We introduce a novel way to incorporate prior information into (semi-) supervised non-negative matrix factorization, which we call differentiable dictionary search. It enables general, highly flexible and principled modelling of mixtures where non-linear sources are linearly mixed. We study its behavior on an audio decomposition task, and conduct an extensive, highly controlled study of its modelling capabilities.
translated by 谷歌翻译
This paper describes several improvements to a new method for signal decomposition that we recently formulated under the name of Differentiable Dictionary Search (DDS). The fundamental idea of DDS is to exploit a class of powerful deep invertible density estimators called normalizing flows, to model the dictionary in a linear decomposition method such as NMF, effectively creating a bijection between the space of dictionary elements and the associated probability space, allowing a differentiable search through the dictionary space, guided by the estimated densities. As the initial formulation was a proof of concept with some practical limitations, we will present several steps towards making it scalable, hoping to improve both the computational complexity of the method and its signal decomposition capabilities. As a testbed for experimental evaluation, we choose the task of frame-level piano transcription, where the signal is to be decomposed into sources whose activity is attributed to individual piano notes. To highlight the impact of improved non-linear modelling of sources, we compare variants of our method to a linear overcomplete NMF baseline. Experimental results will show that even in the absence of additional constraints, our models produce increasingly sparse and precise decompositions, according to two pertinent evaluation measures.
translated by 谷歌翻译
在2015年和2019年之间,地平线的成员2020年资助的创新培训网络名为“Amva4newphysics”,研究了高能量物理问题的先进多变量分析方法和统计学习工具的定制和应用,并开发了完全新的。其中许多方法已成功地用于提高Cern大型Hadron撞机的地图集和CMS实验所执行的数据分析的敏感性;其他几个人,仍然在测试阶段,承诺进一步提高基本物理参数测量的精确度以及新现象的搜索范围。在本文中,在研究和开发的那些中,最相关的新工具以及对其性能的评估。
translated by 谷歌翻译
我们从一组稀疏的光谱时间序列中构建了一个物理参数化的概率自动编码器(PAE),以学习IA型超新星(SNE IA)的内在多样性。 PAE是一个两阶段的生成模型,由自动编码器(AE)组成,该模型在使用归一化流(NF)训练后概率地解释。我们证明,PAE学习了一个低维的潜在空间,该空间可捕获人口内存在的非线性特征范围,并且可以直接从数据直接从数据中准确地对整个波长和观察时间进行精确模拟SNE IA的光谱演化。通过引入相关性惩罚项和多阶段训练设置以及我们的物理参数化网络,我们表明可以在训练期间分离内在和外在的可变性模式,从而消除了需要进行额外标准化的其他模型。然后,我们在SNE IA的许多下游任务中使用PAE进行越来越精确的宇宙学分析,包括自动检测SN Outliers,与数据分布一致的样本的产生以及在存在噪音和不完整数据的情况下解决逆问题限制宇宙距离测量。我们发现,与以前的研究相一致的最佳固有模型参数数量似乎是三个,并表明我们可以用$ 0.091 \ pm 0.010 $ mag标准化SNE IA的测试样本,该样本对应于$ 0.074 \ pm。 0.010 $ mag如果删除了特殊的速度贡献。训练有素的模型和代码在\ href {https://github.com/georgestein/supaernova} {github.com/georgestein/supaernova}上发布
translated by 谷歌翻译
Music discovery services let users identify songs from short mobile recordings. These solutions are often based on Audio Fingerprinting, and rely more specifically on the extraction of spectral peaks in order to be robust to a number of distortions. Few works have been done to study the robustness of these algorithms to background noise captured in real environments. In particular, AFP systems still struggle when the signal to noise ratio is low, i.e when the background noise is strong. In this project, we tackle this problematic with Deep Learning. We test a new hybrid strategy which consists of inserting a denoising DL model in front of a peak-based AFP algorithm. We simulate noisy music recordings using a realistic data augmentation pipeline, and train a DL model to denoise them. The denoising model limits the impact of background noise on the AFP system's extracted peaks, improving its robustness to noise. We further propose a novel loss function to adapt the DL model to the considered AFP system, increasing its precision in terms of retrieved spectral peaks. To the best of our knowledge, this hybrid strategy has not been tested before.
translated by 谷歌翻译
The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.
