机器人关节产生的建模轨迹是复杂的,并且需要轨迹生成,聚类和分类等高级活动。Disentagled代表学习承诺有助于学习的进步,但他们尚未在机器人生成的轨迹中进行评估。在本文中,我们在从3 DOF机器人手臂产生的1M机器人轨迹的数据集上评估三个解除挂起的VAES($ \β$ -VAE,DECORR VAE和新的$ \ BETA $ -DECORR VAE)。我们发现基于去形的标准,轨迹质量和与地理潜在特征的相关性,基于去相关的配方表现了最佳。我们希望这些结果增加了机器人控制中无监督学习的使用。
translated by 谷歌翻译
本文提出了一种从示威(LFD)中进行深度机器人学习的新型概率方法。深度运动原语(DMP)是确定性的LFD模型,可直接将视觉信息映射到机器人轨迹中。本文扩展了DMP,并提出了一个深层概率模型,该模型将视觉信息映射到有效的机器人轨迹的分布中。提出了导致轨迹精度最高水平的结构,并与现有方法进行了比较。此外,本文介绍了一种用于学习域特异性潜在特征的新型培训方法。我们展示了在实验室的草莓收集任务中提出的概率方法和新颖的潜在空间学习的优势。实验结果表明,潜在空间学习可以显着改善模型预测性能。提出的方法允许从分布中采样轨迹并优化机器人轨迹以满足次级目标,例如避免碰撞。
translated by 谷歌翻译
We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon β-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.
translated by 谷歌翻译
We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images. E2C consists of a deep generative model, belonging to the family of variational autoencoders, that learns to generate image trajectories from a latent space in which the dynamics is constrained to be locally linear. Our model is derived directly from an optimal control formulation in latent space, supports long-term prediction of image sequences and exhibits strong performance on a variety of complex control problems.
translated by 谷歌翻译
变化自动编码器(VAE)最近已用于对复杂密度分布的无监督分离学习。存在许多变体,以鼓励潜在空间中的分解,同时改善重建。但是,在达到极低的重建误差和高度分离得分之间,没有人同时管理权衡。我们提出了一个普遍的框架,可以在有限的优化下应对这一挑战,并证明它在平衡重建时,它优于现有模型的最先进模型。我们介绍了三个可控的拉格朗日超级参数,以控制重建损失,KL差异损失和相关度量。我们证明,重建网络中的信息最大化等于在合理假设和约束放松下摊销过程中的信息最大化。
translated by 谷歌翻译
带有变异自动编码器(VAE)的学习分解表示通常归因于损失的正则化部分。在这项工作中,我们强调了数据与损失的重建项之间的相互作用,这是VAE中解散的主要贡献者。我们注意到,标准化的基准数据集的构建方式有利于学习似乎是分解的表示形式。我们设计了一个直观的对抗数据集,该数据集利用这种机制破坏了现有的最新分解框架。最后,我们提供了一种解决方案,可以通过修改重建损失来实现分离,从而影响VAES如何感知数据点之间的距离。
translated by 谷歌翻译
变异自动编码器(VAE)学习脱离表示表示的能力使它们在实际应用中很受欢迎。但是,他们的行为尚未完全理解。例如,何时提供分离的表示形式或后倒塌的问题仍然是积极研究的领域。尽管如此,尚无对VAE学到的表示形式进行层次比较,这将进一步了解这些模型。在本文中,我们使用代表性相似性技术研究VAE的内部行为。具体而言,使用CKA和Procrustes相似性,我们发现编码器的表示早在解码器之前就学会了,并且此行为独立于超参数,学习目标和数据集。此外,在超参数和学习目标之间,编码器的表示形式与均值和方差相似。
translated by 谷歌翻译
The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we provide a sober look at recent progress in the field and challenge some common assumptions. We first theoretically show that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases on both the models and the data. Then, we train more than 12 000 models covering most prominent methods and evaluation metrics in a reproducible large-scale experimental study on seven different data sets. We observe that while the different methods successfully enforce properties "encouraged" by the corresponding losses, well-disentangled models seemingly cannot be identified without supervision. Furthermore, increased disentanglement does not seem to lead to a decreased sample complexity of learning for downstream tasks. Our results suggest that future work on disentanglement learning should be explicit about the role of inductive biases and (implicit) supervision, investigate concrete benefits of enforcing disentanglement of the learned representations, and consider a reproducible experimental setup covering several data sets.
