuitry (110) is configured to compress the neural network based on the set of optimized parameters to output a compressed neural network.

Anmelder

Firma

Airbus S.A.S.

Land

🇫🇷 Frankreich