研究深度学习的鲁棒性的一个主要挑战是定义了给定神经网络（NN）不变的``毫无意义''扰动集。关于鲁棒性的大多数工作隐含地将人作为参考模型来定义这种扰动。我们的工作通过使用另一个参考NN来定义给定的NN应该不变，从而使对任何NN的依赖概述对任何NN的依赖。这使得衡量鲁棒性等同于衡量两个NN共享不稳定的程度，我们提出了一种称为搅拌的措施。搅拌重新调整现有的表示相似性措施，使其适合衡量共享的不稳定。使用我们的度量，我们能够深入了解共享的不断增长，随着重量初始化，体系结构，损失功能和培训数据集的变化如何变化。我们的实现可在：\ url {https://github.com/nvedant07/stir}中获得。

Online bipartite-matching platforms are ubiquitous and find applications in important areas such as crowdsourcing and ridesharing. In the most general form, the platform consists of three entities: two sides to be matched and a platform operator that decides the matching. The design of algorithms for such platforms has traditionally focused on the operator's (expected) profit. Since fairness has become an important consideration that was ignored in the existing algorithms a collection of online matching algorithms have been developed that give a fair treatment guarantee for one side of the market at the expense of a drop in the operator's profit. In this paper, we generalize the existing work to offer fair treatment guarantees to both sides of the market simultaneously, at a calculated worst case drop to operator profit. We consider group and individual Rawlsian fairness criteria. Moreover, our algorithms have theoretical guarantees and have adjustable parameters that can be tuned as desired to balance the trade-off between the utilities of the three sides. We also derive hardness results that give clear upper bounds over the performance of any algorithm.

我们争辩说，当模型学习\ texit {good}表示时，我们应该有一个有价值的视角是，应该由人类类似地观察到模型的类似表示的输入。我们使用\ textit {表示反转}来生成映射到相同模型表示的多个输入，然后通过人类调查量化这些输入的感知相似性。我们的方法产生了模型与人类感知对齐的程度的衡量标准。使用这种对准度量，我们评估了用各种学习范例（例如〜监督和自我监督学习）和不同培训损失（标准和强大培训）培训的模型。我们的研究结果表明，具有人类感知的表现的对齐提供了对模型的品质的有用的额外见解。例如，我们发现与人类感知的对齐可以用作模型对不同模型对输出冲突的输入的模型预测的信任的量度。我们还发现模型的各种属性，如其架构，培训范式，培训损失和数据增强在与人类感知一致的学习陈述中起着重要作用。

This paper proposes a novel controller framework that provides trajectory tracking for an Aerial Manipulator (AM) while ensuring the safe operation of the system under unknown bounded disturbances. The AM considered here is a 2-DOF (degrees-of-freedom) manipulator rigidly attached to a UAV. Our proposed controller structure follows the conventional inner loop PID control for attitude dynamics and an outer loop controller for tracking a reference trajectory. The outer loop control is based on the Model Predictive Control (MPC) with constraints derived using the Barrier Lyapunov Function (BLF) for the safe operation of the AM. BLF-based constraints are proposed for two objectives, viz. 1) To avoid the AM from colliding with static obstacles like a rectangular wall, and 2) To maintain the end effector of the manipulator within the desired workspace. The proposed BLF ensures that the above-mentioned objectives are satisfied even in the presence of unknown bounded disturbances. The capabilities of the proposed controller are demonstrated through high-fidelity non-linear simulations with parameters derived from a real laboratory scale AM. We compare the performance of our controller with other state-of-the-art MPC controllers for AM.

We introduce M-VADER: a diffusion model (DM) for image generation where the output can be specified using arbitrary combinations of images and text. We show how M-VADER enables the generation of images specified using combinations of image and text, and combinations of multiple images. Previously, a number of successful DM image generation algorithms have been introduced that make it possible to specify the output image using a text prompt. Inspired by the success of those models, and led by the notion that language was already developed to describe the elements of visual contexts that humans find most important, we introduce an embedding model closely related to a vision-language model. Specifically, we introduce the embedding model S-MAGMA: a 13 billion parameter multimodal decoder combining components from an autoregressive vision-language model MAGMA and biases finetuned for semantic search.

