Jump to content

20250232000. Geometric Deep Learning (QUALCOMM Incorporated)

From WikiPatents

GEOMETRIC DEEP LEARNING FOR LATTICE REDUCTION

Abstract: certain aspects of the present disclosure provide techniques for wireless communications by an apparatus. certain techniques include providing a first gram matrix to a neural lattice reduction model; generating, with the neural lattice reduction model, one or more partial changed bases; and generating a first reduced basis based on the one or more partial changed bases.

Inventor(s): Giovanni Luca MARCHETTI, Gabriele CESA, Kumar PRATIK, Arash BEHBOODI

CPC Classification: G06F17/11 (for solving equations {, e.g. nonlinear equations, general mathematical optimization problems (optimization specially adapted for a specific administrative, business or logistic context )})

Search for rejections for patent application number 20250232000


Cookies help us deliver our services. By using our services, you agree to our use of cookies.