translated by 谷歌翻译
尽管近年来取得了惊人的进步,但最先进的音乐分离系统会产生具有显着感知缺陷的源估计,例如增加无关噪声或消除谐波。我们提出了一个后处理模型(MAKE听起来不错(MSG)后处理器),以增强音乐源分离系统的输出。我们将我们的后处理模型应用于最新的基于波形和基于频谱图的音乐源分离器,包括在训练过程中未见的分离器。我们对源分离器产生的误差的分析表明,波形模型倾向于引入更多高频噪声,而频谱图模型倾向于丢失瞬变和高频含量。我们引入了客观措施来量化这两种错误并显示味精改善了两种错误的源重建。众包主观评估表明,人类的听众更喜欢由MSG进行后处理的低音和鼓的来源估计。
translated by 谷歌翻译
Deep neural networks (DNN) techniques have become pervasive in domains such as natural language processing and computer vision. They have achieved great success in these domains in task such as machine translation and image generation. Due to their success, these data driven techniques have been applied in audio domain. More specifically, DNN models have been applied in speech enhancement domain to achieve denosing, dereverberation and multi-speaker separation in monaural speech enhancement. In this paper, we review some dominant DNN techniques being employed to achieve speech separation. The review looks at the whole pipeline of speech enhancement from feature extraction, how DNN based tools are modelling both global and local features of speech and model training (supervised and unsupervised). We also review the use of speech-enhancement pre-trained models to boost speech enhancement process. The review is geared towards covering the dominant trends with regards to DNN application in speech enhancement in speech obtained via a single speaker.
translated by 谷歌翻译
我们提出了一种新的四管齐下的方法,在文献中首次建立消防员的情境意识。我们构建了一系列深度学习框架,彼此之叠,以提高消防员在紧急首次响应设置中进行的救援任务的安全性,效率和成功完成。首先,我们使用深度卷积神经网络(CNN)系统,以实时地分类和识别来自热图像的感兴趣对象。接下来,我们将此CNN框架扩展了对象检测,跟踪,分割与掩码RCNN框架,以及具有多模级自然语言处理(NLP)框架的场景描述。第三,我们建立了一个深入的Q学习的代理,免受压力引起的迷失方向和焦虑,能够根据现场消防环境中观察和存储的事实来制定明确的导航决策。最后,我们使用了一种低计算无监督的学习技术,称为张量分解,在实时对异常检测进行有意义的特征提取。通过这些临时深度学习结构,我们建立了人工智能系统的骨干,用于消防员的情境意识。要将设计的系统带入消防员的使用,我们设计了一种物理结构,其中处理后的结果被用作创建增强现实的投入,这是一个能够建议他们所在地的消防员和周围的关键特征,这对救援操作至关重要在手头,以及路径规划功能,充当虚拟指南,以帮助迷彩的第一个响应者恢复安全。当组合时,这四种方法呈现了一种新颖的信息理解,转移和综合方法,这可能会大大提高消防员响应和功效,并降低寿命损失。
translated by 谷歌翻译
听诊器录制的胸部声音为新生儿的偏远有氧呼吸健康监测提供了机会。然而,可靠的监控需要高质量的心脏和肺部声音。本文介绍了新生胸部声音分离的新型非负基质分子(NMF)和非负矩阵协同分解(NMCF)方法。为了评估这些方法并与现有的单源分离方法进行比较,产生人工混合物数据集,包括心脏,肺和噪音。然后计算用于这些人造混合物的信噪比。这些方法也在现实世界嘈杂的新生儿胸部声音上进行测试,并根据生命符号估计误差评估,并在我们以前的作品中发达1-5的信号质量得分。此外,评估所有方法的计算成本,以确定实时处理的适用性。总的来说,所提出的NMF和NMCF方法都以2.7db到11.6db的下一个最佳现有方法而言,对于人工数据集,0.40至1.12的现实数据集的信号质量改进。发现10S记录的声音分离的中值处理时间为NMCF和NMF的342ms为28.3。由于稳定且稳健的性能,我们认为我们的提出方法可用于在真实的环境中弃绝新生儿心脏和肺部。提出和现有方法的代码可以在:https://github.com/egrooby-monash/heart-and-lung-sound-eparation。
translated by 谷歌翻译
The International Workshop on Reading Music Systems (WoRMS) is a workshop that tries to connect researchers who develop systems for reading music, such as in the field of Optical Music Recognition, with other researchers and practitioners that could benefit from such systems, like librarians or musicologists. The relevant topics of interest for the workshop include, but are not limited to: Music reading systems; Optical music recognition; Datasets and performance evaluation; Image processing on music scores; Writer identification; Authoring, editing, storing and presentation systems for music scores; Multi-modal systems; Novel input-methods for music to produce written music; Web-based Music Information Retrieval services; Applications and projects; Use-cases related to written music. These are the proceedings of the 3rd International Workshop on Reading Music Systems, held in Alicante on the 23rd of July 2021.
