There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in training and operation while still achieving competitive performance. For systems having limited long-term temporal dependencies, the approximation capability of recurrent networks is essentially equivalent to that of temporal convolutional nets (TCNs). We prove that TCNs can approximate a large class of input-output maps having approximately finite memory to arbitrary error tolerance. Furthermore, we derive quantitative approximation rates for deep ReLU TCNs in terms of the width and depth of the network and modulus of continuity of the original input-output map, and apply these results to input-output maps of systems that admit finite-dimensional state-space realizations (i.e., recurrent models).
We propose convex relaxations for convolutional neural nets with one hidden layer where the output weights are fixed. For convex activation functions such as rectified linear units, the relaxations are convex second order cone programs which can be solved very efficiently. We prove that the relaxation recovers the global minimum under a planted model assumption, given sufficiently many training samples from a Gaussian distribution. We also identify a phase transition phenomenon in recovering the global minimum for the relaxation.
UC Irvine（加州大学欧文分校）；University of Edinburgh（爱丁堡大学）；Ecole Polytechnique de Montreal（蒙特利尔理工学院）；University of Alberta（阿尔伯塔大学）；University of Washington（华盛顿大学）；Microsoft Research（微软研究院）
Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to be trained. Although previous research showed that shallow feed-forward nets sometimes can learn the complex functions previously learned by deep nets while using the same number of parameters as the deep models they mimic, in this paper we demonstrate that the same methods cannot be used to train accurate models on CIFAR-10 unless the student m…
Convolutional neural networks often dominate fully-connected counterparts in generalization performance, especially on image classification tasks. This is often explained in terms of 'better inductive bias'. However, this has not been made mathematically rigorous, and the hurdle is that the fully connected net can always simulate the convolutional net (for a fixed task). Thus the training algorithm plays a role. The current work describes a natural task on which a provable sample complexity gap can be shown, for standard training algorithms. We construct a single natural distribution on $\math…
We propose introspective convolutional networks (ICN) that emphasize the importance of having convolutional neural networks empowered with generative capabilities. We employ a reclassification-by-synthesis algorithm to perform training using a formulation stemmed from the Bayes theory. Our ICN tries to iteratively: (1) synthesize pseudo-negative samples; and (2) enhance itself by improving the classification. The single CNN classifier learned is at the same time generative --- being able to directly synthesize new samples within its own discriminative model. We conduct experiments on benchmark…
The University of Chicago（芝加哥大学）；Toyota Technological Institute（丰田工业研究所）
Recent work by Cohen \emph{et al.} has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory and noncommutative harmonic analysis. In this paper we propose a generalization of this work that generally exhibits improved performace, but from an implementation point of view is actually simpler. An unusual feature of the proposed architecture is that it uses the Clebsch--Gordan transform as its only source of nonlinearity, thus avoiding repeated forward and backward Fourier transforms. The underlying ideas of the…
We study from a physics viewpoint a class of generative neural nets, Gibbs machines, designed for gradual learning. While including variational auto-encoders, they offer a broader universal platform for incrementally adding newly learned features, including physical symmetries. Their direct connection to statistical physics and information geometry is established. A variational Pythagorean theorem justifies invoking the exponential/Gibbs class of probabilities for creating brand new objects. Combining these nets with classifiers, gives rise to a brand of universal generative neural nets - stoc…
Institute of Physics, University of Amsterdam（阿姆斯特丹大学物理研究所）
We introduce a machine learning model, the q-CNN model, sharing key features with convolutional neural networks and admitting a tensor network description. As examples, we apply q-CNN to the MNIST and Fashion MNIST classification tasks. We explain how the network associates a quantum state to each classification label, and study the entanglement structure of these network states. In both our experiments on the MNIST and Fashion-MNIST datasets, we observe a distinct increase in both the left/right as well as the up/down bipartition entanglement entropy during training as the network learns the …
Temple University（天普大学）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）
Nowadays, it is broadly recognized in the power system community that to meet the ever expanding energy sector's needs, it is no longer possible to rely solely on physics-based models and that reliable, timely and sustainable operation of energy systems is impossible without systematic integration of artificial intelligence (AI) tools. Nevertheless, the adoption of AI in power systems is still limited, while integration of AI particularly into distribution grid investment planning is still an uncharted territory. We make the first step forward to bridge this gap by showing how graph convolutio…
Department of Mathematics, Texas A\&M, College Station, United States
This article concerns the expressive power of depth in neural nets with ReLU activations and bounded width. We are particularly interested in the following questions: what is the minimal width $w_{\text{min}}(d)$ so that ReLU nets of width $w_{\text{min}}(d)$ (and arbitrary depth) can approximate any continuous function on the unit cube $[0,1]^d$ aribitrarily well? For ReLU nets near this minimal width, what can one say about the depth necessary to approximate a given function? Our approach to this paper is based on the observation that, due to the convexity of the ReLU activation, ReLU nets a…
EU-Nets: Enhanced, Explainable and Parsimonious U-Nets
