卷积神经网络(CNN)在各种应用域中达到高精度,但需要大量的计算和产生昂贵的数据移动。在交易准确性时降低这些成本的一种方法是体重和/或激活单词长度的减少。因此,层的混合精液量化可以在充气设计空间时产生更有效的结果。在这项工作中,我们提出了一种深入的定量方法,以考虑给定FPGA的硬件资源有限的硬件资源,以有效地探索设计空间。我们的整体探索方法从架构到逻辑级别垂直穿越各种设计入门级别,并横向涵盖从处理元素到数据流的优化,以获得有效的混合过度CNN加速器。我们由此产生的硬件加速器实施了真正的混合精确操作,从而有效地执行了层和频道量化的CNN。映射进料和身份转换连接混合精液CNNS导致竞争精度 - 触及折衷方案:245帧/s,RESNET-18的最高率为87.48%,resNet-18的前5位准确性和92.9%的前5位准确性,1.13 TOPS/TOPS/TOPS/TOPS/TOPS/ S分别用于Resnet-152。因此,与各自的浮点基线相比,参数所需的内存足迹减少了4.9倍和9.4倍。
translated by 谷歌翻译
A generalized understanding of protein dynamics is an unsolved scientific problem, the solution of which is critical to the interpretation of the structure-function relationships that govern essential biological processes. Here, we approach this problem by constructing coarse-grained molecular potentials based on artificial neural networks and grounded in statistical mechanics. For training, we build a unique dataset of unbiased all-atom molecular dynamics simulations of approximately 9 ms for twelve different proteins with multiple secondary structure arrangements. The coarse-grained models are capable of accelerating the dynamics by more than three orders of magnitude while preserving the thermodynamics of the systems. Coarse-grained simulations identify relevant structural states in the ensemble with comparable energetics to the all-atom systems. Furthermore, we show that a single coarse-grained potential can integrate all twelve proteins and can capture experimental structural features of mutated proteins. These results indicate that machine learning coarse-grained potentials could provide a feasible approach to simulate and understand protein dynamics.
translated by 谷歌翻译
The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi.
translated by 谷歌翻译
Counterfactual Explanations are becoming a de-facto standard in post-hoc interpretable machine learning. For a given classifier and an instance classified in an undesired class, its counterfactual explanation corresponds to small perturbations of that instance that allows changing the classification outcome. This work aims to leverage Counterfactual Explanations to detect the important decision boundaries of a pre-trained black-box model. This information is used to build a supervised discretization of the features in the dataset with a tunable granularity. Using the discretized dataset, a smaller, therefore more interpretable Decision Tree can be trained, which, in addition, enhances the stability and robustness of the baseline Decision Tree. Numerical results on real-world datasets show the effectiveness of the approach in terms of accuracy and sparsity compared to the baseline Decision Tree.
translated by 谷歌翻译
We introduce a new benchmark dataset, Placenta, for node classification in an underexplored domain: predicting microanatomical tissue structures from cell graphs in placenta histology whole slide images. This problem is uniquely challenging for graph learning for a few reasons. Cell graphs are large (>1 million nodes per image), node features are varied (64-dimensions of 11 types of cells), class labels are imbalanced (9 classes ranging from 0.21% of the data to 40.0%), and cellular communities cluster into heterogeneously distributed tissues of widely varying sizes (from 11 nodes to 44,671 nodes for a single structure). Here, we release a dataset consisting of two cell graphs from two placenta histology images totalling 2,395,747 nodes, 799,745 of which have ground truth labels. We present inductive benchmark results for 7 scalable models and show how the unique qualities of cell graphs can help drive the development of novel graph neural network architectures.
