ID 原文 译文
56498 为解决这一问题,本文提出使用随机平滑法对K-近邻分类器进行鲁棒性验证. To tackle this issue, we propose to employ the randomized smoothing method to verify therobustness of K-NN classifiers.
56499 随机平滑法利用了K-近邻分类器对高斯(Gauss)白噪声鲁棒的特点,获得了较为理想的鲁棒性验证效果. By exploiting the resistance of K-NN to random Gaussian noise, the randomizedsmoothing method achieves high performance in verification.
56500 基准数据集上的实验结果表明,相比于最新的鲁棒神经网络,"随机平滑的" K-近邻分类器展现出了更好的验证鲁棒性. Our experiments on benchmark datasets show thatthe smoothed K-NN classifier is more verifiably robust than state-of-the-art robust neural networks.
56501 油气储集层识别是石油能源企业在勘测和开发业务中核心的任务之一. Oil and gas reservoir detection is one of the major tasks of petroleum energy companies in theexploration and production process.
56502 长期以来,油气行业一直依靠专家人工分析海量测井数据以对地下油气储集层进行定性分析,虽然专家解释结论有着很高的精准度,但是时间与经济成本都十分高昂. The oil and gas industry has long relied on the expert manual analysis ofmassive logging data to perform qualitative analyses of oil and gas reservoirs. Although experts’ interpretationsare highly accurate, the time and economic costs are considerably high.
56503 近些年来,随着以深度学习为代表的人工智能技术的迅速发展,智能油气储集层识别技术成为学术界和工业界共同关注的问题. With the rapid development of artificialintelligence technologies such as deep learning in recent years, intelligent oil and gas reservoir detection methodshave become a focus in the academia and industry.
56504 然而,真实工业环境存在严重的传感数据不一致问题,给传统的监督学习模型带来巨大的挑战. However, sensor data in real industrial scenarios presentserious inconsistencies, which bring great challenges to traditional supervised learning models.
56505 本文针对传感器不一致情境中油气储集层识别任务展开研究,提出多尺度地质知识蒸馏网络的方法. This paper presentsa focused study on the oil and gas reservoir detection task in the context of sensor inconsistencies and proposes ageological knowledge distillation multiscale network approach.
56506 首先,该方法提出一种多尺度特征自注意力融合机制来学习地质信息的多尺度动态表征. This method proposes a multiscale feature fusionmechanism based on self-attention to learn the multiscale dynamic representation of geological information.
56507 其次,该方法设计一种地质知识蒸馏学习模型,从非一致传感数据中学习额外的地质知识,进一步提升模型准确度. Then,the model designs a geological knowledge distillation learning framework to learn additional geological knowledgefrom inconsistent sensor data. This step further improves the model’s accuracy.