Patent · US Active

Neural network architecture using control logic determining convolution operation sequence

US11907830B2 · kind B2 · utility

0Cited by
10References
20Claims
0Family size

Assignee

Inventor

Key dates

Filing dateJan 5, 2023
Grant dateFeb 20, 2024
Priority date
Expiry dateJan 5, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/045
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Hardware for implementing a Deep Neural Network (DNN) having a convolution layer. A plurality of convolution engines each perform a convolution operation by applying a filter to a data window. Each of the plurality of convolution engines includes multiplication logic that combines a weight of a filter with a respective data value of a data window; control logic that receives configuration information identifying a set of filters for operation on a set of data windows at the plurality of convolution engines; determines a sequence of convolution operations for evaluation at the multiplication logic; requests weights and data values for at least partially applying a filter to a data window; and causes the multiplication logic to combine the weights with their respective data values. Accumulation logic accumulates the results of a plurality of combinations performed by the multiplication logic to form an output for a convolution operation of the determined sequence.

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