For augmentation of the square-shaped image data of a convolutional neural network (CNN), we introduce a new method, in which the original images are mapped onto a disk with a conformal mapping, rotated around the center of this disk and mapped under such a M\"obius transformation that preserves the disk, and then mapped back onto their original square shape. This process does not result the loss of information caused by removing areas from near the edges of the original images unlike the typical transformations used in the data augmentation for a CNN. We offer here the formulas of all the mappings needed together with detailed instructions how to write a code for transforming the images. The new method is also tested with simulated data and, according the results, using this method to augment the training data of 10 images into 40 images decreases the amount of the error in the predictions by a CNN for a test set of 160 images in a statistically significant way (p-value=0.0360).

We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of layer that enjoys a substantially higher degree of weight sharing than regular convolution layers. G-convolutions increase the expressive capacity of the network without increasing the number of parameters. Group convolution layers are easy to use and can be implemented with negligible computational overhead for discrete groups generated by translations, reflections and rotations. G-CNNs achieve state of the art results on CI-FAR10 and rotated MNIST.

在现代深网（DNS）中，至关重要的，无处不在且知之甚少的成分是批处理（BN），它以特​​征图为中心并归一化。迄今为止，只有有限的进步才能理解为什么BN会提高DN学习和推理表现。工作专注于表明BN平滑DN的损失格局。在本文中，我们从函数近似的角度从理论上研究BN。我们利用这样一个事实，即当今最先进的DNS是连续的分段仿射（CPA），可以通过定义在输入空间的分区上定义的仿射映射来预测培训数据（所谓的“线性”区域”）。 {\ em我们证明了BN是一种无监督的学习技术，它独立于DN的权重或基于梯度的学习 - 适应DN的样条分区的几何形状以匹配数据。} BN提供了“智能初始化”，可提高“智能初始化” DN学习的性能，因为它甚至适应了以随机权重初始化的DN，以使其样条分区与数据保持一致。我们还表明，微型批次之间的BN统计数据的变化引入了辍学的随机扰动，以对分区边界，因此分类问题的决策边界。每次微型摄入扰动可通过增加训练样本和决策边界之间的边距来减少过度拟合并改善概括。

提出了一种准确的翘曲图像方法。与大多数常用技术不同，该方法保证了转换图像的强度的保存，被评估为整个图像上其像素值的总和，或在相应的转换子区域上。这种特性是必须进行定量分析的，例如，当使用变形图像评估辐射，测量光源的光通量或表征材料光学密度时。所提出的方法通过将每个矩形像素分解为两个三角形，并将像素强度投射到转换图像的半像素上，从而强制重新采样采样，并将像素强度投射到与三角形半像素的重叠区域成正比的权重。结果在定量上是精确的，只要假定原始像素值代表像素区域内的恒定图像密度，并且只要坐标转换为差异。讨论了该方法的实现细节和可能的变化。

Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map translations. This is not the case for rotations. Global rotation equivariance is typically sought through data augmentation, but patch-wise equivariance is more difficult. We present Harmonic Networks or H-Nets, a CNN exhibiting equivariance to patch-wise translation and 360-rotation. We achieve this by replacing regular CNN filters with circular harmonics, returning a maximal response and orientation for every receptive field patch.H-Nets use a rich, parameter-efficient and fixed computational complexity representation, and we show that deep feature maps within the network encode complicated rotational invariants. We demonstrate that our layers are general enough to be used in conjunction with the latest architectures and techniques, such as deep supervision and batch normalization. We also achieve state-of-the-art classification on rotated-MNIST, and competitive results on other benchmark challenges.

Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images. We expect this to open up new application domains for GANs. We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5.59 to 2.42.

几乎所有的艺术视觉模型都对图像旋转敏感。现有方法通常通过使用增强的培训数据来学习伪延迟，以弥补缺失的归纳偏见。除了资源要求数据通胀过程之外，预测通常概括。卷积神经网络固有的感应偏置允许通过作用于像素网格的水平和垂直轴的内核进行翻译等效。但是，这种感应性偏差不允许旋转模棱两可。我们提出了一种径向光束采样策略，以及在这些梁上运行的径向内核，以固有地融合了中心反转协方差。加上角度距离损耗，我们提出了一个基于径向光束的图像典型化模型，即短BIC。我们的模型允许最大的连续角度回归，并规范化了任意中心旋转的输入图像。作为一个预处理模型，这可以通过模型不合式旋转敏感的下游预测来实现旋转不变的视觉管道。我们表明，我们的端到端训练的角度回归器能够预测几个视觉数据集的连续旋转角度，即FashionMnist，CIFAR10，COIL100和LFW。

