人工智能(AI)模型的黑框性质不允许用户理解和有时信任该模型创建的输出。在AI应用程序中,不仅结果,而且结果的决策路径至关重要,此类Black-Box AI模型还不够。可解释的人工智能(XAI)解决了此问题,并定义了用户可解释的一组AI模型。最近,有几种XAI模型是通过在医疗保健,军事,能源,金融和工业领域等各个应用领域的黑盒模型缺乏可解释性和解释性来解决有关的问题。尽管XAI的概念最近引起了广泛关注,但它与物联网域的集成尚未完全定义。在本文中,我们在物联网域范围内使用XAI模型对最近的研究进行了深入和系统的综述。我们根据其方法和应用领域对研究进行分类。此外,我们旨在专注于具有挑战性的问题和开放问题,并为未来的方向指导开发人员和研究人员进行未来的未来调查。
translated by 谷歌翻译
Compliance in actuation has been exploited to generate highly dynamic maneuvers such as throwing that take advantage of the potential energy stored in joint springs. However, the energy storage and release could not be well-timed yet. On the contrary, for multi-link systems, the natural system dynamics might even work against the actual goal. With the introduction of variable stiffness actuators, this problem has been partially addressed. With a suitable optimal control strategy, the approximate decoupling of the motor from the link can be achieved to maximize the energy transfer into the distal link prior to launch. However, such continuous stiffness variation is complex and typically leads to oscillatory swing-up motions instead of clear launch sequences. To circumvent this issue, we investigate decoupling for speed maximization with a dedicated novel actuator concept denoted Bi-Stiffness Actuation. With this, it is possible to fully decouple the link from the joint mechanism by a switch-and-hold clutch and simultaneously keep the elastic energy stored. We show that with this novel paradigm, it is not only possible to reach the same optimal performance as with power-equivalent variable stiffness actuation, but even directly control the energy transfer timing. This is a major step forward compared to previous optimal control approaches, which rely on optimizing the full time-series control input.
translated by 谷歌翻译
Large-scale vision-language models such as CLIP have shown impressive performance on zero-shot image classification and image-to-text retrieval. However, such zero-shot performance of CLIP-based models does not realize in tasks that require a finer-grained correspondence between vision and language, such as Visual Question Answering (VQA). We investigate why this is the case, and report an interesting phenomenon of CLIP, which we call the Concept Association Bias (CAB), as a potential cause of the difficulty of applying CLIP to VQA and similar tasks. CAB is especially apparent when two concepts are present in the given image while a text prompt only contains a single concept. In such a case, we find that CLIP tends to treat input as a bag of concepts and attempts to fill in the other missing concept crossmodally, leading to an unexpected zero-shot prediction. For example, when asked for the color of a lemon in an image, CLIP predicts ``purple'' if the image contains a lemon and an eggplant. We demonstrate the Concept Association Bias of CLIP by showing that CLIP's zero-shot classification performance greatly suffers when there is a strong concept association between an object (e.g. lemon) and an attribute (e.g. its color). On the other hand, when the association between object and attribute is weak, we do not see this phenomenon. Furthermore, we show that CAB is significantly mitigated when we enable CLIP to learn deeper structure across image and text embeddings by adding an additional Transformer on top of CLIP and fine-tuning it on VQA. We find that across such fine-tuned variants of CLIP, the strength of CAB in a model predicts how well it performs on VQA.
translated by 谷歌翻译
Sociability is essential for modern robots to increase their acceptability in human environments. Traditional techniques use manually engineered utility functions inspired by observing pedestrian behaviors to achieve social navigation. However, social aspects of navigation are diverse, changing across different types of environments, societies, and population densities, making it unrealistic to use hand-crafted techniques in each domain. This paper presents a data-driven navigation architecture that uses state-of-the-art neural architectures, namely Conditional Neural Processes, to learn global and local controllers of the mobile robot from observations. Additionally, we leverage a state-of-the-art, deep prediction mechanism to detect situations not similar to the trained ones, where reactive controllers step in to ensure safe navigation. Our results demonstrate that the proposed framework can successfully carry out navigation tasks regarding social norms in the data. Further, we showed that our system produces fewer personal-zone violations, causing less discomfort.
