管理折扣促销活动(“ Markdown”)是经营电子商务业务的重要组成部分,这里的效率低下可能会严重阻碍零售商的盈利能力。解决此问题的传统方法在很大程度上取决于价格弹性建模。但是,价格弹性建模的部分信息性质,以及保护盈利能力的不可谈判的责任,意味着机器学习从业人员经常必须经过巨大的时间来定义衡量离线模型质量的策略。面对这一点,许多零售商依靠基于规则的方法,因此可以通过机器学习来捕获的盈利能力获得可观的收益。在本文中,我们介绍了两个新颖的端到端降价管理系统,以优化零售商旅程的不同阶段的赌注。第一个系统“ ITHAX”制定了无需估算的理性供应方定价策略,并且可以用作“冷启动”解决方案,以收集降价数据,同时保持收入控制。第二个系统“ Prosotheus”为价格弹性提供了一个完整的降价优化的框架。我们详细描述了特定的建模和验证程序,在我们的经验中,这对于建立在现实世界中稳健性能的系统至关重要。与我们经验丰富的运营团队在受控的在线测试中做出的决策相比,这两种降级系统都具有卓越的盈利能力,相对于手动策略,改善了86%(Promotheus)和79%(ITHAX)。这些系统已被部署以在ASOS.com上管理Markdown,并且可以在各种零售电子商务环境中进行价格优化的价格优化。
translated by 谷歌翻译
磁共振光谱成像(MRSI)是量化体内代谢物的必不可少的工具,但是低空间分辨率限制了其临床应用。基于深度学习的超分辨率方法为改善MRSI的空间分辨率提供了有希望的结果,但是与实验获得的高分辨率图像相比,超级分辨图像通常是模糊的。已经使用生成对抗网络进行了尝试,以提高图像视觉质量。在这项工作中,我们考虑了另一种类型的生成模型,即基于流的模型,与对抗网络相比,训练更稳定和可解释。具体而言,我们提出了一个基于流动的增强器网络,以提高超分辨率MRSI的视觉质量。与以前的基于流的模型不同,我们的增强器网络包含了来自其他图像模式(MRI)的解剖信息,并使用可学习的基础分布。此外,我们施加指南丢失和数据一致性丢失,以鼓励网络在保持高忠诚度的同时以高视觉质量生成图像。从25名高级神经胶质瘤患者获得的1H-MRSI数据集上进行的实验表明,我们的增强子网络的表现优于对抗网络和基线基线方法。我们的方法还允许视觉质量调整和不确定性估计。
translated by 谷歌翻译
在试图在为人类建立的世界中执行有用任务的类人形机器人时,我们解决了自主运动的问题。人形机器人计划和控制算法在崎rough地形上行走的算法变得越来越有能力。同时,市售的深度摄像机已经变得越来越准确,而GPU计算已成为AI研究中的主要工具。在本文中,我们提出了一个新建造的行为控制系统,用于实现快速,自主,两足步行,而无需暂停或审议。我们使用最近发表的快速平面区域感知算法,基于高度图的身体路径计划器,A*脚步计划器和基于动量的步行控制器来实现这一目标。我们将这些元素放在一起,形成一个由现代软件开发实践和仿真工具支持的行为控制系统。
translated by 谷歌翻译
内核Stein差异(KSD)是一种基于内核的广泛使用概率指标之间差异的非参数量度。它通常在用户从候选概率度量中收集的样本集合的情况下使用,并希望将它们与指定的目标概率度量进行比较。 KSD的一个有用属性是,它可以仅从候选度量的样本中计算出来,并且不知道目标度量的正常化常数。 KSD已用于一系列设置,包括合适的测试,参数推断,MCMC输出评估和生成建模。当前KSD方法论的两个主要问题是(i)超出有限维度欧几里得环境之外的适用性以及(ii)缺乏影响KSD性能的清晰度。本文提供了KSD的新频谱表示,这两种补救措施都使KSD适用于希尔伯特(Hilbert)评估数据,并揭示了内核和Stein oterator Choice对KSD的影响。我们通过在许多合成数据实验中对各种高斯和非高斯功能模型进行拟合优度测试来证明所提出的方法的功效。
translated by 谷歌翻译
在建立工程基础设施的预测模型时,提出了人群级分析来解决数据稀疏性。利用可解释的层次贝叶斯方法和操作车队数据,域专业知识是自然编码(并适当共享)在不同的子组之间,代表(i)使用型,(ii)组件或(iii)操作条件。具体而言,利用领域专业知识来通过假设(和先前的分布)来限制模型,从而使该方法可以自动共享相似资产之间的信息,从而改善了对风电场中卡车机队和权力预测的生存分析。在每个资产管理示例中,在合并的推理中学习了一组相关的功能,以学习人口模型。当允许子型在层次结构中的不同级别共享相关信息时,参数估计得到改善。反过来,数据不完整的组会自动从数据丰富的组中借用统计强度。统计相关性使知识转移能够通过贝叶斯转移学习,并且可以检查相关性,以告知哪些资产共享有关哪些效果(即参数)的信息。两种案例研究的成功都证明了实践基础设施监测的广泛适用性,因为该方法自然适应了不同原位示例的可解释的车队模型。
translated by 谷歌翻译
多对比度MRI(MC-MRI)捕获了多种互补成像方式,以帮助放射决策。鉴于需要降低多次收购的时间成本,当前的深度加速MRI重建网络集中于利用多个对比度之间的冗余。但是,现有的作品在很大程度上受到了配对数据和/或过度昂贵的完全采样的MRI序列的监督。此外,重建网络通常依赖于卷积体系结构,这些卷积体系结构在建模远程相互作用的能力上受到限制,并可能导致良好的解剖学细节的次优恢复。对于这些目的,我们提出了一个双域自我监督的变压器(DSFORMER),用于加速MC-MRI重建。 DSFormer开发了一个深层条件级联变压器(DCCT),该变压器由几个级联的Swin Transformer重建网络(SWINRN)组成,该网络(SWINRN)在两种深层调理策略下训练,以实现MC-MRI信息共享。我们进一步提出了DCCT的双域(图像和K空间)自我监督的学习策略,以减轻获取完全采样的培训数据的成本。 DSFormer会生成高保真重建,从而超过电流完全监督的基线。此外,我们发现,通过全面监督或我们提出的双域自学训练,DSFORMER可以实现几乎相同的性能。
translated by 谷歌翻译
Proteins are fundamental biological entities that play a key role in life activities. The amino acid sequences of proteins can be folded into stable 3D structures in the real physicochemical world, forming a special kind of sequence-structure data. With the development of Artificial Intelligence (AI) techniques, Protein Representation Learning (PRL) has recently emerged as a promising research topic for extracting informative knowledge from massive protein sequences or structures. To pave the way for AI researchers with little bioinformatics background, we present a timely and comprehensive review of PRL formulations and existing PRL methods from the perspective of model architectures, pretext tasks, and downstream applications. We first briefly introduce the motivations for protein representation learning and formulate it in a general and unified framework. Next, we divide existing PRL methods into three main categories: sequence-based, structure-based, and sequence-structure co-modeling. Finally, we discuss some technical challenges and potential directions for improving protein representation learning. The latest advances in PRL methods are summarized in a GitHub repository https://github.com/LirongWu/awesome-protein-representation-learning.
