Patent · US Active

Weights safety mechanism in an artificial neural network processor

US11811421B2 · kind B2 · utility

2Cited by
121References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 29, 2020
Grant dateNov 7, 2023
Priority date
Expiry dateJun 8, 2042

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH03M13/15
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Novel and useful system and methods of several functional safety mechanisms for use in an artificial neural network (ANN) processor. The mechanisms can be deployed individually or in combination to provide a desired level of safety in neural networks. Multiple strategies are applied involving redundancy by design, redundancy through spatial mapping as well as self-tuning procedures that modify static (weights) and monitor dynamic (activations) behavior. The mechanisms address ANN system level safety in situ, as a system level strategy tightly coupled with the processor architecture. The NN processor incorporates several functional safety concepts that function to detect and promptly flag and report an error with some mechanisms capable of correction as well. The safety mechanisms cover data stream fault detection, software defined redundant allocation, cluster interlayer safety, cluster intralayer safety, layer control unit (LCU) instruction addressing, weights storage safety, and neural network intermediate results storage safety.

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