Title:
PROCESSING ARCHITECTURE FOR FUNDAMENTAL SYMBOLIC LOGIC OPERATIONS AND METHOD FOR EMPLOYING THE SAME
Document Type and Number:
WIPO Patent Application WO/2024/072483
Kind Code:
A3
Abstract:
This invention provides a system and method for processing data that includes a processor arrangement adapted to handle rich multivariate relational data from sensors or a database in which the relations are implicit. The processor arrangement can be adapted to learn composable part-whole and part-part relations from data, and matches against new data. The relations are composable into symbols of value for distinguishing or associating datapoints, and the symbols can correlate with business and personal use cases, and more particularly hand-written digits or a credit score. Operations of the processor can be defined by a formality, such as Hamiltonian Compositional Logic Networks (HNet). The operations can compare each input to a data model, stored in component parameters and connectivity. Also, operations can be carried out via extremely low-precision processing. Hamiltonians can be implicit, explicit, and/or exact. The processor can perform learning operations that are symbolic, local and free of gradients.
Inventors:
GRANGER RICHARD (US)
RODRIGUEZ ANTONIO (US)
BOWEN ELIJAH (US)
RODRIGUEZ ANTONIO (US)
BOWEN ELIJAH (US)
Application Number:
PCT/US2023/016336
Publication Date:
May 10, 2024
Filing Date:
March 24, 2023
Export Citation:
Assignee:
THE TRUSTEES OF DARTMOUTH COLLEGE (US)
International Classes:
G06V10/42; G06F17/10; G06N20/00; G06V10/44; G06V10/77; G06V10/82; G06V30/18
Attorney, Agent or Firm:
LOGINOV, William, A. (PLLCP.O. Box 710, Sheridan WY, US)
Download PDF:
Previous Patent: PRINT SETTING CUSTOMIZATION OF PRINTER DRIVER
Next Patent: AUDIO AMPLIFICATION SYSTEMS, DEVICES AND METHODS
Next Patent: AUDIO AMPLIFICATION SYSTEMS, DEVICES AND METHODS