对抗性实例的有趣现象引起了机器学习中的显着关注,对社区可能更令人惊讶的是存在普遍对抗扰动(UAPS),即欺骗目标DNN的单一扰动。随着对深层分类器的关注,本调查总结了最近普遍对抗攻击的进展,讨论了攻击和防御方的挑战,以及uap存在的原因。我们的目标是将此工作扩展为动态调查,该调查将定期更新其内容,以遵循关于在广泛的域中的UAP或通用攻击的新作品,例如图像,音频,视频,文本等。将讨论相关更新:https://bit.ly/2sbqlgg。我们欢迎未来的作者在该领域的作品,联系我们,包括您的新发现。
translated by 谷歌翻译
Data-driven models such as neural networks are being applied more and more to safety-critical applications, such as the modeling and control of cyber-physical systems. Despite the flexibility of the approach, there are still concerns about the safety of these models in this context, as well as the need for large amounts of potentially expensive data. In particular, when long-term predictions are needed or frequent measurements are not available, the open-loop stability of the model becomes important. However, it is difficult to make such guarantees for complex black-box models such as neural networks, and prior work has shown that model stability is indeed an issue. In this work, we consider an aluminum extraction process where measurements of the internal state of the reactor are time-consuming and expensive. We model the process using neural networks and investigate the role of including skip connections in the network architecture as well as using l1 regularization to induce sparse connection weights. We demonstrate that these measures can greatly improve both the accuracy and the stability of the models for datasets of varying sizes.
translated by 谷歌翻译
A digital twin is defined as a virtual representation of a physical asset enabled through data and simulators for real-time prediction, optimization, monitoring, controlling, and improved decision-making. Unfortunately, the term remains vague and says little about its capability. Recently, the concept of capability level has been introduced to address this issue. Based on its capability, the concept states that a digital twin can be categorized on a scale from zero to five, referred to as standalone, descriptive, diagnostic, predictive, prescriptive, and autonomous, respectively. The current work introduces the concept in the context of the built environment. It demonstrates the concept by using a modern house as a use case. The house is equipped with an array of sensors that collect timeseries data regarding the internal state of the house. Together with physics-based and data-driven models, these data are used to develop digital twins at different capability levels demonstrated in virtual reality. The work, in addition to presenting a blueprint for developing digital twins, also provided future research directions to enhance the technology.
translated by 谷歌翻译
Deep Ensemble Convolutional Neural Networks has become a methodology of choice for analyzing medical images with a diagnostic performance comparable to a physician, including the diagnosis of Diabetic Retinopathy. However, commonly used techniques are deterministic and are therefore unable to provide any estimate of predictive uncertainty. Quantifying model uncertainty is crucial for reducing the risk of misdiagnosis. A reliable architecture should be well-calibrated to avoid over-confident predictions. To address this, we propose a UATTA-ENS: Uncertainty-Aware Test-Time Augmented Ensemble Technique for 5 Class PIRC Diabetic Retinopathy Classification to produce reliable and well-calibrated predictions.
