我们研究限制的Boltzmann机器(RBM)提取的特征当它在各种温度下旋转模型的自旋配置时训练。使用训练的RBM,我们获得了自旋配置的迭代重建(RBM流量)的流程,并在某些情况下发现流程接近阶段转换点$ T = T_C $ IN ISING模型。由于在重建配置中强调提取的特征,因此在这种固定点处的配置应该除了提取的特征之外。然后,我们研究了固定点对各种参数的依赖性,并猜测RBM流程的固定点处于相位过渡点的状态。我们还通过分析训练RBM的重量矩阵来提供猜想的支持证据。
translated by 谷歌翻译
Event cameras are novel bio-inspired sensors that offer advantages over traditional cameras (low latency, high dynamic range, low power, etc.). Optical flow estimation methods that work on packets of events trade off speed for accuracy, while event-by-event (incremental) methods have strong assumptions and have not been tested on common benchmarks that quantify progress in the field. Towards applications on resource-constrained devices, it is important to develop optical flow algorithms that are fast, light-weight and accurate. This work leverages insights from neuroscience, and proposes a novel optical flow estimation scheme based on triplet matching. The experiments on publicly available benchmarks demonstrate its capability to handle complex scenes with comparable results as prior packet-based algorithms. In addition, the proposed method achieves the fastest execution time (> 10 kHz) on standard CPUs as it requires only three events in estimation. We hope that our research opens the door to real-time, incremental motion estimation methods and applications in real-world scenarios.
translated by 谷歌翻译
Event cameras are emerging vision sensors and their advantages are suitable for various applications such as autonomous robots. Contrast maximization (CMax), which provides state-of-the-art accuracy on motion estimation using events, may suffer from an overfitting problem called event collapse. Prior works are computationally expensive or cannot alleviate the overfitting, which undermines the benefits of the CMax framework. We propose a novel, computationally efficient regularizer based on geometric principles to mitigate event collapse. The experiments show that the proposed regularizer achieves state-of-the-art accuracy results, while its reduced computational complexity makes it two to four times faster than previous approaches. To the best of our knowledge, our regularizer is the only effective solution for event collapse without trading off runtime. We hope our work opens the door for future applications that unlocks the advantages of event cameras.
translated by 谷歌翻译
期望 - 最大化(EM)算法是一种简单的元叠加,当观察到的数据中缺少测量值或数据由可观察到的数据组成时,它已多年来用作统计推断的方法。它的一般属性进行了充分的研究,而且还有无数方法将其应用于个人问题。在本文中,我们介绍了$ em $ $ and算法,EM算法的信息几何公式及其扩展和应用程序以及各种问题。具体而言,我们将看到,可以制定一个异常稳定推理算法,用于计算通道容量的算法,概率单纯性的参数估计方法,特定的多变量分析方法,例如概率模型中的主要组件分析和模态回归中的主成分分析,基质分解和学习生成模型,这些模型最近从几何学角度引起了深度学习的关注。
translated by 谷歌翻译
事件摄像机对场景动态做出响应,并提供了估计运动的优势。遵循最近基于图像的深度学习成就,事件摄像机的光流估计方法急于将基于图像的方法与事件数据相结合。但是,由于它们具有截然不同的属性,因此需要几个改编(数据转换,损失功能等)。我们开发了一种原则性的方法来扩展对比度最大化框架以估算仅事件的光流。我们研究关键要素:如何设计目标函数以防止过度拟合,如何扭曲事件以更好地处理遮挡,以及如何改善与多规模原始事件的收敛性。有了这些关键要素,我们的方法在MVSEC基准的无监督方法中排名第一,并且在DSEC基准上具有竞争力。此外,我们的方法使我们能够在这些基准测试中揭露地面真相流的问题,并在将其转移到无监督的学习环境中时会产生出色的结果。我们的代码可在https://github.com/tub-rip/event_based_optility_flow上找到
translated by 谷歌翻译
上下文最大化(CMAX)是一个框架,可在几个基于事件的计算机视觉任务(例如自我移动或光流估计)上提供最新结果。但是,它可能会遇到一个称为事件崩溃的问题,这是一种不希望的解决方案,其中事件被扭曲成太少的像素。由于先前的工作在很大程度上忽略了这个问题或提议的解决方法,因此必须详细分析这种现象。我们的工作证明了事件以最简单的形式崩溃,并通过使用基于差异几何和物理学的时空变形的第一原理提出了崩溃指标。我们通过实验表明,公开可用的数据集表明,拟议的指标减轻了事件崩溃,并且不会损害良好的扭曲。据我们所知,与其他方法相比,基于提议的指标的正规化器是唯一有效的解决方案,可以防止在考虑的实验环境中发生事件崩溃。我们希望这项工作激发了进一步的研究,以应对更复杂的翘曲模型。
translated by 谷歌翻译
从任务到任务的顺序训练正在成为深度学习应用中的主要对象之一,例如持续学习和转移学习。尽管如此,在训练有素的模型的性能改善或恶化的情况下,它仍然不清楚。为了深化我们对顺序培训的理解,本研究在不断学习的可解下的案例中提供了对概括性表现的理论分析。我们考虑神经切线内核(NTK)制度中的神经网络,以便将目标功能从任务中持续学习到任务,并通过使用核心脊的统计机械分析来调查延伸的核心脊的回归。我们首先表现出从积极转移到负转移的特征过渡。高于特定临界值的更类似的目标可以实现随后的任务的积极知识转移,而灾难性的遗忘也会发生,即使具有非常相似的目标。接下来,我们调查持续学习的变体,其中模型在多个任务中学习相同的目标函数。即使对于同一目标,训练型模型也会显示一些转移和遗忘,具体取决于每个任务的样本大小。我们可以保证泛化误差从任务单调减少到相同的样本大小的任务,而不平衡样本大小会降低泛化。我们分别指的是自我知识转移和遗忘的这些改善和恶化,并经验证实它们的深神经网络的现实培训。
translated by 谷歌翻译
The purpose of this study is to introduce new design-criteria for next-generation hyperparameter optimization software. The criteria we propose include (1) define-by-run API that allows users to construct the parameter search space dynamically, (2) efficient implementation of both searching and pruning strategies, and (3) easy-to-setup, versatile architecture that can be deployed for various purposes, ranging from scalable distributed computing to light-weight experiment conducted via interactive interface. In order to prove our point, we will introduce Optuna, an optimization software which is a culmination of our effort in the development of a next generation optimization software. As an optimization software designed with define-by-run principle, Optuna is particularly the first of its kind. We will present the design-techniques that became necessary in the development of the software that meets the above criteria, and demonstrate the power of our new design through experimental results and real world applications. Our software is available under the MIT license (https://github.com/pfnet/optuna/).
translated by 谷歌翻译