Adapting Neural Networks for Reduced Power Consumption on Multiplier Circuits

ChangeBridge: EPO Bulletin - AI & Computing (G06N)

Published March 25th, 2026

Detected April 2nd, 2026

Summary

The European Patent Office published patent EP4713800A1, filed by Google LLC, covering techniques for adapting neural networks to reduce power consumption in multiplier circuits. Inventors SCHMIT and YAZDANBAKHSH developed methods for optimizing neural network processing on hardware-level circuits. The patent is designated across 31 European states including major markets DE, FR, GB, IT, NL, ES.

View original document View source feed page

What changed

EPO published patent EP4713800A1, a patent application by Google LLC for methods and systems adapting neural networks to achieve reduced power consumption in multiplier circuits. The patent, classified under G06N 3/00 (AI) and G06F 16/907 (computing), names inventors SCHMIT, Herman Henry and YAZDANBAKHSH, Amir. The filing covers technical implementations for optimizing neural network hardware efficiency.

Technology companies developing AI hardware and semiconductor manufacturers should review this patent for awareness of Google's IP position in power-efficient neural network processing. Patent publications do not impose compliance obligations but establish intellectual property rights that may affect future product development decisions in the designated European states.

Source document (simplified)

← EPO Patent Bulletin

ADAPTING NEURAL NETWORKS FOR REDUCED POWER CONSUMPTION ON MULTIPLIER CIRCUITS

Publication EP4713800A1 Kind: A1 Mar 25, 2026

Applicants

Google LLC

Inventors

SCHMIT, Herman Henry, YAZDANBAKHSH, Amir

IPC Classifications

G06F 16/903 20190101AFI20250111BHEP G06F 16/907 20190101ALI20250111BHEP G06N 3/00 20230101ALI20250111BHEP

Designated States

AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LI, LT, LU, LV, MC, ME, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR

View original document →