在构建培训迷你批次时,最半监督的学习方法在样本标记的数据上。本文研究了这种常见做法是否改善了学习和方法。我们将其与替代设置进行比较,其中每个迷你批次从所有训练数据均匀地采样,标有或不统计,这大大减少了典型的低标签制度中真正标签的直接监督。然而,这种更简单的设置也可以看作更通用,甚至是必要的,在多任务问题中,标记数据的过采样将变得棘手。我们对半监控的CiFar-10图像分类的实验,使用FixMatch显示使用均匀采样方法时的性能下降,当标记数据的量或训练时间增加时,在均匀采样方法增加时。此外,我们分析培训动态,了解标记数据的过采样如何比较均匀采样。我们的主要发现是,在训练中特别有益,但在更多伪标签变得正确时,在后期的阶段中不太重要。尽管如此,我们还发现,保持一些真正的标签仍然很重要,以避免从错误的伪标签中积累确认错误。
translated by 谷歌翻译
In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine learning, yet very limited systematic research is available in the context of deep learning. In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities. Our main evaluation metric is area under the receiver operating characteristic curve (ROC AUC) adjusted to multi-class tasks since overall accuracy metric is associated with notable difficulties in the context of imbalanced data. Based on results from our experiments we conclude that (i) the effect of class imbalance on classification performance is detrimental; (ii) the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; (iii) oversampling should be applied to the level that completely eliminates the imbalance, whereas the optimal undersampling ratio depends on the extent of imbalance; (iv) as opposed to some classical machine learning models, oversampling does not cause overfitting of CNNs; (v) thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest.
translated by 谷歌翻译
Automation of berthing maneuvers in shipping is a pressing issue as the berthing maneuver is one of the most stressful tasks seafarers undertake. Berthing control problems are often tackled via tracking a predefined trajectory or path. Maintaining a tracking error of zero under an uncertain environment is impossible; the tracking controller is nonetheless required to bring vessels close to desired berths. The tracking controller must prioritize the avoidance of tracking errors that may cause collisions with obstacles. This paper proposes a training method based on reinforcement learning for a trajectory tracking controller that reduces the probability of collisions with static obstacles. Via numerical simulations, we show that the proposed method reduces the probability of collisions during berthing maneuvers. Furthermore, this paper shows the tracking performance in a model experiment.
translated by 谷歌翻译
在使用深神经网络的现有图像分类系统中,图像分类所需的知识隐含在模型参数中。如果用户想更新此知识,则需要微调模型参数。此外,用户无法验证推理结果的有效性或评估知识对结果的贡献。在本文中,我们研究了一个存储图像分类知识的系统,例如图像特征图,标签和原始图像,而不是模型参数,而是在外部高容量存储中。我们的系统在对输入图像进行分类时,像数据库一样引用存储。为了增加知识,我们的系统会更新数据库,而不是微调模型参数,从而避免了在增量学习方案中灾难性的遗忘。我们重新访问一个KNN(K-Nearest邻居)分类器,并在我们的系统中使用它。通过分析KNN算法引用的邻域样本,我们可以解释过去如何将知识用于推理结果。我们的系统在ImageNet数据集上实现了79.8%的TOP-1精度,而在预处理后无需微调模型参数,而在任务增量学习设置中,在Split CIFAR-100数据集中获得了90.8%的精度。
translated by 谷歌翻译
对海洋中船舶反应的关键评估和理解对于未来平台的设计和工程来说是重要的,也很重要,而且是目前部署的操作和安全性。模拟或实验通常在船舶设计期间或在部署之前在标称海洋状况中进行,并且在部署时,结果可能不会反映船只和海洋环境的瞬时状态。船舶反应的短期时间预测给出了当前波浪环境和船舶状态将使有人和无人驾驶船只增强决策。然而,目前在数值流体动力模拟工具中的最新技术过于计算地用于用于实时船舶运动预测,并且计算有效的工具太低的保真度以提供准确的响应。一种方法论是用长短短期记忆(LSTM)神经网络开发的方法,以代表自由运行的David Taylor模型盆(DTMB)5415驱逐舰在海州7斯泰宁不规则海洋中运行20节。案例研究是对课程保存和转向圈情景进行的。对船只遇到框架的估计是用训练数据集中观察到的轨迹进行的。波升时间历史由人工波探针给出,该探针与估计的遇到帧一起旅行并用作神经网络的输入,而输出是6-DOF暂时船舶运动响应。总的来说,神经网络能够预测由于看不见的波准确而导致船的时间响应,这使得该方法适用于系统识别和实时船舶运动预测。方法,模型精度对波探测和训练数据量的依赖性以及估计的遇到帧都详细说明。
translated by 谷歌翻译
我们提出了一种依赖于大约解决最小化问题的orcacles的马鞍点优化方法。我们在强凸凹面上分析其收敛性,并向全球最大马鞍点显示线性趋同。根据收敛分析,我们开发了一种适应学习率的启发式方法。显示使用(1 + 1)-cma-es作为最小化Oracle的开发方法的实施方式,即普通话-CMA-es,优于几种现有的测试问题方法。数值评估证实了理论会聚速率的紧密性以及学习率适应机制的效率。作为实际问题的一个例子,建议的优化方法应用于模型不确定性下的自动停泊控制问题,显示其在获得解决方案到不确定性的解决方案中的用处。
translated by 谷歌翻译