translated by 谷歌翻译
Learning efficient and interpretable policies has been a challenging task in reinforcement learning (RL), particularly in the visual RL setting with complex scenes. While neural networks have achieved competitive performance, the resulting policies are often over-parameterized black boxes that are difficult to interpret and deploy efficiently. More recent symbolic RL frameworks have shown that high-level domain-specific programming logic can be designed to handle both policy learning and symbolic planning. However, these approaches rely on coded primitives with little feature learning, and when applied to high-dimensional visual scenes, they can suffer from scalability issues and perform poorly when images have complex object interactions. To address these challenges, we propose \textit{Differentiable Symbolic Expression Search} (DiffSES), a novel symbolic learning approach that discovers discrete symbolic policies using partially differentiable optimization. By using object-level abstractions instead of raw pixel-level inputs, DiffSES is able to leverage the simplicity and scalability advantages of symbolic expressions, while also incorporating the strengths of neural networks for feature learning and optimization. Our experiments demonstrate that DiffSES is able to generate symbolic policies that are simpler and more and scalable than state-of-the-art symbolic RL methods, with a reduced amount of symbolic prior knowledge.
translated by 谷歌翻译
Deep learning-based 3D human pose estimation performs best when trained on large amounts of labeled data, making combined learning from many datasets an important research direction. One obstacle to this endeavor are the different skeleton formats provided by different datasets, i.e., they do not label the same set of anatomical landmarks. There is little prior research on how to best supervise one model with such discrepant labels. We show that simply using separate output heads for different skeletons results in inconsistent depth estimates and insufficient information sharing across skeletons. As a remedy, we propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. The discovered latent 3D points capture the redundancy among skeletons, enabling enhanced information sharing when used for consistency regularization. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model, which outperforms prior work on a range of benchmarks, including the challenging 3D Poses in the Wild (3DPW) dataset. Our code and models are available for research purposes.
translated by 谷歌翻译
This short paper compiles the big ideas behind some philosophical views, definitions, and examples of causality. This collection spans the realms of the four commonly adopted approaches to causality: Humes regularity, counterfactual, manipulation, and mechanisms. This short review is motivated by presenting simplified views and definitions and then supplements them with examples from various fields, including economics, education, medicine, politics, physics, and engineering. It is the hope that this short review comes in handy for new and interested readers with little knowledge of causality and causal inference.
translated by 谷歌翻译