许多应用程序需要神经网络的鲁棒性或理想的不变性，以使输入数据的某些转换。最常见的是，通过使用对抗性培训或定义包括设计所需不变性的网络体系结构来解决此要求。在这项工作中，我们提出了一种方法，使网络体系结构通过基于固定标准从（可能连续的）轨道中选择一个元素，从而使网络体系结构相对于小组操作证明是不变的。简而言之，我们打算在将数据馈送到实际网络之前“撤消”任何可能的转换。此外，我们凭经验分析了通过训练或体系结构结合不变性的不同方法的特性，并在鲁棒性和计算效率方面证明了我们方法的优势。特别是，我们研究了图像旋转（可以持续到离散化工件）以及3D点云分类的可证明的方向和缩放不变性方面的鲁棒性。

我描述了使用规定规则作为替代物的训练流模型的技巧，以最大程度地发出可能性。此技巧的实用性限制在非条件模型中，但是该方法的扩展应用于数据和条件信息的最大可能性分布的最大可能性，可用于训练复杂的\ textit \ textit {条件{条件}流模型。与以前的方法不同，此方法非常简单：它不需要明确了解条件分布，辅助网络或其他特定体系结构，或者不需要超出最大可能性的其他损失项，并且可以保留潜在空间和数据空间之间的对应关系。所得模型具有非条件流模型的所有属性，对意外输入具有鲁棒性，并且可以预测在给定输入上的解决方案的分布。它们具有预测代表性的保证，并且是解决高度不确定问题的自然和强大方法。我在易于可视化的玩具问题上演示了这些属性，然后使用该方法成功生成类条件图像并通过超分辨率重建高度退化的图像。

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。

标准化流是生成模型，其通过从简单的基本分布到复杂的目标分布的可逆性转换提供易于变换的工艺模型。然而，该技术不能直接模拟支持未知的低维歧管的数据，在诸如图像数据之类的现实世界域中的公共发生。最近的补救措施的尝试引入了击败归一化流量的中央好处的几何并发症：精确密度估计。我们通过保形嵌入流量来恢复这种福利，这是一种设计流动与贸易密度的流动的流动的框架。我们争辩说，使用培训保育嵌入的标准流量是模型支持数据的最自然的方式。为此，我们提出了一系列保形构建块，并在具有合成和实际数据的实验中应用它们，以证明流动可以在不牺牲贸易可能性的情况下模拟歧管支持的分布。

在本文中，我们提出了一种新方法，以可靠的方式使用基于几何的变异自动编码器以可靠的方式执行数据增强。我们的方法结合了VAE被视为Riemannian歧管的适当潜在空间建模和新一代方案，该方案产生了更有意义的样本，尤其是在小型数据集的背景下。该方法通过广泛的实验研究进行了测试，在该研究中，其对数据集，分类器和训练样品的稳健性受到了强调。还可以在充满挑战的ADNI数据库上进行医学成像分类任务进行验证，其中使用拟议的VAE框架考虑了少量的3D脑MRIS并增强。在每种情况下，所提出的方法都可以在分类指标中获得显着可靠的增益。例如，在最先进的CNN分类器中，经过50次认知正常（CN）和50例阿尔茨海默氏病（AD）患者的最先进的CNN分类器，平衡准确度从66.3％跃升至74.3％，从77.7％到86.3％。具有243 CN和210 AD，同时提高了极大的敏感性和特异性指标。

图像表示是计算机视觉和模式识别中的一个重要主题。它在一系列应用中扮演了了解视觉内容的基本作用。据报道，基于矩的图像表示在满足其由于其有益的数学特性而满足语义描述的核心条件，特别是几何不变性和独立性。本文介绍了对图像表示的正交矩的全面调查，涵盖了快速/准确计算，鲁棒性/不变性优化，定义扩展和应用程序的最新进步。我们还为各种广泛使用的正交瞬间创建一个软件包，并在同一基地中评估此类方法。提出的理论分析，软件实施和评估结果可以支持社区，特别是在开发新颖的技术和促进现实世界的应用方面。

我们开发了一种新类型的模型，以解决通过构建$ \ mathrm {so}^{+}（2,1）$ ecurivariant神经网络来解决多模式光纤的传输效果的任务。该模型利用了已知存在于纤维斑点模式中已知的方位角相关性，并且自然说明了输入和斑点模式之间的空间布置差异。此外，我们使用第二个后处理网络去除圆形伪像，填充间隙并锐化图像，这是由于光纤传输的性质所需的。这种两阶段的方法允许检查由更健壮的身体动机模型产生的预测图像，该模型可能在安全关键的应用程序中或两种模型的输出，从而产生高质量的图像。此外，该模型可以扩展到以前无法实现的成像分辨率，并在256美元\ times 256 $像素图像上显示出来。这是将可训练的参数需求从$ \ MATHCAL {O}（n^4）$提高到$ \ Mathcal {o}（M）$的结果，其中$ n $是像素大小，$ m $是光纤数模式。最后，该模型将在培训数据类别之外的新图像中概括，比以前的模型更好。

