从一组给定对象中计算共识对象是机器学习和模式识别的核心问题。一种流行的方法是使用广义中位数将其作为优化问题。先前的方法(例如原型和距离嵌入方法)将对象转换为矢量空间,解决该空间中的广义中值问题,并反相转换回原始空间。这两种方法已成功地应用于广泛的对象域,其中广义的中值问题具有固有的高计算复杂性(通常为$ \ Mathcal {np} $ - 硬),因此需要近似解决方案。以前,在计算中使用了显式嵌入方法,这通常不反映对象之间的空间关系。在这项工作中,我们介绍了一个基于内核的广义中间框架,该框架适用于积极的确定和无限核。该框架计算对象与其在内核空间中的广义中位数之间的关系,而无需显式嵌入。我们表明,与使用易于计算的内核相比,对象之间的空间关系比在显式矢量空间中更准确地表示,并在三个不同域的数据集上展示了广义中值计算的出色性能。我们的工作产生的软件工具箱可公开使用,以鼓励其他研究人员探索广义的中位数计算和应用。
translated by 谷歌翻译
瀑布推荐系统(RS)是移动应用程序中RS的流行形式,是推荐的项目流,这些项目由连续页面组成,可以通过滚动浏览。在Waterfall RS中,当用户完成浏览页面时,Edge(例如,手机)将向Cloud Server发送请求,以获取新的建议页面,称为分页请求机制。 RSS通常将大量项目放入一页中,以减少众多分页请求中的过度资源消耗,但是,这将降低RSS根据用户的实时兴趣及时续订建议的能力,并导致贫穷的用户。经验。直观地,在页面内插入其他请求以更新频率的建议可以减轻问题。但是,以前的尝试,包括非自适应策略(例如,统一插入请求)最终会导致资源过度消费。为此,我们设想了一项名为智能请求策略设计(IRSD)的Edge Intelligence的新学习任务。它旨在通过根据用户的实时意图确定请求插入的适当情况来提高瀑布RSS的有效性。此外,我们提出了一种新的自适应请求插入策略的范式,名为基于Uplift的On-Ending Smart请求框架(AdareQuest)。 AdareQuest 1)通过将实时行为与基于基于注意力的神经网络相匹配的历史兴趣来捕获用户意图的动态变化。 2)估计根据因果推理插入的请求带来的用户购买的反事实提升。 3)通过在在线资源约束下最大化效用功能来确定最终请求插入策略。我们在离线数据集和在线A/B测试上进行了广泛的实验,以验证AdareQuest的有效性。
translated by 谷歌翻译
短期负载预测(STLF)在电力交易市场的运营中起着重要作用。考虑到对数据隐私的日益关注,在最近的研究中,越来越多地采用了联合学习(FL)来培训公用事业公司(UCS)的STLF模型。令人鼓舞的是,在批发市场中,由于发电厂(PPS)直接访问UCS数据并不现实,因此FL绝对是可行的解决方案,可以为PPS获得准确的STLF模型。但是,由于FL的分布性质和UC之间的激烈竞争,缺陷越来越多,导致STLF模型的性能差,表明仅采用FL是不够的。在本文中,我们提出了一种DRL辅助方法,缺陷感知的联合软性参与者 - 批评者(DearFSAC),以稳健地训练PPS的准确的STLF模型,以预测精确的短期公用事业需求。首先。我们仅使用历史负载数据和时间数据设计了基于长期短期内存(LSTM)的STLF模型。此外,考虑到缺陷发生的不确定性,采用了深入的增强学习(DRL)算法来通过减轻缺陷引起的模型退化来协助FL。此外,为了更快的FL训练融合,自动编码器设计用于缩小尺寸和上载模型的质量评估。在模拟中,我们在2019年验证了赫尔辛基UCS的真实数据的方法。结果表明,无论是否发生缺陷,DearFSAC都比所有其他方法都胜过所有其他方法。
translated by 谷歌翻译
近年来3D成像技术的进步已经允许大型标本的越来越高的分辨率体积图像。由数百个千兆字节的结果数据集大小调用了图像处理领域的新可扩展和内存有效方法,其中已经进行了一些进度。同时,在特定数据大小的可用性和生成相关地面真理数据方面,这些新方法对这些新方法的定量评估难以。在本文中,我们介绍了一种算法框架,可用于有效地生成测试(和地面真理)卷数据,即使以流式方式也是如此。由于提出的嵌套扫描算法快速,它可用于根据需求生成测试数据。我们分析了所提出的算法的渐近运行时间,并将其实验与替代方法以及假设的最佳案例基线方法进行比较。在一个案例研究中,该框架应用于流行的Vascusynth软件,用于血管图像的产生,使得能够有效地产生较大的内存体积,通过产生千氧克素(1TB)图像来证明。所呈现的框架的实现以修改版的Vascusynth和用于实验评估的代码的形式在线提供。此外,测试数据生成过程已集成到流行的卷渲染和处理框架Voreen中。
translated by 谷歌翻译
工作记忆(WM)表示在脑海中存储的信息,是人类认知领域的一个基本研究主题。可以监测大脑的电活动的脑电图(EEG)已被广泛用于测量WM的水平。但是,关键的挑战之一是个体差异可能会导致无效的结果,尤其是当既定模型符合陌生主题时。在这项工作中,我们提出了一个具有空间注意力(CS-DASA)的跨主题深层适应模型,以概括跨科目的工作负载分类。首先,我们将EEG时间序列转换为包含空间,光谱和时间信息的多帧EEG图像。首先,CS-DASA中的主题共享模块从源和目标主题中接收多帧的EEG图像数据,并学习了共同的特征表示。然后,在特定于主题的模块中,实现了最大平均差异,以测量重现的内核希尔伯特空间中的域分布差异,这可以为域适应增加有效的罚款损失。此外,采用主题对象的空间注意机制专注于目标图像数据的判别空间特征。在包含13个受试者的公共WM EEG数据集上进行的实验表明,所提出的模型能够达到比现有最新方法更好的性能。
translated by 谷歌翻译
图像分割的随机沃克方法是半自动图像分割的流行工具,尤其是在生物医学领域。但是,它的线性渐近运行时间和内存要求使应用于增加大小不切实际的3D数据集。我们提出了一个分层框架,据我们所知,这是克服这些随机沃克算法的限制并实现sublinear的运行时间和持续的内存复杂性的尝试。该框架的目的是 - 与基线​​方法相比,而不是改善细分质量,以使交互式分割在核心外数据集中成为可能。确认该方法的合成数据和CT-ORG数据集进行了定量评估,其中确认了算法运行时间的预期改进,同时确认了高分段质量。即使对于数百千兆字节的大小,增量(即互动更新)运行时间也已在标准PC上以秒为单位。在一个小案例研究中,证明了当前生物医学研究对大型现实世界的适用性。在广泛使用的卷渲染和处理软件Voreen(https://www.uni-muenster.de/voreen/)的5.2版5.2版中,介绍方法的实现公开可用。
translated by 谷歌翻译
This paper focuses on designing efficient models with low parameters and FLOPs for dense predictions. Even though CNN-based lightweight methods have achieved stunning results after years of research, trading-off model accuracy and constrained resources still need further improvements. This work rethinks the essential unity of efficient Inverted Residual Block in MobileNetv2 and effective Transformer in ViT, inductively abstracting a general concept of Meta-Mobile Block, and we argue that the specific instantiation is very important to model performance though sharing the same framework. Motivated by this phenomenon, we deduce a simple yet efficient modern \textbf{I}nverted \textbf{R}esidual \textbf{M}obile \textbf{B}lock (iRMB) for mobile applications, which absorbs CNN-like efficiency to model short-distance dependency and Transformer-like dynamic modeling capability to learn long-distance interactions. Furthermore, we design a ResNet-like 4-phase \textbf{E}fficient \textbf{MO}del (EMO) based only on a series of iRMBs for dense applications. Massive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, \eg, our EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass \textbf{SoTA} CNN-/Transformer-based models, while trading-off the model accuracy and efficiency well.
