地面运动预测方程通常用于预测地震强度分布。但是,将这种方法应用于受地下板结构影响的地震分布并不容易,这通常称为异常地震分布。这项研究提出了使用神经网络进行回归和分类方法的混合体。提出的模型将分布视为二维数据,如图像。我们的方法可以准确预测地震强度分布,甚至异常分布。
translated by 谷歌翻译
Deep learning (DL) has become a driving force and has been widely adopted in many domains and applications with competitive performance. In practice, to solve the nontrivial and complicated tasks in real-world applications, DL is often not used standalone, but instead contributes as a piece of gadget of a larger complex AI system. Although there comes a fast increasing trend to study the quality issues of deep neural networks (DNNs) at the model level, few studies have been performed to investigate the quality of DNNs at both the unit level and the potential impacts on the system level. More importantly, it also lacks systematic investigation on how to perform the risk assessment for AI systems from unit level to system level. To bridge this gap, this paper initiates an early exploratory study of AI system risk assessment from both the data distribution and uncertainty angles to address these issues. We propose a general framework with an exploratory study for analyzing AI systems. After large-scale (700+ experimental configurations and 5000+ GPU hours) experiments and in-depth investigations, we reached a few key interesting findings that highlight the practical need and opportunities for more in-depth investigations into AI systems.
translated by 谷歌翻译
众所周知,深度神经网络(DNNS)通过特别注意某些特定像素来对输入图像进行分类。对每个像素的注意力的图形表示称为显着图。显着图用于检查分类决策基础的有效性,例如,如果DNN对背景而不是图像的主题更加关注,则它不是分类的有效基础。语义扰动可以显着改变显着性图。在这项工作中,我们提出了第一种注意鲁棒性的验证方法,即显着映射对语义扰动的组合的局部稳健性。具体而言,我们的方法确定了扰动参数的范围(例如,亮度变化),该参数维持实际显着性映射变化与预期的显着映射图之间的差异低于给定的阈值。我们的方法基于激活区域遍历,重点是最外面的鲁棒边界,以在较大的DNN上可伸缩。实验结果表明,无论语义扰动如何,我们的方法都可以显示DNN可以与相同基础进行分类的程度,并报告激活区域遍历的性能和性能因素。
translated by 谷歌翻译
深度学习模型容易受到对抗性例子的影响,用于产生此类示例的对抗性攻击引起了相当大的研究兴趣。尽管基于最陡峭下降的现有方法已经取得了很高的攻击成功率,但条件不足的问题偶尔会降低其性能。为了解决此限制,我们利用了对这种类型问题有效的共轭梯度(CG)方法,并提出了一种受CG方法启发的新型攻击算法,称为自动结合梯度(ACG)攻击。在最新的健壮模型上进行的大规模评估实验的结果表明,对于大多数模型而言,ACG能够找到比现有SOTA算法自动PGD(APGD)更少迭代的对抗性示例。我们研究了ACG和APGD在多元化和强化方面的搜索性能差异,并定义了一种称为多样性指数(DI)的度量,以量化多样性的程度。从使用该指数对多样性的分析中,我们表明对所提出方法的更多样化的搜索显着提高了其攻击成功率。
translated by 谷歌翻译
本文提出了在新日本大学入学考试中自动评分手写描述性答案的实验,这是2017年和2018年的约120,000名审查。大约有400,000个答案超过2000万个字符。虽然人类审查员的所有答案都得到了评分,但手写字符没有标记。我们展示了我们试图调整基于神经网络的手写识别员,在标记的手写数据集上培训到此未标记的答案集。我们所提出的方法结合了不同的培训策略,集成了多个识别器,并使用由大型常规语料库构建的语言模型来避免过度填充到特定数据。在我们的实验中,使用约2,000个验证标记的答案记录了超过97%的字符精度,该标记答案占数据集的0.5%。然后,将认可的答案基于BERT模型进入预先训练的自动评分系统,而无需纠正误识别的字符并提供Rubric注释。自动评分系统从二次加权Kappa(QWK)的0.84到0.98达到0.84至0.98。由于QWK超过0.8,它代表了自动评分系统与人类审查员之间得分的可接受相似性。这些结果是对描述性答案的结束自动评分的进一步研究。
translated by 谷歌翻译
Quantum Kernel方法是量子机器学习的关键方法之一,这具有不需要优化的优点,并且具有理论简单。凭借这些属性,到目前为止已经开发了几种实验演示和对潜在优势的讨论。但是,正如古典机器学习所在的情况一样,并非所有量子机器学习模型都可以被视为内核方法。在这项工作中,我们探讨了具有深层参数化量子电路的量子机器学习模型,旨在超出传统量子核法。在这种情况下,预计表示功率和性能将得到增强,而培训过程可能是丢储Plateaus问题的瓶颈。然而,我们发现,在训练期间,深度足够的量子电路的参数不会从其初始值中移动到初始值,从而允许一阶扩展参数。这种行为类似于经典文献中的神经切线内核,并且可以通过另一个紧急内核,量子切线内核来描述这种深度变化量子机器学习。数值模拟表明,所提出的Quantum切线内核优于传统的Quantum核心核对ANSATZ生成的数据集。该工作提供了超出传统量子内核法的新方向,并探讨了用深层参数化量子电路的量子机器学习的潜在力量。
translated by 谷歌翻译
FIG. 1. Schematic diagram of a Variational Quantum Algorithm (VQA). The inputs to a VQA are: a cost function C(θ), with θ a set of parameters that encodes the solution to the problem, an ansatz whose parameters are trained to minimize the cost, and (possibly) a set of training data {ρ k } used during the optimization. Here, the cost can often be expressed in the form in Eq. ( 3), for some set of functions {f k }. Also, the ansatz is shown as a parameterized quantum circuit (on the left), which is analogous to a neural network (also shown schematically on the right). At each iteration of the loop one uses a quantum computer to efficiently estimate the cost (or its gradients). This information is fed into a classical computer that leverages the power of optimizers to navigate the cost landscape C(θ) and solve the optimization problem in Eq. ( 1). Once a termination condition is met, the VQA outputs an estimate of the solution to the problem. The form of the output depends on the precise task at hand. The red box indicates some of the most common types of outputs.
translated by 谷歌翻译
We propose a classical-quantum hybrid algorithm for machine learning on near-term quantum processors, which we call quantum circuit learning. A quantum circuit driven by our framework learns a given task by tuning parameters implemented on it. The iterative optimization of the parameters allows us to circumvent the high-depth circuit. Theoretical investigation shows that a quantum circuit can approximate nonlinear functions, which is further confirmed by numerical simulations. Hybridizing a low-depth quantum circuit and a classical computer for machine learning, the proposed framework paves the way toward applications of near-term quantum devices for quantum machine learning.
translated by 谷歌翻译