In photoacoustic tomography (PAT) with flat sensor, we routinely encounter two types of limited data. The first is due to using a finite sensor and is especially perceptible if the region of interest is large relative to the sensor or located farther away from the sensor. In this paper, we focus on the second type caused by a varying sensitivity of the sensor to the incoming wavefront direction which can be modelled as binary i.e. by a cone of sensitivity. Such visibility conditions result, in the Fourier domain, in a restriction of both the image and the data to a bow-tie, akin to the one corresponding to the range of the forward operator. The visible wavefrontsets in image and data domains, are related by the wavefront direction mapping. We adapt the wedge restricted Curvelet decomposition, we previously proposed for the representation of the full PAT data, to separate the visible and invisible wavefronts in the image. We optimally combine fast approximate operators with tailored deep neural network architectures into efficient learned reconstruction methods which perform reconstruction of the visible coefficients and the invisible coefficients are learned from a training set of similar data.

Multilayer Neural Networks trained with the backpropagation algorithm constitute the best example of a successful Gradient-Based Learning technique. Given an appropriate network architecture, Gradient-Based Learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional Neural Networks, that are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques.Real-life document recognition systems are composed of multiple modules including eld extraction, segmentation, recognition, and language modeling. A new learning paradigm, called Graph Transformer Networks (GTN), allows such multi-module systems to be trained globally using Gradient-Based methods so as to minimize an overall performance measure.Two systems for on-line handwriting recognition are described. Experiments demonstrate the advantage of global training, and the exibility of Graph Transformer Networks.A Graph Transformer Network for reading bank check is also described. It uses Convolutional Neural Network character recognizers combined with global training techniques to provides record accuracy on business and personal checks. It is deployed commercially and reads several million checks per day.

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。

投影技术经常用于可视化高维数据，使用户能够更好地理解在2D屏幕上的多维空间的总体结构。尽管存在着许多这样的方法，相当小的工作已经逆投影的普及方法来完成 - 绘制投影点，或者更一般的过程中，投影空间回到原来的高维空间。在本文中我们提出NNInv，用近似的任何突起或映射的逆的能力的深学习技术。 NNInv学会重建上的二维投影空间从任意点高维数据，给用户在视觉分析系统所学习的高维表示的能力进行交互。我们提供NNInv的参数空间的分析，并在选择这些参数提供指导。我们通过一系列定量和定性分析的延长NNInv的有效性验证。交互式实例中插值，分级协议，梯度可视化：然后，我们把它应用到三个可视化任务，验证了该方法的效用。

Generative Adversarial Networks (GANs) were introduced by Goodfellow in 2014, and since then have become popular for constructing generative artificial intelligence models. However, the drawbacks of such networks are numerous, like their longer training times, their sensitivity to hyperparameter tuning, several types of loss and optimization functions and other difficulties like mode collapse. Current applications of GANs include generating photo-realistic human faces, animals and objects. However, I wanted to explore the artistic ability of GANs in more detail, by using existing models and learning from them. This dissertation covers the basics of neural networks and works its way up to the particular aspects of GANs, together with experimentation and modification of existing available models, from least complex to most. The intention is to see if state of the art GANs (specifically StyleGAN2) can generate album art covers and if it is possible to tailor them by genre. This was attempted by first familiarizing myself with 3 existing GANs architectures, including the state of the art StyleGAN2. The StyleGAN2 code was used to train a model with a dataset containing 80K album cover images, then used to style images by picking curated images and mixing their styles.

In neural networks, it is often desirable to work with various representations of the same space. For example, 3D rotations can be represented with quaternions or Euler angles. In this paper, we advance a definition of a continuous representation, which can be helpful for training deep neural networks. We relate this to topological concepts such as homeomorphism and embedding. We then investigate what are continuous and discontinuous representations for 2D, 3D, and n-dimensional rotations. We demonstrate that for 3D rotations, all representations are discontinuous in the real Euclidean spaces of four or fewer dimensions. Thus, widely used representations such as quaternions and Euler angles are discontinuous and difficult for neural networks to learn. We show that the 3D rotations have continuous representations in 5D and 6D, which are more suitable for learning. We also present continuous representations for the general case of the n dimensional rotation group SO(n). While our main focus is on rotations, we also show that our constructions apply to other groups such as the orthogonal group and similarity transforms. We finally present empirical results, which show that our continuous rotation representations outperform discontinuous ones for several practical problems in graphics and vision, including a simple autoencoder sanity test, a rotation estimator for 3D point clouds, and an inverse kinematics solver for 3D human poses.