translated by 谷歌翻译
全球越来越多的大学将各种形式的在线学习和混合学习作为其学术课程的一部分。此外,由于199年大流行而造成的最新变化导致在线教育的重要性和无处不在。电子学习的主要优点之一不仅是改善学生的学习经验并扩大教育前景,而且还可以通过学习分析来洞悉学生的学习过程。这项研究有助于通过以下方式改善和理解电子学习过程的主题。首先,我们证明可以根据从学生的行为数据中得出的顺序模式来构建准确的预测模型,这些模式能够在课程的早期识别出表现不佳的学生。其次,我们通过研究是否应根据特定于课程的顺序模式或基于更一般的行为模式的几个课程来构建每个课程的预测模型,从而调查了建立此类预测模型的特异性征用性权衡。最后,我们提出了一种捕获行为数据中时间方面的方法,并分析了其对模型预测性能的影响。我们改进的序列分类技术的结果能够以高度准确性来预测学生的表现,而对于课程特异性模型的结果达到了90%。
translated by 谷歌翻译
视频稳定是现代采集设备通常应用的相机内处理。尽管显着提高了所得视频的视觉质量,但已显示此类操作通常阻碍对视频信号的法医分析。实际上,通常基于照片响应不均匀性(PRNU)的采集来源的正确识别应受到稳定阶段应用于每个帧的转换的估计。已经提出了许多用于处理此问题的技术,但是由于反转参数空间的网格搜索,通常会遭受高计算负担。我们的工作试图通过利用图形处理单元(GPU)(通常用于深度学习应用程序)的平行化功能来减轻这些缺点,这是在稳定框架倒置的框架内。此外,我们建议利用SIFT功能{估计相机动量和}%,以识别较少稳定的时间段,从而实现更准确的识别分析,并有效地初始化连续帧的框架参数搜索。在合并基准数据集上进行的实验证实了拟议方法在减少所需的计算时间和提高源识别精度方面的有效性。 {代码可在\ url {https://github.com/amontib/gpu-prnu-sift}}中获得。
translated by 谷歌翻译
我们提出了一种学习在某些协变量反事实变化下不变的预测因子的方法。当预测目标受到不应影响预测因子输出的协变量影响时,此方法很有用。例如,对象识别模型可能会受到对象本身的位置,方向或比例的影响。我们解决了训练预测因素的问题,这些预测因素明确反对反对这种协变量的变化。我们提出了一个基于条件内核均值嵌入的模型不合稳定项,以在训练过程中实现反事实的不变性。我们证明了我们的方法的健全性,可以处理混合的分类和连续多变量属性。关于合成和现实世界数据的经验结果证明了我们方法在各种环境中的功效。
translated by 谷歌翻译
反事实解释为从机器学习模型中获得预期结果的方法提供了信息。但是,这种解释对基础模型的某些现实世界变化(例如,重新训练模型,更改的超参数等)并不强大,质疑其在多种应用程序中的可靠性,例如信用贷款。在这项工作中,我们提出了一种新颖的策略 - 我们称之为Robx,以生成基于树的合奏,例如XGBoost的强大反事实。基于树的合奏在强大的反事实生成中提出了其他挑战,例如,它们具有非平滑和非差异的目标函数,并且在非常相似的数据上,它们可以在RETOR下的参数空间中进行很多更改。我们首先引入了一种新颖的指标(我们称之为反事实稳定性),该指标试图量化反事实的鲁棒性将是为了模拟重新训练下的变化,并具有理想的理论属性。我们提出的策略ROBX使用任何反事实生成方法(基本方法),并通过使用我们的度量反事实稳定性迭代地完善基本方法生成的反事实来搜索强大的反事实。我们将ROBX的性能与基于基准数据集的流行反事实生成方法(对于基于树的合奏)进行了比较。结果表明,我们的策略会产生反事实,这些反事实是强大的(实际模型更改后的有效性近100%),并且在现有最新方法上也是现实的(就局部异常因素而言)。
translated by 谷歌翻译
聋哑人在看直播电视时经常依靠字幕来聋。实时电视字幕通过使用各种标题评估指标的监管机构评估。但是,字幕评估指标通常不会由DHH用户的偏好或字幕有多有意义。有必要构建字幕评估指标,以考虑成绩单中单词的相对重要性。我们在现有语料库中的两种类型的单词嵌入和人类宣传的单词形象分数之间进行了相关分析。我们发现,使用BERT生成的归一化情境化嵌入与基于Word2VEC的单词嵌入更好的与手动注释的重要性分数更好的相关性。我们提供了单词嵌入及其人类宣布的重要性分数的配对。我们还通过训练单词重要性模型来提供概念验证效用,在6级单词重要性分类任务中达到0.57的F1得分。
translated by 谷歌翻译