Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022072979 - QUANTIZED FEEDBACK IN FEDERATED LEARNING WITH RANDOMIZATION

Publication Number WO/2022/072979
Publication Date 07.04.2022
International Application No. PCT/US2021/071545
International Filing Date 22.09.2021
IPC
G06N 3/04 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G06N 3/08 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 3/063 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
06Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
063using electronic means
CPC
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/063
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
06Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
063using electronic means
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
H04L 67/01
Applicants
  • QUALCOMM INCORPORATED [US]/[US]
Inventors
  • TAHERZADEH BOROUJENI, Mahmoud
  • YOO, Taesang
  • LUO, Tao
  • PEZESHKI, Hamed
Agents
  • SPECTOR, Elaine P.
  • HARRITY, John E.
  • HARRITY, Paul A.
  • GURZO, Paul M.
Priority Data
17/448,29821.09.2021US
63/085,74830.09.2020US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) QUANTIZED FEEDBACK IN FEDERATED LEARNING WITH RANDOMIZATION
(FR) RÉTROACTION QUANTIFIÉE DANS UN APPRENTISSAGE FÉDÉRÉ AVEC RANDOMISATION
Abstract
(EN) Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a client device may determine a feedback associated with a machine learning component based at least in part on applying the machine learning component. Accordingly, the client device may transmit a quantized value based at least in part on the feedback. The quantized value is determined using randomization with probabilities based at least in part on respective distances between one or more values of the feedback and a plurality of quantized digits. Numerous other aspects are provided.
(FR) Divers aspects de la présente divulgation portent d'une manière générale sur la communication sans fil. Selon certains aspects, un dispositif client peut déterminer une rétroaction associée à un composant d'apprentissage automatique sur la base, au moins en partie, de l'application du composant d'apprentissage automatique. En conséquence, le dispositif client peut transmettre une valeur quantifiée sur la base, au moins en partie, de la rétroaction. La valeur quantifiée est déterminée à l'aide d'une randomisation avec des probabilités basées au moins en partie sur des distances respectives entre une ou plusieurs valeurs de la rétroaction et une pluralité de chiffres quantifiés. La divulgation concerne également de nombreux autres aspects.
Related patent documents
Latest bibliographic data on file with the International Bureau