translated by 谷歌翻译
We aim to bridge the gap between our common-sense few-sample human learning and large-data machine learning. We derive a theory of human-like few-shot learning from von-Neuman-Landauer's principle. modelling human learning is difficult as how people learn varies from one to another. Under commonly accepted definitions, we prove that all human or animal few-shot learning, and major models including Free Energy Principle and Bayesian Program Learning that model such learning, approximate our theory, under Church-Turing thesis. We find that deep generative model like variational autoencoder (VAE) can be used to approximate our theory and perform significantly better than baseline models including deep neural networks, for image recognition, low resource language processing, and character recognition.
translated by 谷歌翻译
Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot, generalized zero-shot and open set recognition using a unified framework. Specifically, we propose a weighted maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms. Distance constraints ensure that labeled samples are projected closer to their correct prototypes, in the embedding space, than to others. We illustrate that resulting model shows improvements in supervised, zero-shot, generalized zero-shot, and large open set recognition, with up to 310K class vocabulary on Animal with Attributes and ImageNet datasets.
translated by 谷歌翻译
We consider infinite horizon Markov decision processes (MDPs) with fast-slow structure, meaning that certain parts of the state space move "fast" (and in a sense, are more influential) while other parts transition more "slowly." Such structure is common in real-world problems where sequential decisions need to be made at high frequencies, yet information that varies at a slower timescale also influences the optimal policy. Examples include: (1) service allocation for a multi-class queue with (slowly varying) stochastic costs, (2) a restless multi-armed bandit with an environmental state, and (3) energy demand response, where both day-ahead and real-time prices play a role in the firm's revenue. Models that fully capture these problems often result in MDPs with large state spaces and large effective time horizons (due to frequent decisions), rendering them computationally intractable. We propose an approximate dynamic programming algorithmic framework based on the idea of "freezing" the slow states, solving a set of simpler finite-horizon MDPs (the lower-level MDPs), and applying value iteration (VI) to an auxiliary MDP that transitions on a slower timescale (the upper-level MDP). We also extend the technique to a function approximation setting, where a feature-based linear architecture is used. On the theoretical side, we analyze the regret incurred by each variant of our frozen-state approach. Finally, we give empirical evidence that the frozen-state approach generates effective policies using just a fraction of the computational cost, while illustrating that simply omitting slow states from the decision modeling is often not a viable heuristic.
translated by 谷歌翻译