The recent advent of large language models - large neural networks trained on a simple predictive objective over a massive corpus of natural language - has reinvigorated debate over whether human cognitive capacities might emerge in such generic models given sufficient training data. Of particular interest is the ability of these models to reason about novel problems zero-shot, without any direct training on those problems. In human cognition, this capacity is closely tied to an ability to reason by analogy. Here, we performed a direct comparison between human reasoners and a large language model (GPT-3) on a range of analogical tasks, including a novel text-based matrix reasoning task closely modeled on Raven's Progressive Matrices. We found that GPT-3 displayed a surprisingly strong capacity for abstract pattern induction, matching or even surpassing human capabilities in most settings. Our results indicate that large language models such as GPT-3 have acquired an emergent ability to find zero-shot solutions to a broad range of analogy problems.
translated by 谷歌翻译
Time series anomaly detection has applications in a wide range of research fields and applications, including manufacturing and healthcare. The presence of anomalies can indicate novel or unexpected events, such as production faults, system defects, or heart fluttering, and is therefore of particular interest. The large size and complex patterns of time series have led researchers to develop specialised deep learning models for detecting anomalous patterns. This survey focuses on providing structured and comprehensive state-of-the-art time series anomaly detection models through the use of deep learning. It providing a taxonomy based on the factors that divide anomaly detection models into different categories. Aside from describing the basic anomaly detection technique for each category, the advantages and limitations are also discussed. Furthermore, this study includes examples of deep anomaly detection in time series across various application domains in recent years. It finally summarises open issues in research and challenges faced while adopting deep anomaly detection models.
translated by 谷歌翻译
天文瞬态是在各种时间尺度变得暂时更亮的恒星物体,并导致宇宙学和天文学中的一些最重要的发现。其中一些瞬变是被称为超新星的爆炸物的爆炸性死亡,而其他瞬间是罕见的,异国情调的,或完全是新的令人兴奋的恒星爆炸。新的天文天空调查正在观察前所未有的多波长瞬变数量,在视觉上识别新的和有趣的瞬态的标准方法不可行。为了满足这一需求,我们提出了两种新的方法,旨在实时快速,自动地自动检测异常瞬态光线曲线。两种方法都基于简单的想法,如果可以精确建模来自已知瞬态频体群体的光曲线,则从模型预测的任何偏差可能是异常的。第一方法是使用时间卷积网络(TCN)建造的概率神经网络,第二个是瞬态的可解释的贝叶斯参数模型。我们展示了神经网络的灵活性,使它们成为许多回归任务的这种强大工具的属性,是与我们的参数模型相比时不太适合于异常检测的原因。
translated by 谷歌翻译
估计具有有限样本的2个高维分布之间的发散的问题是各种领域的重要问题,例如机器学习。虽然以前的方法以中等维度数据执行良好,但它们的准确性开始在具有100多个二进制变量的情况下降低。因此,我们建议使用可分解模型来估算高维数据的分歧。这些允许我们将高维分布的估计密度分解成较低尺寸函数的产物。我们进行正式和实验分析,探讨在分歧估算的背景下使用可分解模型的性质。为此,我们凭经验展示使用来自最大似然估计器的可分解模型来估计Kullback-Leibler分歧,优于在可以从可用数据中学习高度和有用的可分解模型的情况下发散估计的现有方法。
translated by 谷歌翻译
