US Patent Application 17752203. SYSTEM AND METHOD FOR AUTOMATED CATALOGING AND BUILDING MACHINE LEARNING MODELS simplified abstract

From WikiPatents
Jump to navigation Jump to search

SYSTEM AND METHOD FOR AUTOMATED CATALOGING AND BUILDING MACHINE LEARNING MODELS

Organization Name

AT&T Intellectual Property I, L.P.

Inventor(s)

Mukundan Sarukkai of Manalapan NJ (US)

Eshrat Huda of Hillsborough NJ (US)

SYSTEM AND METHOD FOR AUTOMATED CATALOGING AND BUILDING MACHINE LEARNING MODELS - A simplified explanation of the abstract

This abstract first appeared for US patent application 17752203 titled 'SYSTEM AND METHOD FOR AUTOMATED CATALOGING AND BUILDING MACHINE LEARNING MODELS

Simplified Explanation

The patent application describes a device with a processing system and memory that stores instructions for performing operations related to machine learning models.

  • The device selects a first building block pattern function (bbDNA) from a catalog based on certain criteria.
  • The first bbDNA is associated with at least one machine learning model.
  • The device also selects a second bbDNA from the catalog, which is associated with another machine learning model.
  • The device then creates a new machine learning model by combining the first and second bbDNA.
  • The patent application also mentions other embodiments and variations of the invention.


Original Abstract Submitted

Aspects of the subject disclosure may include, for example, a device having a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, including: selecting a first building block pattern function (bbDNA) having a first weight from a catalog, wherein the first bbDNA is based on a first mature pattern reaching a first bbDNA frequency threshold, wherein the first bbDNA is associated with at least one machine learning (ML) model of a plurality of ML models; selecting a second bbDNA having a second weight from the catalog, wherein the second bbDNA is associated with at least one ML model in the plurality of ML models; and creating a new ML model based on a combination of the first bbDNA and the second bbDNA. Other embodiments are disclosed.