translated by 谷歌翻译
A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the parameterization of an easily invertible elementwise transformation, whose choice determines the flexibility of these models. Building upon recent work, we propose a fully-differentiable module based on monotonic rational-quadratic splines, which enhances the flexibility of both coupling and autoregressive transforms while retaining analytic invertibility. We demonstrate that neural spline flows improve density estimation, variational inference, and generative modeling of images.
translated by 谷歌翻译
即使机器学习算法已经在数据科学中发挥了重要作用,但许多当前方法对输入数据提出了不现实的假设。由于不兼容的数据格式,或数据集中的异质,分层或完全缺少的数据片段,因此很难应用此类方法。作为解决方案,我们提出了一个用于样本表示,模型定义和培训的多功能,统一的框架,称为“ Hmill”。我们深入审查框架构建和扩展的机器学习的多个范围范式。从理论上讲,为HMILL的关键组件的设计合理,我们将通用近似定理的扩展显示到框架中实现的模型所实现的所有功能的集合。本文还包含有关我们实施中技术和绩效改进的详细讨论,该讨论将在MIT许可下发布供下载。该框架的主要资产是其灵活性,它可以通过相同的工具对不同的现实世界数据源进行建模。除了单独观察到每个对象的一组属性的标准设置外,我们解释了如何在框架中实现表示整个对象系统的图表中的消息推断。为了支持我们的主张,我们使用框架解决了网络安全域的三个不同问题。第一种用例涉及来自原始网络观察结果的IoT设备识别。在第二个问题中,我们研究了如何使用以有向图表示的操作系统的快照可以对恶意二进制文件进行分类。最后提供的示例是通过网络中实体之间建模域黑名单扩展的任务。在所有三个问题中,基于建议的框架的解决方案可实现与专业方法相当的性能。
translated by 谷歌翻译
语音分离的目标是从单个麦克风记录中提取多个语音源。最近,随着大型数据集的深度学习和可用性的进步,言语分离已被制定为监督的学习问题。这些方法旨在使用监督学习算法,通常是深神经网络学习语音,扬声器和背景噪声的判别模式。监督语音分离中的一个持久问题正在为每个分离的语音信号找到正确的标签,称为标签置换歧义。置换歧义是指确定分离源和可用的单扬声器语音标签之间的输出标签分配的问题。计算分离误差需要找到最佳输出标签分配,后来用于更新模型的参数。最近,置换不变训练(PIT)已被证明是处理标签歧义问题的有希望的解决方案。但是,通过坑的输出标签分配的过度自信选择导致次优训练模型。在这项工作中,我们提出了一个概率的优化框架来解决坑中找到最佳输出标签分配的效率。然后,我们所提出的方法在折放不变训练(PIT)语音分离方法中使用的相同的长短期内存(LSTM)架构。我们的实验结果表明,所提出的方法优于传统的坑语音分离(P值$ <0.01 $),在信号到失真比(SDR)和干扰比中的失真率(SDR)和+ 1.5dB中的+ 1dB(SIR)。
translated by 谷歌翻译
$ \ Texit {Fermi} $数据中的银河系中多余(GCE)的两个领先假设是一个未解决的微弱毫秒脉冲条件(MSP)和暗物质(DM)湮灭。这些解释之间的二分法通常通过将它们建模为两个单独的发射组分来反映。然而,诸如MSP的点源(PSS)在超微弱的极限中具有统计变质的泊松发射(正式的位置,预期每个来源平均贡献远低于一个光子),导致可能提出问题的歧义如排放是否是PS样或性质中的泊松人。我们提出了一种概念上的新方法,以统一的方式描述PS和泊松发射,并且刚刚从此获得的结果中获得了对泊松组件的约束。为了实现这种方法,我们利用深度学习技术,围绕基于神经网络的方法,用于直方图回归,其表达量数量的不确定性。我们证明我们的方法对许多困扰先前接近的系统,特别是DM / PS误操作来稳健。在$ \ texit {fermi} $数据中,我们发现由$ \ sim4 \ times 10 ^ {-11} \ \ text {counts} \ {counts} \ text {counts} \ text {counts} \ \ text {cm} ^ { - 2} \ \ text {s} ^ { - 1} $(对应于$ \ sim3 - 4 $每pL期望计数),这需要$ n \ sim \ mathcal {o}( 10 ^ 4)$源来解释整个过剩(中位数价值$ n = \文本{29,300} $横跨天空)。虽然微弱,但这种SCD允许我们获得95%信心的Poissonian比赛的约束$ \ eta_p \ leq 66 \%$。这表明大量的GCE通量是由于PSS 。