translated by 谷歌翻译
在本研究中,我们提出了一种模拟绘图/研磨轨迹的局部和全局特征的方法,通过分层变分自动化器(VAES)。通过将两个单独训练的VAE模型组合在分层结构中,可以为本地和全局特征产生高再现性的轨迹。分层生成网络使得能够生成具有相对较少量的训练数据的高阶轨迹。模拟和实验结果表明了该方法的泛化性能。此外,我们确认可以通过改变学习模型的组合来生成过去从未学到过的新轨迹。
translated by 谷歌翻译
近年来,由于其对复杂分布进行建模的能力,深层生成模型引起了越来越多的兴趣。在这些模型中,变异自动编码器已被证明是计算有效的,并且在多个领域中产生了令人印象深刻的结果。在这一突破之后,为了改善原始出版物而进行了广泛的研究,从而导致各种不同的VAE模型响应不同的任务。在本文中,我们介绍了Pythae,这是一个多功能的开源Python库,既可以提供统一的实现和专用框架,允许直接,可重现且可靠地使用生成自动编码器模型。然后,我们建议使用此库来执行案例研究基准测试标准,在其中我们介绍并比较了19个生成自动编码器模型,代表了下游任务的一些主要改进,例如图像重建,生成,分类,聚类,聚类和插值。可以在https://github.com/clementchadebec/benchmark_vae上找到开源库。
translated by 谷歌翻译
For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills must handle raw sensory input such as images. In this paper, we propose an algorithm that acquires such general-purpose skills by combining unsupervised representation learning and reinforcement learning of goal-conditioned policies. Since the particular goals that might be required at test-time are not known in advance, the agent performs a self-supervised "practice" phase where it imagines goals and attempts to achieve them. We learn a visual representation with three distinct purposes: sampling goals for self-supervised practice, providing a structured transformation of raw sensory inputs, and computing a reward signal for goal reaching. We also propose a retroactive goal relabeling scheme to further improve the sample-efficiency of our method. Our off-policy algorithm is efficient enough to learn policies that operate on raw image observations and goals for a real-world robotic system, and substantially outperforms prior techniques. * Equal contribution. Order was determined by coin flip.
translated by 谷歌翻译
When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features into a single objective. If they try to do both at once from input designed to teach the full reward function, it is easy to end up with a representation that contains spurious correlations in the data, which fails to generalize to new settings. Instead, our ultimate goal is to enable robots to identify and isolate the causal features that people actually care about and use when they represent states and behavior. Our idea is that we can tune into this representation by asking users what behaviors they consider similar: behaviors will be similar if the features that matter are similar, even if low-level behavior is different; conversely, behaviors will be different if even one of the features that matter differs. This, in turn, is what enables the robot to disambiguate between what needs to go into the representation versus what is spurious, as well as what aspects of behavior can be compressed together versus not. The notion of learning representations based on similarity has a nice parallel in contrastive learning, a self-supervised representation learning technique that maps visually similar data points to similar embeddings, where similarity is defined by a designer through data augmentation heuristics. By contrast, in order to learn the representations that people use, so we can learn their preferences and objectives, we use their definition of similarity. In simulation as well as in a user study, we show that learning through such similarity queries leads to representations that, while far from perfect, are indeed more generalizable than self-supervised and task-input alternatives.
