首页> 外文会议>Machine learning >On-Line Adaptation of a Signal Predistorter through Dual Reinforcement Learning

【24h】

On-Line Adaptation of a Signal Predistorter through Dual Reinforcement Learning

机译：通过双重强化学习对信号预失真器进行在线自适应

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Several researchers have demonstrated how neural networks can be trained to compensate for nonlinear signal distortion in e.g. digital satellite communications systems. These networks, however, require that both the original signal and its distorted version are known. Therefore, they have to be trained off-line, and they cannot adapt to changing channel characteristics. In this paper, a novel dual reinforcement learning approach is proposed that can adapt on-line while the system is performing. Assuming that the channel characteristics are the same in both directions, two predistorters at each end of the communication channel cc-adapt using the output of the other predistorter to determine their own reinforcement. Using the common Volterra Series model to simulate the channel, the system is shown to successfully learn to compensate for distortions up to 30%, which is significantly higher than what might be expected in an actual channel.

机译：几位研究人员证明了如何训练神经网络来补偿非线性信号失真，例如数字卫星通信系统。但是，这些网络要求原始信号及其失真的版本都已知。因此，它们必须脱机训练，并且它们不能适应变化的信道特性。本文提出了一种新颖的双重强化学习方法，该方法可以在系统运行时进行在线适应。假设信道特性在两个方向上都相同，则通信信道cc-adapt两端的两个预失真器将使用另一个预失真器的输出来确定它们自己的增强。使用通用的Volterra系列模型来模拟通道，系统可以成功学会补偿高达30％的失真，该失真大大高于实际通道中的预期失真。

著录项

来源
《Machine learning》|1996年|175-181|共8页
会议地点 Bari(IT);Bari(IT)
作者
Patrick Goetz; Shailesh Kumar; Risto Miikkulainen;
展开▼
作者单位

Computational and Applied Math The University of Texas at Austin Austin, TX 78712 USA;

Department of Computer Sciences The University of Texas at Austin Austin, TX 78712 USA;

Department of Computer Sciences The University of Texas at Austin Austin, TX 78712 USA;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类计算机的应用;
关键词

相似文献

外文文献
中文文献
专利

1. Multi-agent reinforcement learning-based approach for controlling signals through adaptation [J] . Mohammed Tahifa, Jaouad Boumhidi, Ali Yahyaouy International journal of autonomous and adaptive communications systems . 2018,第2期

机译：基于多主体强化学习的方法，通过自适应控制信号
2. Reinforcement learning in learning automata and cellular learning automata via multiple reinforcement signals [J] . Vafashoar Reza, Meybodi Mohammad Reza Knowledge-Based Systems . 2019,第APRa1期

机译：通过多个增强信号学习自动机和细胞学习自动机中的增强学习
3. On-line anxiety level detection from biosignals: Machine learning based on a randomized controlled trial with spider-fearful individuals [J] . Frank R. Ihmig, Antonio Gogeascoechea H., Frank Neurohr-Parakenings, PLoS One . 2020,第6期

机译：生物可爱的在线焦虑水平检测：基于随机对照试验的机器学习与蜘蛛恐惧的个人
4. On-line Incremental Adaptation Based on Reinforcement Learning for Robust Speech Recognition [C] . Masafumi Nishida, Yoshitaka Mamiya, Yasuo Horiuchi, International Conference on Spoken Language Processing; 20041004-08; Jeju(KR) . 2004

机译：基于强化学习的在线增量自适应以实现鲁棒语音识别
5. Evidence for Reinforcement Learning Signals in the Climbing Fiber Pathway Expands the Possible Repertoire of Cerebellar Learning Rules [D] . Heffley, William, II. 2019

机译：攀岩光纤途径中加固学习信号的证据扩大了可能的大脑学习规则的曲目
6. A multiplicative reinforcement learning model capturing learning dynamics and interindividual variability in mice [O] . Brice Bathellier, Sui Poh Tee, Christina Hrovat, 2013

机译：捕获小鼠学习动态和个体差异的乘法强化学习模型
7. On-line Building Energy Optimization using Deep Reinforcement Learning [O] . Mocanu, Elena, Mocanu, Decebal Constantin, Nguyen, Phuong H., 2017

机译：基于深度强化学习的在线建筑能量优化

On-Line Adaptation of a Signal Predistorter through Dual Reinforcement Learning

摘要

著录项

相似文献

相关主题

期刊订阅