TU Dresden www.cityscapes-dataset.net train/val -fine annotation -3475 images train -coarse annotation -20 000 images test -fine annotation -1525 images
translated by 谷歌翻译
Recent years have witnessed a growth in mathematics for deep learning--which seeks a deeper understanding of the concepts of deep learning with mathematics, and explores how to make it more robust--and deep learning for mathematics, where deep learning algorithms are used to solve problems in mathematics. The latter has popularised the field of scientific machine learning where deep learning is applied to problems in scientific computing. Specifically, more and more neural network architectures have been developed to solve specific classes of partial differential equations (PDEs). Such methods exploit properties that are inherent to PDEs and thus solve the PDEs better than classical feed-forward neural networks, recurrent neural networks, and convolutional neural networks. This has had a great impact in the area of mathematical modeling where parametric PDEs are widely used to model most natural and physical processes arising in science and engineering, In this work, we review such methods and extend them for parametric studies as well as for solving the related inverse problems. We equally proceed to show their relevance in some industrial applications.
translated by 谷歌翻译
We analyze the problem of detecting tree rings in microscopy images of shrub cross sections. This can be regarded as a special case of the instance segmentation task with several particularities such as the concentric circular ring shape of the objects and high precision requirements due to which existing methods don't perform sufficiently well. We propose a new iterative method which we term Iterative Next Boundary Detection (INBD). It intuitively models the natural growth direction, starting from the center of the shrub cross section and detecting the next ring boundary in each iteration step. In our experiments, INBD shows superior performance to generic instance segmentation methods and is the only one with a built-in notion of chronological order. Our dataset and source code are available at http://github.com/alexander-g/INBD.
translated by 谷歌翻译
Human-technology collaboration relies on verbal and non-verbal communication. Machines must be able to detect and understand the movements of humans to facilitate non-verbal communication. In this article, we introduce ongoing research on human activity recognition in intralogistics, and show how it can be applied in industrial settings. We show how semantic attributes can be used to describe human activities flexibly and how context informantion increases the performance of classifiers to recognise them automatically. Beyond that, we present a concept based on a cyber-physical twin that can reduce the effort and time necessary to create a training dataset for human activity recognition. In the future, it will be possible to train a classifier solely with realistic simulation data, while maintaining or even increasing the classification performance.
translated by 谷歌翻译
