Cadence Design Systems, Inc.
Filtering in trainable networks

Last updated:

Abstract:

Some embodiments perform, in a multi-layer neural network in a computing device, a convolution operation on input feature maps with multiple convolutional filters. The convolutional filters have multiple filter precisions. In other embodiments, electronic design automation (EDA) systems, methods, and computer-readable media are presented for adding such a multi-layer neural network into an integrated circuit (IC) design.

Status:
Grant
Type:

Utility

Filling date:

24 Feb 2017

Issue date:

28 Sep 2021