Patent · US Active

Machine learning through multiple layers of novel machine trained processing nodes

US10867247B1 · kind B1 · utility

4Cited by
4References
15Claims
0Family size

Assignee

Inventor

Key dates

Filing dateAug 9, 2016
Grant dateDec 15, 2020
Priority date
Expiry dateJul 14, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/048
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Some embodiments of the invention provide efficient, expressive machine-trained networks for performing machine learning. The machine-trained (MT) networks of some embodiments use novel processing nodes with novel activation functions that allow the MT network to efficiently define with fewer processing node layers a complex mathematical expression that solves a particular problem (e.g., face recognition, speech recognition, etc.). In some embodiments, the same activation function (e.g., a cup function) is used for numerous processing nodes of the MT network, but through the machine learning, this activation function is configured differently for different processing nodes so that different nodes can emulate or implement two or more different functions (e.g., two or more Boolean logical operators, such as XOR and AND). The activation function in some embodiments is a periodic function that can be configured to implement different functions (e.g., different sinusoidal functions).

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