.png){kind=icon}
返回
Partial Adversarial Training for Neural Network-Based Uncertainty Quantification
.png){kind=icon}
PRE
AI
DOI：10.1109/TETCI.2019.2936546.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Currently available uncertainty quantification (UQ) neural networks (NNs) are trained through the statistical error minimization. Therefore, NNs perform poorly for critical input patterns. Some input patterns have lower coverage probabilities than others. Such input dependent performance is evident in electricity price prediction where different input features are coming from heterogeneous monitoring sources. This paper proposes a prediction interval (PI) based UQ of the electricity price with the proposed partial adversarial training to achieve the input-domain independent performance. The proposed training consists of initial training, adversarial sample generations from critical samples and a final training with the combined datasets of critical samples and initial training samples. Critical situations are situations where prediction systems struggle to predict and make higher statistical errors. Multiple NNs are first trained with different initializations. Each uncovered sample to the NN pair in the training set generates an adversarial sample. The adversarial dataset is concatenated with the initial samples. The final NN training is performed with the combined dataset. The technique is visualized with rough sketches in both time and input domain. The feasibility and performance are examined on experimental electricity market price datasets.
Keyword:
Uncertainty
Artificial neural networks
Training
Neurons
Probability distribution
Electron mobility
Conductors
Uncertainty Quantification
Heteroscedastic Uncertainty
Neural Network
Prediction Interval
Electricity Price
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
6.5
论文数:
1.4K
被引数:
4.5K
机构
引用论文
Probabilistic Forecasting of Sensory Data With Generative Adversarial Networks - ForGAN使用生成对抗网络对感觉数据进行概率预测-ForGAN.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Judo technical-tactical dynamics: analysis of attack system effectiveness in high-level athletes
PREAI
分享收藏Dynamic simulator and model predictive control of an integrated solar combined cycle plantENERGY
OAAI
ENERGYIF9.4
OAAI分享收藏Neural Network-Based Uncertainty Quantification: A Survey of Methodologies and Applications基于神经网络的不确定性量化: 方法与应用综述IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容