Patent · US Active

Neural associative memories based on optimal bayesian learning

US8521669B2 · kind B2 · utility

40Cited by

0References

16Claims

0Family size

Assignee

Honda Research Institute Europe GmbH · DE

Inventor

Andreas Knoblauch · Munich, DE

Key dates

Filing date	May 28, 2010
Grant date	Aug 27, 2013
Priority date	—
Expiry date	Jan 11, 2032

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/09
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

This invention is in the field of machine learning and neural associative memory. In particular the invention discloses a neural associative memory structure for storing and maintaining associations between memory address patterns and memory content patterns using a neural network, as well as methods for storing and retrieving such associations. Bayesian learning is applied to achieve non-linear learning.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.