translated by 谷歌翻译
这本数字本书包含在物理模拟的背景下与深度学习相关的一切实际和全面的一切。尽可能多,所有主题都带有Jupyter笔记本的形式的动手代码示例,以便快速入门。除了标准的受监督学习的数据中,我们将看看物理丢失约束,更紧密耦合的学习算法,具有可微分的模拟,以及加强学习和不确定性建模。我们生活在令人兴奋的时期:这些方法具有从根本上改变计算机模拟可以实现的巨大潜力。
translated by 谷歌翻译
声源本地化旨在从观察到的多通道音频寻求所有声源的到达方向(DOA)。对于未知数量来源的实际问题,现有的本地化算法试图预测基于似然的编码(即空间频谱),并采用预先确定的阈值来检测源编号和相应的DOA值。但是,这些基于阈值的算法不稳定,因为它们受到仔细选择阈值的限制。为了解决此问题,我们提出了一种称为ISSL的迭代声源本地化方法,该方法可以迭代地提取每个源的DOA而无需阈值,直到满足终止标准为止。与基于阈值的算法不同,ISSL设计基于二进制分类器的活动源检测器网络,以接受残留的空间频谱并决定是否停止迭代。通过这样做,我们的ISSL可以处理任意数量的来源,甚至超过培训阶段中看到的来源数量。实验结果表明,与现有的基于阈值的算法相比,我们的ISSL在DOA估计和源数检测方面都取得了重大的性能提高。
translated by 谷歌翻译
这是一门专门针对STEM学生开发的介绍性机器学习课程。我们的目标是为有兴趣的读者提供基础知识,以在自己的项目中使用机器学习,并将自己熟悉术语作为进一步阅读相关文献的基础。在这些讲义中,我们讨论受监督,无监督和强化学习。注释从没有神经网络的机器学习方法的说明开始,例如原理分析,T-SNE,聚类以及线性回归和线性分类器。我们继续介绍基本和先进的神经网络结构,例如密集的进料和常规神经网络,经常性的神经网络,受限的玻尔兹曼机器,(变性)自动编码器,生成的对抗性网络。讨论了潜在空间表示的解释性问题,并使用梦和对抗性攻击的例子。最后一部分致力于加强学习,我们在其中介绍了价值功能和政策学习的基本概念。
translated by 谷歌翻译
Normalizing flows provide a general mechanism for defining expressive probability distributions, only requiring the specification of a (usually simple) base distribution and a series of bijective transformations. There has been much recent work on normalizing flows, ranging from improving their expressive power to expanding their application. We believe the field has now matured and is in need of a unified perspective. In this review, we attempt to provide such a perspective by describing flows through the lens of probabilistic modeling and inference. We place special emphasis on the fundamental principles of flow design, and discuss foundational topics such as expressive power and computational trade-offs. We also broaden the conceptual framing of flows by relating them to more general probability transformations. Lastly, we summarize the use of flows for tasks such as generative modeling, approximate inference, and supervised learning.
translated by 谷歌翻译
最近归一化流量(NFS)在建模3D点云上已经证明了最先进的性能,同时允许在推理时间以任意分辨率进行采样。然而,这些基于流的模型仍然需要长期训练时间和大型模型来代表复杂的几何形状。这项工作通过将NFS的混合物应用于点云来增强它们的代表性。我们展示在更普遍的框架中,每个组件都学会专门以完全无监督的方式专门化对象的特定子区域。通过将每个混合组件与相对小的NF实例化,我们通过更好的细节生成点云,而与基于单流量的模型相比,使用较少的参数,并且大大减少推理运行时。我们进一步证明通过添加数据增强,各个混合组件可以学习以语义有意义的方式专注。基于ShapEnet​​ DataSet评估NFS对生成,自动编码和单视重建的混合物。
translated by 谷歌翻译