Patent · US Active

Neural network apparatus, vehicle control system, decomposition device, and program

US11657267B2 · kind B2 · utility

0Cited by
4References
7Claims
0Family size

Assignee

Inventor

Key dates

Filing dateJul 20, 2017
Grant dateMay 23, 2023
Priority date
Expiry dateSep 17, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/063
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A neural network apparatus (20) includes a storage unit (24) storing a neural network model, and an arithmetic unit (22) inputting input information into an input layer of the neural network and outputting an output layer. A weight matrix (W) of an FC layer of the neural network model is constituted by a product of a weight basis matrix (Mw) of integers and a weight coefficient matrix (Cw) of real numbers. In the FC layer, the arithmetic unit (22) uses an output vector from a previous layer as an input vector (x) to decompose the input vector (x) into a product of a binary input basis matrix (Mx) and an input coefficient vector (cx) of real numbers and an input bias (bx) and derives a product of the input vector (x) and a weight matrix (W).

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