US 12,306,870 B2Granted

Set of resonator networks for factorizing hyper vectors

AssigneeInternational Business Machines Corporation

InventorAbbas Rahimi

Life of this patent

Estimating the term…

Loading patent…

Abstract

The present disclosure relates to a resonator network system comprising a set of resonator networks, each resonator network being configured to execute a resonator network, the resonator network being configured to receive an input hypervector representing a data structure and to perform an iterative process in order to factorize the input hypervector into individual hypervectors representing a set of concepts respectively, the set of N resonator networks being associated with N permutations respectively. The resonator network system being configured for applying the N permutations to N first hypervectors respectively, the N first hypervectors representing a set of N data structures respectively; and combining the N permuted hypervectors into a bundled hypervector. The resonator networks being configured for processing the bundled hypervector respectively, thereby factorizing the first hypervectors.

Claims16

Dependent claims

A method comprising:

providing an encoder for representing data structures in a vector space, the vector space being defined by a set of codebooks, which encode a set of cognitive concepts respectively, the codebooks comprising candidate code hypervectors representing items of the respective cognitive concepts;
providing a set of N resonator networks, where N>1, each resonator network being configured to receive an input hypervector representing a data structure and to perform an iterative process in order to factorize the input hypervector into individual hypervectors representing the set of cognitive concepts respectively utilizing superposition and clean-up memory, the set of N resonator networks being associated with N permutations respectively;
representing using the encoder a set of N data structures by N first hypervectors respectively;
applying the N permutations to the N first hypervectors respectively;
combining the N permuted hypervectors into a bundled hypervector;
and
processing the bundled hypervector by the resonator networks, thereby simultaneously factorizing the N first hypervectors.

4 more elements

A resonator network system comprising:

a set of resonator networks, each resonator network being configured to receive an input hypervector representing a data structure and to perform an iterative process in order to factorize the input hypervector into individual hypervectors representing a set of cognitive concepts respectively utilizing superposition and clean-up memory, the set of N resonator networks being associated with N permutations respectively;
the resonator network system being configured for applying the N permutations to N first hypervectors respectively, the N first hypervectors representing a set of N data structures respectively;
and combining the N permuted hypervectors into a bundled hypervector;
and
the resonator networks being configured for processing the bundled hypervector, thereby simultaneously factorizing the N first hypervectors.

2 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/658,536Filed 8 Apr 2022
Published: US 2023/0325435 A112 Oct 2023
Granted: 20 May 2025
Term ends: Not estimatedThe source records don’t support an estimate.

Classification16 codes

G06F 16/56
Of still image data: having vectorial format
G06F 16/55
Of still image data: clustering; Classification
G06F 17/11
Complex mathematical operations: for solving equations , e.g. nonlinear equations, general mathematical optimization problems
G06F 17/16
Complex mathematical operations: matrix or vector computation , e.g. matrix-matrix or matrix-vector multiplication, matrix factorization