公开(公告)号：US11461635B2

公开(公告)日：2022-10-04

申请号：US16153018

申请日：2018-10-05

Applicant: NEC Laboratories America, Inc.

Inventor： Yue-Kai Huang ,  Shaoliang Zhang ,  Ezra Ip ,  Weiyang Mo

IPC: G06N3/08 ,  H04B10/556 ,  G06N3/04 ,  H04B10/077 ,  H04B10/54

Abstract: Systems and methods for predicting performance of a modulation system are provided. A neural network model is trained using performance information of a source system. The neural network model is modified with transferable knowledge about a target system to be evaluated. The neural network model is tuned using specific characteristics of the target system to create a source-based target model. The target system performance is evaluated using the source-based target model to predict system performance of the target system.

公开(公告)号：US20190109736A1

公开(公告)日：2019-04-11

申请号：US16153051

申请日：2018-10-05

Applicant: NEC Laboratories America, Inc. ,  NEC Corporation

Inventor： Fatih Yaman ,  Shaoliang Zhang ,  Eduardo Mateo Rodriguez ,  Yoshihisa Inada ,  Yue-Kai Huang ,  Weiyang Mo

IPC: H04L25/03 ,  H04B10/079 ,  G06N3/08

Abstract: Systems and methods for transmission filtering are provided. A receiver includes an input coupled to a transmission line to receive distorted optical symbols. A distortion filter is coupled to the input to replace the distorted optical symbols with predicted symbols using a trained neural network. A decoder is coupled to the distortion filter to decode the predicted symbols.

公开(公告)号：US20190108445A1

公开(公告)日：2019-04-11

申请号：US16153018

申请日：2018-10-05

Applicant: NEC Laboratories America, Inc.

Inventor： Yue-Kai Huang ,  Shaoliang Zhang ,  Ezra Ip ,  Weiyang Mo

IPC: G06N3/08

Abstract: Systems and methods for predicting performance of a modulation system are provided. A neural network model is trained using performance information of a source system. The neural network model is modified with transferable knowledge about a target system to be evaluated. The neural network model is tuned using specific characteristics of the target system to create a source-based target model. The target system performance is evaluated using the source-based target model to predict system performance of the target system.

公开(公告)号：US10708094B2

公开(公告)日：2020-07-07

申请号：US16153051

申请日：2018-10-05

Applicant: NEC Laboratories America, Inc. ,  NEC Corporation

Inventor： Fatih Yaman ,  Shaoliang Zhang ,  Eduardo Mateo Rodriguez ,  Yoshihisa Inada ,  Yue-Kai Huang ,  Weiyang Mo

IPC: H04L25/03 ,  G06N3/08 ,  H04B10/079 ,  H04B10/2513 ,  H04B10/2507 ,  H04B10/69

Abstract: Systems and methods for transmission filtering are provided. A receiver includes an input coupled to a transmission line to receive distorted optical symbols. A distortion filter is coupled to the input to replace the distorted optical symbols with predicted symbols using a trained neural network. A decoder is coupled to the distortion filter to decode the predicted symbols.