This paper shows the implementation of reinforcement learning (RL) in commercial flowsheet simulator software (Aspen Plus V12) for designing and optimising a distillation sequence. The aim of the SAC agent was to separate a hydrocarbon mixture in its individual components by utilising distillation. While doing so it tries to maximise the profit produced by the distillation sequence. All actions of the agent were set by the SAC agent in Python and communicated in Aspen Plus via an API. Here the distillation column was simulated by use of the build-in RADFRAC column. With this a connection was established for data transfer between Python and Aspen and the agent succeeded to show learning behaviour, while increasing profit. Although results were generated, the use of Aspen was slow (190 hours) and Aspen was found unsuitable for parallelisation. This makes that Aspen is incompatible for solving RL problems. Code and thesis are available at https://github.com/lollcat/Aspen-RL
translated by 谷歌翻译
具有波束成型的天线阵列在较高的载波频率下克服了高空间路径损耗。但是,必须正确对齐光束,以确保用户设备(UE)辐射(并接收)最高功率。尽管有一些方法可以通过某种形式的层次搜索来详尽地搜索最佳光束,但它们可能很容易返回具有小型梁增益的本地最佳解决方案。其他方法通过利用上下文信息(例如UE的位置或来自相邻基站(BS)的信息的位置)来解决此问题,但是计算和传达此附加信息的负担可能很高。迄今为止,基于机器学习的方法受到随附的培训,性能监控和部署复杂性的影响,从而阻碍了其规模的应用。本文提出了一种解决初始光束发现问题的新方法。它是可扩展的,易于调整和实施。我们的算法基于一个推荐系统,该系统基于培训数据集将组(即UES)和偏好(即来自代码簿中的光束)关联。每当需要提供新的UE时,我们的算法都会返回此用户群集中的最佳光束。我们的仿真结果证明了我们方法的效率和鲁棒性,不仅在单个BS设置中,而且在需要几个BS之间协调的设置中。我们的方法在给定任务中始终优于标准基线算法。
translated by 谷歌翻译
为了了解材料特性的起源,三轴光谱仪(TAS)处的中子散射实验通过测量其动量(Q)和能量(E)空间中的强度分布来研究样品中的磁和晶格激发。但是,TAS实验的高需求和有限的光束时间可用性提出了自然的问题,即我们是否可以提高其效率或更好地利用实验者的时间。实际上,使用TAS,有许多科学问题需要在Q-E空间的特定区域中搜索感兴趣的信号,但是当手动完成时,这是耗时且效率低下的,因为测量点可能会放置在此类的无信息区域中作为背景。主动学习是一种有前途的通用机器学习方法,可以迭代地检测自主信号的信息区域,即不受人类干扰,从而避免了不必要的测量并加快实验。此外,自主模式允许实验者在此期间专注于其他相关任务。我们在本文中描述的方法利用了对数高斯过程,由于对数转换,该过程在信号区域中具有最大的近似不确定性。因此,将不确定性最大化为采集功能,因此直接产生了信息测量的位置。我们证明了我们方法对在Themal Tas Eiger(PSI)进行真实中子实验的结果的好处,以及在合成环境中基准的结果,包括许多不同的激发。
translated by 谷歌翻译
转移学习或域适应性与机器学习问题有关,在这些问题中,培训和测试数据可能来自可能不同的概率分布。在这项工作中,我们在Russo和Xu发起的一系列工作之后,就通用错误和转移学习算法的过量风险进行了信息理论分析。我们的结果也许表明,也许正如预期的那样,kullback-leibler(kl)Divergence $ d(\ mu || \ mu')$在$ \ mu $和$ \ mu'$表示分布的特征中起着重要作用。培训数据和测试测试。具体而言,我们为经验风险最小化(ERM)算法提供了概括误差上限,其中两个分布的数据在训练阶段都可用。我们进一步将分析应用于近似的ERM方法,例如Gibbs算法和随机梯度下降方法。然后,我们概括了与$ \ phi $ -Divergence和Wasserstein距离绑定的共同信息。这些概括导致更紧密的范围,并且在$ \ mu $相对于$ \ mu' $的情况下,可以处理案例。此外,我们应用了一套新的技术来获得替代的上限,该界限为某些学习问题提供了快速(最佳)的学习率。最后,受到派生界限的启发,我们提出了Infoboost算法,其中根据信息测量方法对源和目标数据的重要性权重进行了调整。经验结果表明了所提出的算法的有效性。
translated by 谷歌翻译
增强学习(RL)是多能管理系统的有前途的最佳控制技术。它不需要先验模型 - 降低了前期和正在进行的项目特定工程工作,并且能够学习基础系统动力学的更好表示。但是,香草RL不能提供约束满意度的保证 - 导致其在安全至关重要的环境中产生各种不安全的互动。在本文中,我们介绍了两种新颖的安全RL方法,即SafeFallback和Afvafe,其中安全约束配方与RL配方脱钩,并且提供了硬构成满意度,可以保证在培训(探索)和开发过程中(近距离) )最佳政策。在模拟的多能系统案例研究中,我们已经表明,这两种方法均与香草RL基准相比(94,6%和82,8%,而35.5%)和香草RL基准相比明显更高的效用(即有用的政策)开始。提出的SafeFallback方法甚至可以胜过香草RL基准(102,9%至100%)。我们得出的结论是,这两种方法都是超越RL的安全限制处理技术,正如随机代理所证明的,同时仍提供坚硬的保证。最后,我们向I.A.提出了基本的未来工作。随着更多数据可用,改善约束功能本身。
translated by 谷歌翻译
由自我发项层组成的大型,预训练的神经网络(变形金刚)最近在几种语音情绪识别(SER)数据集上取得了最新的结果。这些模型通常以自我监督的方式进行预训练,以提高自动语音识别性能,从而了解语言信息。在这项工作中,我们研究了在Ser微调过程中利用此信息的程度。使用基于开源工具的可重现方法,我们在改变文本的情感时综合了韵律中性的语音话语。变压器模型的价预测对正面和负面情绪含量以及否定性非常反应,但对增强剂或还原器不反应,而这些语言特征都没有影响唤醒或优势。这些发现表明,变形金刚可以成功利用语言信息来改善其价预测,并且应将语言分析包括在其测试中。
translated by 谷歌翻译