translated by 谷歌翻译
现在,合成视觉媒体发电和操纵的加速增长已经达到了引起重大关注并对社会造成巨大恐吓的地步。当务之急需要自动检测网络涉及虚假数字内容,并避免危险人造信息的传播以应对这种威胁。在本文中,我们利用和比较了两种手工制作的功能(Sift和Hog)以及两种深层特征(Xpection和CNN+RNN),以进行深层捕获检测任务。当训练集和测试集之间存在不匹配时,我们还会检查这些功能的性能。评估是对著名的FaceForensics ++数据集进行的,该数据集包含四个子数据集,深盘,face2face,faceswap和neuralTextures。最好的结果来自Xception,当训练和测试集都来自同一子数据库时,精度可能会超过99 \%。相比之下,当训练集不匹配测试集时,结果急剧下降。这种现象揭示了创建通用深击检测系统的挑战。
translated by 谷歌翻译
变压器体系结构在许多最新应用程序中取得了显着进展。然而,尽管他们取得了成功,但现代变形金刚依赖于自我发挥的机制,其时间和空间复杂性在输入的长度上是二次的。已经提出了几种方法来加快自我注意力的机制以实现次级运行时间。但是,这些作品中的绝大多数并不伴随着严格的错误保证。在这项工作中,我们在许多情况下就自我注意的计算复杂性建立了下限。我们证明,自我注意力的时间复杂性在输入长度上必定是二次的,除非强烈的指数时间假设(SETH)是错误的。即使注意力计算仅执行大约和各种注意力机制,该论点也存在。作为对我们的下限的补充,我们表明确实可以使用有限的泰勒级数在线性时间中近似点产物自我发作,而成本依赖于多项式顺序。
translated by 谷歌翻译
徽标检索是一个具有挑战性的问题,因为与图像检索任务相比,相似性的定义更为主观,并且已知相似性的集合非常稀缺。为了应对这一挑战,在本文中,我们提出了一种简单但有效的基于细分市场的增强策略,以引入人工相似的徽标,以训练徽标检索的深层网络。在这种新颖的增强策略中,我们首先在徽标中找到细分市场,并在细分市场上应用旋转,缩放和颜色变化等转换,这与传统的图像级增强策略不同。此外,我们评估最近引入的基于排名的损失函数Smooth-AP是否是学习徽标检索相似性的更好方法。在大规模的METU商标数据集上,我们表明(i)基于细分市场的增强策略与基线模型或图像级增强策略相比提高了检索性能,并且(ii)平滑 - AP的表现确实比徽标的常规损失更好恢复。
translated by 谷歌翻译
由于交通的固有复杂性和不确定性,自主驾驶决策是一项具有挑战性的任务。例如,相邻的车辆可能随时改变其车道或超越,以通过慢速车辆或帮助交通流量。预期周围车辆的意图,估算其未来状态并将其整合到自动化车辆的决策过程中,可以提高复杂驾驶场景中自动驾驶的可靠性。本文提出了一种基于预测的深入强化学习(PDRL)决策模型,该模型在公路驾驶决策过程中考虑了周围车辆的操纵意图。该模型是使用真实流量数据训练的,并通过模拟平台在各种交通条件下进行了测试。结果表明,与深入的增强学习(DRL)模型相比,提出的PDRL模型通过减少碰撞数量来改善决策绩效,从而导致更安全的驾驶。
translated by 谷歌翻译
现代机器学习模型使用大型数据集使用越来越多的参数(GPT-3参数1750亿参数),以获得更好的性能。更大的是常态。光学计算已被恢复为通过执行线性操作的同时降低电力的光学加速器的大规模计算的潜在解决方案。但是,要用光实现有效的计算,在光学上而不是电子上创建和控制非线性仍然是一个挑战。这项研究探讨了一种储层计算方法(RC)方法,通过该方法,在绝缘体上的Linbo3中的14毫米长的几种模式波导被用作复杂的非线性光学处理器。数据集在飞秒脉冲的频谱上进行数字编码,然后在波导中启动。输出频谱非线性取决于输入。我们通过实验表明,与非转换数据相比,使用波导的输出谱提高了几个数据库的分类精度,使用来自波导的输出频谱具有784个参数的简单数字线性分类器,约为10 $ \%$。相比之下,必须具有40000个参数的深数字神经网络(NN)才能达到相同的准确性。将参数的数量减少$ \ sim $ 50,这说明了紧凑的光RC方法可以与深数字NN一起执行。
translated by 谷歌翻译
夫妻通常在一起管理慢性疾病,管理层对患者及其浪漫伴侣造成了情感上的伤害。因此,认识到日常生活中每个伴侣的情绪可以提供对他们在慢性疾病管理中的情感健康的见解。当前,评估每个伴侣的情绪的过程是手动,时间密集和昂贵的。尽管夫妻之间存在着关于情感识别的作品,但这些作品都没有使用夫妻在日常生活中的互动中收集的数据。在这项工作中,我们收集了85小时(1,021个5分钟样本)现实世界多模式智能手表传感器数据(语音,心率,加速度计和陀螺仪)和自我报告的情绪数据(n = 612)(13个伙伴)(13)夫妻)在日常生活中管理2型糖尿病。我们提取了生理,运动,声学和语言特征,以及训练有素的机器学习模型(支持向量机和随机森林),以识别每个伴侣的自我报告的情绪(价和唤醒)。我们最佳模型的结果比偶然的结果更好,唤醒和价值分别为63.8%和78.1%。这项工作有助于建立自动情绪识别系统,最终使伙伴能够监视他们在日常生活中的情绪,并能够提供干预措施以改善其情感幸福感。
translated by 谷歌翻译