translated by 谷歌翻译
我们为基于分数的生成模型(SGM)(例如Denoising扩散概率模型(DDPM))提供理论收敛保证,该模型构成了大型现实世界中生成模型的骨干,例如DALL $ \ cdot $ E2。我们的主要结果是,假设有准确的分数估计值,此类SGM可以从本质上有效地从任何现实的数据分布中进行采样。与先前的作品相反,我们的结果(1)以$ l^2 $准确的分数估算(而不是$ l^\ infty $ -CACCRATE)保持; (2)不需要限制性的功能不平等条件,而这些条件排除了实质性的非con虫; (3)在所有相关问题参数中刻度缩放; (4)匹配兰格文扩散离散的最新复杂性保证,前提是得分误差足够小。我们认为这是SGM的经验成功的强有力理论理由。我们还基于严重阻尼的Langevin扩散(CLD)检查SGM。与传统的观点相反,我们提供了证据,表明CLD的使用不会降低SGM的复杂性。
translated by 谷歌翻译
随着数据的不断增加,将现代机器学习方法应用于建模和控制等领域的兴趣爆炸。但是,尽管这种黑盒模型具有灵活性和令人惊讶的准确性,但仍然很难信任它们。结合两种方法的最新努力旨在开发灵活的模型,这些模型仍然可以很好地推广。我们称为混合分析和建模(HAM)的范式。在这项工作中,我们调查了使用数据驱动模型纠正基于错误的物理模型的纠正源术语方法(COSTA)。这使我们能够开发出可以进行准确预测的模型,即使问题的基本物理学尚未得到充分理解。我们将Costa应用于铝电解电池中的Hall-H \'Eroult工艺。我们证明该方法提高了准确性和预测稳定性,从而产生了总体可信赖的模型。
translated by 谷歌翻译
不确定性在未来预测中起关键作用。未来是不确定的。这意味着可能有很多可能的未来。未来的预测方法应涵盖坚固的全部可能性。在自动驾驶中,涵盖预测部分中的多种模式对于做出安全至关重要的决策至关重要。尽管近年来计算机视觉系统已大大提高,但如今的未来预测仍然很困难。几个示例是未来的不确定性,全面理解的要求以及嘈杂的输出空间。在本论文中,我们通过以随机方式明确地对运动进行建模并学习潜在空间中的时间动态,从而提出了解决这些挑战的解决方案。
translated by 谷歌翻译
深厚的强化学习政策尽管在模拟的视觉控制任务中出色地效率,但表现出令人失望的能力,可以在输入培训图像中跨越跨干扰。图像统计或分散背景元素的变化是防止这种控制策略的概括和现实世界中适用性的陷阱。我们阐述了这样的直觉,即良好的视觉政策应该能够确定哪些像素对其决策很重要,并保留对图像跨图像的重要信息来源的识别。这意味着对具有较小概括差距的政策进行培训应集中在如此重要的像素上,而忽略其他像素。这导致引入显着引导的Q-Networks(SGQN),这是一种视觉增强学习的通用方法,与任何值函数学习方法兼容。 SGQN极大地提高了软演员 - 批评者的概括能力,并且在DeepMind Control Generalization基准上胜过现有的现有方法,为训练效率,概括性差距和政策解释性提供了新的参考。
translated by 谷歌翻译
人工神经网络今天具有广泛的应用程序,因为它们的高度灵活性和从数据中建模非线性功能的能力。但是,由于其黑盒性质,从小型数据集概括的能力差以及在培训期间的不一致的融合,神经网络的可信度受到限制。铝电解是一个复杂的非线性过程,具有许多相互关联的子处理。人工神经网络可能非常适合对铝电解过程进行建模,但是此过程的安全性最关键的性质需要值得信赖的模型。在这项工作中,稀疏的神经网络经过训练,以建模铝电解模拟器的系统动力学。与相应的密集神经网络相比,稀疏模型结构的模型复杂性显着降低。我们认为这使模型更容易解释。此外,实证研究表明,稀疏模型比密集的神经网络从小型训练集中概括得更好。此外,训练具有不同参数初始化的稀疏神经网络的合奏表明,模型会收敛到具有相似学习的输入特征的相似模型结构。
translated by 谷歌翻译
基于物理学的模型已成为流体动力学的主流,用于开发预测模型。近年来,由于数据科学,处理单元,基于神经网络的技术和传感器适应性的快速发展,机器学习为流体社区提供了复兴。到目前为止,在流体动力学中的许多应用中,机器学习方法主要集中在标准过程上,该过程需要将培训数据集中在指定机器或数据中心上。在这封信中,我们提出了一种联合机器学习方法,该方法使本地化客户能够协作学习一个汇总和共享的预测模型,同时将所有培训数据保留在每个边缘设备上。我们证明了这种分散学习方法的可行性和前景,并努力为重建时空领域建立深度学习的替代模型。我们的结果表明,联合机器学习可能是设计与流体动力学相关的高度准确预测分散的数字双胞胎的可行工具。
translated by 谷歌翻译