MUMBAI, India, Aug. 12 -- Intellectual Property India has published a patent application (202638024762 A) filed by Fraunhofer-Gesellschaft Zur Frderung Der on March 02, 2026, for Improved Concept For A Representation Of Neural Network Parameters.

Inventors include Wiedemann, Simon; Marinc, Talmaj; Samek, Wojciech; Haase, Paul; Mller, Karsten; Kirchhoffer, Heiner; Marpe, Detlev Filed On; Schwarz, Heiko; and Wiegand, Thomas.

The application for the patent was published on August 07, 2026, under issue no. 32/2026.

Abstract: Apparatus for generating a NN representation, configured to quantize an NN parameter onto a quantized value by determining a quantization parameter and a quantization value for the NN parameter so that from the quantization parameter, there is derivable a multiplier and a bit shift number. Additionally, the determining of the quantization parameter and the quantization value for the NN parameter is performed so that the quantized value of the NN parameter corresponds to a product between the quantization value and a factor, which depends on the multiplier, bit-shifted by a number of bits which depends on the bit shift number.

Disclaimer: Curated by HT Syndication.