We are interested in neurosymbolic systems consisting of a high-level symbolic layer for explainable prediction in terms of human-intelligible concepts; and a low-level neural layer for extracting symbols required to generate the symbolic explanation. Real data is often imperfect meaning that even if the symbolic theory remains unchanged, we may still need to address the problem of mapping raw data to high-level symbols, each time there is a change in the data acquisition environment or equipment. Manual (re-)annotation of the raw data each time this happens is laborious and expensive; and automated labelling methods are often imperfect, especially for complex problems. NEUROLOG proposed the use of a semantic loss function that allows an existing feature-based symbolic model to guide the extraction of feature-values from raw data, using `abduction'. However, the experiments demonstrating the use of semantic loss through abduction appear to rely heavily on a domain-specific pre-processing step that enables a prior delineation of feature locations in the raw data. We examine the use of semantic loss in domains where such pre-processing is not possible, or is not obvious. We show that without any prior information about the features, the NEUROLOG approach can continue to predict accurately even with substantially incorrect feature predictions. We show also that prior information about the features in the form of even imperfect pre-training can help correct this situation. These findings are replicated on the original problem considered by NEUROLOG, without the use of feature-delineation. This suggests that symbolic explanations constructed for data in a domain could be re-used in a related domain, by `feature-adaptation' of pre-trained neural extractors using the semantic loss function constrained by abductive feedback.

“感应头”是注意力头，它实现了一种简单的算法来完成令牌序列，例如[a] [b] ... [a] - > [b]。在这项工作中，我们提供了一个假设的初步和间接证据，即诱导头可能构成大型大型变压器模型中所有“文本学习”中大多数的机制（即减少在增加代币指数时损失的损失）。我们发现，诱导头在与秘密学习能力突然急剧上的急剧上升的位置完全相同，这是训练损失的颠簸。我们提出了六种互补的证据，认为诱导头可能是任何大小的变压器模型中一般性内部学习的机理来源。对于仅关注的小型模型，我们提供了有力的因果证据。对于具有MLP的较大模型，我们提供相关证据。

数据驱动的湍流建模正在经历数据科学算法和硬件开发后的兴趣激增。我们讨论了一种使用可区分物理范式的方法，该方法将已知的物理学与机器学习结合起来，以开发汉堡湍流的闭合模型。我们将1D汉堡系统视为一种原型测试问题，用于建模以对流为主的湍流问题中未解决的术语。我们训练一系列模型，这些模型在后验损失函数上结合了不同程度的物理假设，以测试模型在一系列系统参数（包括粘度，时间和网格分辨率）上的疗效。我们发现，以部分微分方程形式的归纳偏差的约束模型包含已知物理或现有闭合方法会产生高度数据效率，准确和可推广的模型，并且表现优于最先进的基准。以物理信息形式添加结构还为模型带来了一定程度的解释性，可能为封闭建模的未来提供了垫脚石。

最近，电子学习平台已经发展为学生可以发表疑问（用智能手机拍摄的快照）并在几分钟内解决的地方。但是，这些平台的质量差异很大的学生寄出疑问的数量显着增加，这不仅给教师导航解决方案带来了挑战，还增加了每个疑问的分辨率时间。两者都是不可接受的，因为高度怀疑的时间阻碍了学生学习进度的学习。这需要方法来自动识别存储库中是否存在类似的疑问，然后将其作为验证和与学生沟通的合理解决方案。监督的学习技术（如暹罗建筑）需要标签来识别比赛，这是不可行的，因为标签稀缺且昂贵。因此，在这项工作中，我们基于通过自我监督技术学到的表示形式开发了符合范式的标签不足的疑问。在BYOL的先前理论见解（Bootstrap您自己的潜在空间）的基础上，我们提出了Custom Byol，将特定于域特异性的增强与对比目标结合在一起，而不是各种适当构建的数据视图。结果强调，与BYOL和监督学习实例相比，Custom Byol分别将TOP-1匹配精度提高了大约6 \％和5 \％。我们进一步表明，基于BYOL的学习实例在标准杆上的性能比人类标签更好。

随着摩尔的定律饱和和丹纳德的缩放率撞到了墙壁，传统的冯·诺伊曼系统无法为CNN等计算密集型算法提供GFLOPS/WATT。非常规计算方法的最新趋势使我们希望为此类算法设计高能节能的计算系统。神经形态计算是一种有希望的方法，其脑启发的电路，新兴技术的使用和低功率性质。研究人员使用各种新型技术，例如回忆录，硅光子学，鳍片和碳纳米管来演示神经形态计算机。但是，从神经形态的逻辑设计开始并进行建筑模拟的灵活CAD工具尚未得到证明，以支持这种有希望的范式的兴起。在这个项目中，我们旨在构建Neucasl，这是一个基于OpenSource Python的完整系统CAD框架，用于神经形态逻辑设计，电路模拟以及系统性能和可靠性估计。据我们所知，这是同类产品中的第一个。