动态时间翘曲(DTW)及其约束(CDTW)和加权(WDTW)变体,是具有各种应用范围的时间序列距离。它们最小化了系列之间的非线性校准成本。已经引入了CDTW和WDTW,因为DTW在其对齐方面过于允许。但是,CDTW使用粗略的步骤功能,允许窗口内的无限制灵活性,而不是超出它。 WDTW的乘法重量是相对于沿着翘曲路径的对齐点之间的距离,而不是引入的翘曲量的直接函数。在本文中,我们介绍了Amerced动态时间翘曲(ADTW),一种新的直观的DTW变体,可以通过固定的添加剂成本来惩罚翘曲的行为。像CDTW和WDTW一样,ADTW约束了翘曲量。但是,它避免突然不连续性在允许的扭曲量和乘法惩罚的局限性中。我们正式介绍ADTW,证明其一些属性,并讨论其参数化。我们展示了一个简单的示例,如何参数化以实现直观的结果,并展示其对标准时间序列分类基准的实用性。我们在C ++中提供了一个演示应用程序。
translated by 谷歌翻译
虽然最先进的对比自我监督学习(SSL)模型产生与监督对应物竞争的结果,但它们缺乏推断潜在变量的能力。相反,规定的潜在变量(LV)模型能够归因于不确定性,诱导任务特定压缩,并且通常允许更可解释的表示。在这项工作中,我们向大规模对比SSL模型引入LV近似值。我们证明,此添加可提高下游性能(导致96.42%和77.49%的测试在CIFAR10和ImageNet上的前1个微调性能,以及resnet50),并产生可用于解释性的高度压缩表示(588倍降低),分类和回归下游任务。
translated by 谷歌翻译
尽管近期寻求自我监督深度学习的许多技术的成功,但对最终学习的陈述有限调查。通过利用最近在对神经表示的比较方面的进步,我们通过比较对比自我监督算法在公共架构中的简单图像数据的监督中探讨了这种方向。我们发现该方法通过不同的手段来学习类似的中间陈述,并且表示在最终几层中迅速发散。我们调查这种分歧,发现这些层非常适合他们独特的学习目标。我们还发现对比物镜隐含地适合中间层的监督目标,但反向不是真的。我们的工作特别突出了学到的中间陈述的重要性,并提高了辅助任务设计的关键问题。
translated by 谷歌翻译
汽车行业在过去几十年中见证了越来越多的发展程度;从制造手动操作车辆到具有高自动化水平的制造车辆。随着近期人工智能(AI)的发展,汽车公司现在雇用BlackBox AI模型来使车辆能够感知其环境,并使人类少或没有输入的驾驶决策。希望能够在商业规模上部署自治车辆(AV),通过社会接受AV成为至关重要的,并且可能在很大程度上取决于其透明度,可信度和遵守法规的程度。通过为AVS行为的解释提供对这些接受要求的遵守对这些验收要求的评估。因此,解释性被视为AVS的重要要求。 AV应该能够解释他们在他们运作的环境中的“见到”。在本文中,我们对可解释的自动驾驶的现有工作体系进行了全面的调查。首先,我们通过突出显示并强调透明度,问责制和信任的重要性来开放一个解释的动机;并审查与AVS相关的现有法规和标准。其次,我们识别并分类了参与发展,使用和监管的不同利益相关者,并引出了AV的解释要求。第三,我们对以前的工作进行了严格的审查,以解释不同的AV操作(即,感知,本地化,规划,控制和系统管理)。最后,我们确定了相关的挑战并提供建议,例如AV可解释性的概念框架。该调查旨在提供对AVS中解释性感兴趣的研究人员所需的基本知识。
translated by 谷歌翻译
聚类算法的全面基准是困难的两个关键因素:(i)〜这种无监督的学习方法的独特数学定义和(ii)〜某些聚类算法采用的生成模型或群集标准之间的依赖性的依赖性内部集群验证。因此,对严格基准测试的最佳做法没有达成共识,以及是否有可能在给定申请的背景之外。在这里,我们认为合成数据集必须继续在群集算法的评估中发挥重要作用,但这需要构建适当地涵盖影响聚类算法性能的各种属性集的基准。通过我们的框架,我们展示了重要的角色进化算法,以支持灵活的这种基准,允许简单的修改和扩展。我们说明了我们框架的两种可能用途:(i)〜基准数据的演变与一组手派生属性和(ii)〜生成梳理给定对算法之间的性能差异的数据集。我们的作品对设计集群基准的设计具有足够挑战广泛算法的集群基准,并进一步了解特定方法的优势和弱点。
translated by 谷歌翻译
With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations. However, learning from synthetic images may not achieve the desired performance due to a gap between synthetic and real image distributions. To reduce this gap, we propose Simulated+Unsupervised (S+U) learning, where the task is to learn a model to improve the realism of a simulator's output using unlabeled real data, while preserving the annotation information from the simulator. We develop a method for S+U learning that uses an adversarial network similar to Generative Adversarial Networks (GANs), but with synthetic images as inputs instead of random vectors. We make several key modifications to the standard GAN algorithm to preserve annotations, avoid artifacts, and stabilize training: (i) a 'self-regularization' term, (ii) a local adversarial loss, and (iii) updating the discriminator using a history of refined images. We show that this enables generation of highly realistic images, which we demonstrate both qualitatively and with a user study. We quantitatively evaluate the generated images by training models for gaze estimation and hand pose estimation. We show a significant improvement over using synthetic images, and achieve state-of-the-art results on the MPIIGaze dataset without any labeled real data.
translated by 谷歌翻译