translated by 谷歌翻译
我们提出了一种自我监督的方法,以解除高维数据变化的因素,该因素不依赖于基本变化概况的先验知识(例如,没有关于要提取单个潜在变量的数量或分布的假设)。在我们称为nashae的方法中,通过促进从所有其他编码元素中恢复的每个编码元素和恢复的元素的信息之间的差异,在标准自动编码器(AE)的低维潜在空间中完成了高维的特征分离。通过将其作为AE和回归网络合奏之间的Minmax游戏来有效地促进了分解,从而估算了一个元素,该元素以对所有其他元素的观察为条件。我们将我们的方法与使用现有的分离指标进行定量比较。此外,我们表明Nashae具有提高的可靠性和增加的能力来捕获学习潜在表示中的显着数据特征。
translated by 谷歌翻译
神经网络在许多科学学科中发挥着越来越大的作用,包括物理学。变形AutoEncoders(VAE)是能够表示在低维潜空间中的高维数据的基本信息,该神经网络具有概率解释。特别是所谓的编码器网络,VAE的第一部分,其将其输入到潜伏空间中的位置,另外在该位置的方差方面提供不确定性信息。在这项工作中,介绍了对AutoEncoder架构的扩展,渔民。在该架构中,借助于Fisher信息度量,不使用编码器中的附加信息信道生成潜在空间不确定性,而是从解码器导出。这种架构具有来自理论观点的优点,因为它提供了从模型的直接不确定性量化,并且还考虑不确定的交叉相关。我们可以通过实验表明,渔民生产比可比较的VAE更准确的数据重建,并且其学习性能也明显较好地缩放了潜伏空间尺寸的数量。
translated by 谷歌翻译
$ \ beta $ -vae是对变形的自身额外转换器的后续技术,提出了在VAE损失中的KL分歧项的特殊加权,以获得解除戒备的表示。即使在玩具数据集和有意义的情况下,甚至在玩具数据集上也是脆弱的学习,难以找到的难以找到的。在这里,我们调查原来的$ \β$ -VAE纸,并向先前获得的结果添加证据表明其缺乏可重复性。我们还进一步扩展了模型的实验,并在分析中包括进一步更复杂的数据集。我们还为$ \β$ -VAE模型实施了FID评分度量,并得出了对所获得的结果的定性分析。我们结束了关于可能进行的未来调查的简要讨论,以增加对索赔的更具稳健性。
translated by 谷歌翻译
We present a detailed study on Variational Autoencoders (VAEs) for anomalous jet tagging at the Large Hadron Collider. By taking in low-level jet constituents' information, and training with background QCD jets in an unsupervised manner, the VAE is able to encode important information for reconstructing jets, while learning an expressive posterior distribution in the latent space. When using the VAE as an anomaly detector, we present different approaches to detect anomalies: directly comparing in the input space or, instead, working in the latent space. In order to facilitate general search approaches such as bump-hunt, mass-decorrelated VAEs based on distance correlation regularization are also studied. We find that the naive mass-decorrelated VAEs fail at maintaining proper detection performance, by assigning higher probabilities to some anomalous samples. To build a performant mass-decorrelated anomalous jet tagger, we propose the Outlier Exposed VAE (OE-VAE), for which some outlier samples are introduced in the training process to guide the learned information. OE-VAEs are employed to achieve two goals at the same time: increasing sensitivity of outlier detection and decorrelating jet mass from the anomaly score. We succeed in reaching excellent results from both aspects. Code implementation of this work can be found at https://github.com/taolicheng/VAE-Jet
