Patent · US Active

Sparse convolutional neural networks

US11061402B2 · kind B2 · utility

3Cited by
1References
16Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 7, 2018
Grant dateJul 13, 2021
Priority date
Expiry dateAug 28, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG05D1/249
  • WIPO fieldControl
  • WIPO sectorInstruments

Abstract

The present disclosure provides systems and methods that apply neural networks such as, for example, convolutional neural networks, to sparse imagery in an improved manner. For example, the systems and methods of the present disclosure can be included in or otherwise leveraged by an autonomous vehicle. In one example, a computing system can extract one or more relevant portions from imagery, where the relevant portions are less than an entirety of the imagery. The computing system can provide the relevant portions of the imagery to a machine-learned convolutional neural network and receive at least one prediction from the machine-learned convolutional neural network based at least in part on the one or more relevant portions of the imagery. Thus, the computing system can skip performing convolutions over regions of the imagery where the imagery is sparse and/or regions of the imagery that are not relevant to the prediction being sought.

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