Echo State Network with Adversarial Training

机译：回声州网络对抗训练

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Reservoir Computing (RC) is a high-speed machine learning framework for temporal data processing. Especially, the Echo State Network (ESN), which is one of the RC models, has been successfully applied to many temporal tasks. However, its prediction ability depends heavily on hyperparameter values. In this work, we propose a new ESN training method inspired by Generative Adversarial Networks (GANs). Our method intends to minimize the difference between the distribution of teacher data and that of generated samples, and therefore we can generate samples that reflect the dynamics in the teacher data. We apply a feedforward neural network as a discriminator so that we don't need to use backpropagation through time in training. We justify the effectiveness of the proposed method in time series prediction tasks.

机译：储层计算（RC）是用于时态数据处理的高速机器学习框架。尤其是，作为RC模型之一的Echo State Network（ESN）已成功应用于许多时间任务。但是，其预测能力在很大程度上取决于超参数值。在这项工作中，我们提出了一种受创对抗网络（GANs）启发的新的ESN培训方法。我们的方法旨在最小化教师数据分布与生成的样本之间的差异，因此，我们可以生成反映教师数据动态的样本。我们将前馈神经网络用作判别器，因此我们无需在训练中随时间使用反向传播。我们证明了该方法在时间序列预测任务中的有效性。

著录项

来源
《International conference on artificial neural networks》|2019年|82-88|共7页
会议地点
作者
Takanori Akiyama; Gouhei Tanaka;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Echo State Network; Recurrent Neural Network; Generative Adversarial Network; Nonlinear time series prediction;

机译：回声状态网;递归神经网络生成对抗网络;非线性时间序列预测;

相似文献

外文文献
中文文献
专利

1. Robust Graph Neural Networks Against Adversarial Attacks via Jointly Adversarial Training [J] . Hu Tian, Bowei Ye, Xiaolong Zheng, IFAC PapersOnLine . 2020,第5期

机译：通过共同对抗培训，强大的图形神经网络对抗对抗攻击
2. RazorNet: Adversarial Training and Noise Training on a Deep Neural Network Fooled by a Shallow Neural Network [J] . Shayan Taheri, Milad Salem, Jiann-Shiun Yuan Big Data and Cognitive Computing . 2019,第3期

机译：razornet：浅神经网络愚弄的深层神经网络上的对抗训练和噪声训练
3. Generative Adversarial Networks Capabilities for Super-Resolution Reconstruction of Weather Radar Echo Images [J] . Hongguang Chen, Xing Zhang, Yintian Liu, Atmosphere . 2019,第9期

机译：天气雷达回波图像超分辨率重建的生成对抗网络能力
4. Echo State Network with Adversarial Training [C] . Takanori Akiyama, Gouhei Tanaka International conference on artificial neural networks . 2019

机译：与对抗培训的回声状态网络
5. Improved Speech Enhancement Algorithm based on Generative Adversarial Networks [D] . Wang, Kebei. 2021

机译：基于生成对抗性网络的改进语音增强算法
6. Deep learning approach to classification of lung cytological images: Two-step training using actual and synthesized images by progressive growing of generative adversarial networks [O] . Atsushi Teramoto, Tetsuya Tsukamoto, Ayumi Yamada, 2020

机译：深层学习方法肺细胞学图像分类：使用实际和合成图像的两步训练通过逐步生长的生长生长育种网络
7. Diversity Adversarial Training against Adversarial Attack on Deep Neural Networks [O] . Hyun Kwon, Jun Lee 2021

机译：深度神经网络对抗对抗攻击的多样性对抗培训

Echo State Network with Adversarial Training

摘要

著录项

相似文献

相关主题

期刊订阅