translated by 谷歌翻译
合理和可控3D人类运动动画的创建是一个长期存在的问题,需要对技术人员艺术家进行手动干预。目前的机器学习方法可以半自动化该过程,然而,它们以显着的方式受到限制:它们只能处理预期运动的单个轨迹,该轨迹排除了对输出的细粒度控制。为了缓解该问题,我们在多个轨迹表示为具有缺失关节的姿势的空间和时间内将未来姿态预测的问题重构为姿势完成。我们表明这种框架可以推广到设计用于未来姿态预测的其他神经网络。曾经在该框架中培训,模型能够从任何数量的轨迹预测序列。我们提出了一种新颖的变形金刚架构,Trajevae,在这个想法上建立了一个,为3D人类动画提供了一个多功能框架。我们展示了Trajevae提供比基于轨迹的参考方法和方法基于过去的姿势。我们还表明,即使仅提供初始姿势,它也可以预测合理的未来姿势。
translated by 谷歌翻译
高维数据的歧管假设假设数据是通过改变从低维潜在空间获得的一组参数而生成的。深层生成模型(DGM)被广泛用于以无监督的方式学习数据表示。 DGM使用瓶颈体系结构(例如变异自动编码器(VAE))参数化数据空间中的基础低维歧管。 VAE的瓶颈尺寸被视为取决于数据集的超参数,并在广泛调整后在设计时间固定。由于大多数实际数据集的内在维度尚不清楚,因此固有维度与选择为超参数的潜在维度之间存在不匹配。这种不匹配可能会对表示形式学习和样本生成任务的模型性能产生负面影响。本文提出了相关性编码网络(RENS):一种新型的基于VAE的概率VAE框架,该框架在潜在空间中使用自动相关性确定(ARD)来学习数据特定的瓶颈维度。每个潜在维度的相关性是直接从数据以及使用随机梯度下降的其他模型参数以及适合非高斯先验的重新聚集技巧的其他模型参数中学到的。我们利用深处的概念来捕获数据和潜在空间中的置换统计属性,以确定相关性。所提出的框架是一般且灵活的,可用于最先进的VAE模型,该模型利用正规化器在潜在空间中施加特定特征(例如,脱离)。通过对合成和公共图像数据集进行了广泛的实验,我们表明,所提出的模型了解了相关的潜在瓶颈维度,而不会损害样品的表示和发电质量。
translated by 谷歌翻译
配备具有推断人类意图的能力的机器人是有效合作的重要前提。对于这种目标的大多数计算方法采用了概率的推理,以回收机器人感知状态的“意图”的分布。然而,这些方法通常假设人类意图的特定任务概念(例如标记目标)是先验的。为了克服这一限制,我们提出了解离序列聚类变分性Autiachoder(Discvae),该群集框架可以用于以无监督的方式学习意图的这种分布。 DiscVae利用最近在无监督的学习方面的进步导出了顺序数据的解除不诚格潜在表示,从时间不变的全局方面分离时变化的本地特征。虽然与前面的解剖学框架不同,但是所提出的变体也涉及分立变量,以形成潜在混合模型,并使全局序列概念进行聚类,例如,观察到人类行为的意图。为了评估Discvae,首先使用弹跳数字和2D动画的视频数据集来验证其从未标记序列发现类的容量。然后,我们从机器人轮椅上进行的现实世界机器人交互实验报告结果。我们的调查结果引入了推断离散变量如何与人类意图一致,从而用于改善协作设置的帮助,例如共享控制。
translated by 谷歌翻译
我们采用变化性AutoEncoders从单粒子Anderson杂质模型谱函数的数据集中提取物理洞察。培训AutoEncoders以查找低维,潜在的空间表示,其忠实地表征培训集的每个元素,通过重建误差测量。变形式自动化器,标准自动化器的概率概括,进一步条件促进了高度可解释的特征。在我们的研究中,我们发现学习的潜在变量与众所周知的众所周知,但非活动的参数强烈关联,这些参数表征了安德森杂质模型中的紧急行为。特别地,一种潜在的可变变量与粒子孔不对称相关,而另一个潜在的变量与杂质模型中动态产生的低能量尺度接近一对一的对应关系。使用符号回归,我们将此变量模拟了该变量作为已知的裸物理输入参数和“重新发现”的kondo温度的非扰动公式。我们开发的机器学习管道表明了一种通用方法,它开启了发现其他物理系统中的新领域知识的机会。
translated by 谷歌翻译