SYSTEM AND METHOD FOR COMPILING A TRAINED ARTIFICIAL NEURAL NETWORK

Number of patents in Portfolio can not be more than 2000

United States of America

APP PUB NO 20250117651A1
SERIAL NO

18910448

Stats

ATTORNEY / AGENT: (SPONSORED)

Importance

Loading Importance Indicators... loading....

Abstract

See full text

According to one aspect, a computer-implemented method compiles a first trained artificial neural network comprising at least one succession of layers including a depthwise convolutional layer, a saturated rectified linear unit layer, and a two-dimensional convolutional layer. The method comprises equalizing between layers, replacing the saturated rectified linear unit layer with an adaptive channel pruning layer to obtain an artificial neural network with a modified topology, tensor quantizing the layers of the artificial neural network with the modified topology, and compiling the quantized artificial neural network with the modified topology.

Loading the Abstract Image... loading....

First Claim

See full text

Family

Loading Family data... loading....

Patent Owner(s)

Patent OwnerAddress
STMICROELECTRONICS (ROUSSET) SASZI DE PEYNIER-ROUSSET AVENUE COQ ROUSSET 13790

International Classification(s)

  • [Classification Symbol]
  • [Patents Count]

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Demaj, Pierre Nice, FR 47 90
Folliot, Laurent Gourdon, FR 25 14

Cited Art Landscape

Load Citation

Patent Citation Ranking

Forward Cite Landscape

Load Citation