公开(公告)号：US11620804B2

公开(公告)日：2023-04-04

申请号：US17834269

申请日：2022-06-07

Applicant: X Development LLC

Inventor： Jie Jacquot ,  Hongxu Ma ,  Allen Richard Zhao ,  Vadim Tschernezki ,  Ronald Votel

IPC: G06V10/143 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06T3/40 ,  G06V10/40 ,  G10L15/16 ,  G06V10/58

Abstract: Methods, systems, apparatus, and computer-readable media for data band selection using machine learning. In some implementations, image data comprising information for each of multiple wavelength bands is obtained. A multi-layer neural network is trained using the image data to perform one or more classification or regression tasks. A proper subset of the wavelength bands is selected based on parameters of a layer of the trained multi-layer neural network, where the parameters were determined through training of the multi-layer neural network using the image data. Output is provided indicating that the selected wavelength bands are selected for the one or more classification or regression tasks.

公开(公告)号：US20220383606A1

公开(公告)日：2022-12-01

申请号：US17834269

申请日：2022-06-07

Applicant: X Development LLC

Inventor： Jie Jacquot ,  Hongxu Ma ,  Allen Richard Zhao ,  Vadim Tschernezki ,  Ronald Votel

IPC: G06V10/143 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06T3/40 ,  G06V10/40

Abstract: Methods, systems, apparatus, and computer-readable media for data band selection using machine learning. In some implementations, image data comprising information for each of multiple wavelength bands is obtained. A multi-layer neural network is trained using the image data to perform one or more classification or regression tasks. A proper subset of the wavelength bands is selected based on parameters of a layer of the trained multi-layer neural network, where the parameters were determined through training of the multi-layer neural network using the image data. Output is provided indicating that the selected wavelength bands are selected for the one or more classification or regression tasks.

公开(公告)号：US20210374448A1

公开(公告)日：2021-12-02

申请号：US16887037

申请日：2020-05-29

Applicant: X Development LLC

Inventor： Jie Jacquot ,  Hongxu Ma ,  Allen Richard Zhao ,  Vadim Tschernezki ,  Ronald Votel

IPC: G06K9/20 ,  G06K9/62 ,  G06T3/40 ,  G06K9/46 ,  G06N3/04 ,  G06N3/08

Abstract: Methods, systems, apparatus, and computer-readable media for data band selection using machine learning. In some implementations, image data comprising information for each of multiple wavelength bands is obtained. A multi-layer neural network is trained using the image data to perform one or more classification or regression tasks. A proper subset of the wavelength bands is selected based on parameters of a layer of the trained multi-layer neural network, where the parameters were determined through training of the multi-layer neural network using the image data. Output is provided indicating that the selected wavelength bands are selected for the one or more classification or regression tasks.