Pub Date : 2020-01-31DOI: 10.1109/WIFS49906.2020.9360887
Liangping Ma, John Kaewell
Monte Carlo dropout may effectively capture model uncertainty in deep learning, where a measure of uncertainty is obtained by using multiple instances of dropout at test time. However, Monte Carlo dropout is applied across the whole network and the use of it significantly increases the computational complexity, proportional to the number of instances. To reduce the computational complexity, at test time we enable dropout layers only near the output of the neural network and reuse the computation from prior layers while keeping, if any, other dropout layers disabled. Additionally, we leverage the side information about the ideal distributions for various input samples to do ‘error correction’ on the predictions. We apply these techniques to the radio frequency (RF) transmitter classification problem and show that the proposed algorithm is able to provide better prediction uncertainty than the simple ensemble average algorithm and can be used to effectively identify transmitters that are not in the training data set while correctly classifying transmitters it has been trained on.
蒙特卡罗dropout可以有效地捕获深度学习中的模型不确定性，其中通过在测试时使用多个dropout实例来获得不确定性的度量。然而，Monte Carlo dropout应用于整个网络，它的使用显着增加了计算复杂性，与实例数量成正比。为了降低计算复杂性，在测试时，我们只在神经网络的输出附近启用退出层，并重用先前层的计算，同时保持其他退出层(如果有的话)禁用。此外，我们利用关于各种输入样本的理想分布的侧信息对预测进行“错误校正”。我们将这些技术应用于射频(RF)发射机分类问题，并表明所提出的算法能够提供比简单的集成平均算法更好的预测不确定性，并且可以有效地识别不在训练数据集中的发射机，同时正确分类它所训练的发射机。
{"title":"Fast Monte Carlo Dropout and Error Correction for Radio Transmitter Classification","authors":"Liangping Ma, John Kaewell","doi":"10.1109/WIFS49906.2020.9360887","DOIUrl":"https://doi.org/10.1109/WIFS49906.2020.9360887","url":null,"abstract":"Monte Carlo dropout may effectively capture model uncertainty in deep learning, where a measure of uncertainty is obtained by using multiple instances of dropout at test time. However, Monte Carlo dropout is applied across the whole network and the use of it significantly increases the computational complexity, proportional to the number of instances. To reduce the computational complexity, at test time we enable dropout layers only near the output of the neural network and reuse the computation from prior layers while keeping, if any, other dropout layers disabled. Additionally, we leverage the side information about the ideal distributions for various input samples to do ‘error correction’ on the predictions. We apply these techniques to the radio frequency (RF) transmitter classification problem and show that the proposed algorithm is able to provide better prediction uncertainty than the simple ensemble average algorithm and can be used to effectively identify transmitters that are not in the training data set while correctly classifying transmitters it has been trained on.","PeriodicalId":354881,"journal":{"name":"2020 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130786835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：