School of Information and Software Engineering, University of Electronic Science and Technology of China（电子科技大学信息与软件工程学院）；Department of Computer Science and Technology, University of Cambridge（剑桥大学计算机科学与技术系）
In this paper we review the mathematical foundations of convolutional neural nets (CNNs) with the goals of: i) highlighting connections with techniques from statistics, signal processing, linear algebra, differential equations, and optimization, ii) demystifying underlying computations, and iii) identifying new types of applications. CNNs are powerful machine learning models that highlight features from grid data to make predictions (regression and classification). The grid data object can be represented as vectors (in 1D), matrices (in 2D), or tensors (in 3D or higher dimensions) and can inco…
Deutsches Medizinrechenzentrum GmbH & Co KG（德国医学计算中心有限两合公司）
Baseline detection is still a challenging task for heterogeneous collections of historical documents. We present a novel approach to baseline extraction in such settings, turning out the winning entry to the ICDAR 2017 Competition on Baseline detection (cBAD). It utilizes deep convolutional nets (CNNs) for both, the actual extraction of baselines, as well as for a simple form of layout analysis in a pre-processing step. To the best of our knowledge it is the first CNN-based system for baseline extraction applying a U-net architecture and sliding window detection, profiting from a high local ac…
Recent findings indicate that over-parametrization, while crucial for successfully training deep neural networks, also introduces large amounts of redundancy. Tensor methods have the potential to efficiently parametrize over-complete representations by leveraging this redundancy. In this paper, we propose to fully parametrize Convolutional Neural Networks (CNNs) with a single high-order, low-rank tensor. Previous works on network tensorization have focused on parametrizing individual layers (convolutional or fully connected) only, and perform the tensorization layer-by-layer separately. In con…
Traditional architectures for solving computer vision problems and the degree of success they enjoyed have been heavily reliant on hand-crafted features. However, of late, deep learning techniques have offered a compelling alternative -- that of automatically learning problem-specific features. With this new paradigm, every problem in computer vision is now being re-examined from a deep learning perspective. Therefore, it has become important to understand what kind of deep networks are suitable for a given problem. Although general surveys of this fast-moving paradigm (i.e. deep-networks) exi…
Princeton University（普林斯顿大学）；Institute for Advanced Study（高等研究院）；Carnegie Mellon University（卡内基梅隆大学）
Recent research shows that the following two models are equivalent: (a) infinitely wide neural networks (NNs) trained under l2 loss by gradient descent with infinitesimally small learning rate (b) kernel regression with respect to so-called Neural Tangent Kernels (NTKs) (Jacot et al., 2018). An efficient algorithm to compute the NTK, as well as its convolutional counterparts, appears in Arora et al. (2019a), which allowed studying performance of infinitely wide nets on datasets like CIFAR-10. However, super-quadratic running time of kernel methods makes them best suited for small-data tasks. W…
University of California, Irvine（加州大学尔湾分校）；Baidu Research（百度研究院）
In this work, we present a fully automated lung CT cancer diagnosis system, DeepLung. DeepLung contains two parts, nodule detection and classification. Considering the 3D nature of lung CT data, two 3D networks are designed for the nodule detection and classification respectively. Specifically, a 3D Faster R-CNN is designed for nodule detection with a U-net-like encoder-decoder structure to effectively learn nodule features. For nodule classification, gradient boosting machine (GBM) with 3D dual path network (DPN) features is proposed. The nodule classification subnetwork is validated on a pub…
NSF Center for Cloud and Autonomic Computing（NSF云与自主计算中心）；Department of Computer Science（计算机科学系）；The University of Arizona（亚利桑那大学）；The University of North Texas（北得克萨斯大学）
Anomaly detection is critically important for intelligent surveillance systems to detect in a timely manner any malicious activities. Many video anomaly detection approaches using deep learning methods focus on a single camera video stream with a fixed scenario. These deep learning methods use large-scale training data with large complexity. As a solution, in this paper, we show how to use pre-trained convolutional neural net models to perform feature extraction and context mining, and then use denoising autoencoder with relatively low model complexity to provide efficient and accurate surveil…
Waterloo Artificial Intelligence Institute, University of Waterloo（滑铁卢大学滑铁卢人工智能研究所）；DarwinAI Corp.（DarwinAI公司）
Much of the focus in the design of deep neural networks has been on improving accuracy, leading to more powerful yet highly complex network architectures that are difficult to deploy in practical scenarios, particularly on edge devices such as mobile and other consumer devices given their high computational and memory requirements. As a result, there has been a recent interest in the design of quantitative metrics for evaluating deep neural networks that accounts for more than just model accuracy as the sole indicator of network performance. In this study, we continue the conversation towards …
Univ. of California, Los Angeles（加州大学洛杉矶分校）；Google Inc.（谷歌公司）；CentraleSupélec（巴黎中央理工-高等电力学院）；INRIA（法国国家信息与自动化研究所）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）
Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called "semantic image segmentation"). We show that responses at the final layer of DCNNs are not sufficiently localized for accurate object segmentation. This is due to the very invariance properties that make DCNNs good for high level tasks. We overcome this poor localization property o…
University of Colorado, Boulder（科罗拉多大学博尔德分校）；Google Research（谷歌研究院）
In human perception and cognition, a fundamental operation that brains perform is interpretation: constructing coherent neural states from noisy, incomplete, and intrinsically ambiguous evidence. The problem of interpretation is well matched to an early and often overlooked architecture, the attractor network---a recurrent neural net that performs constraint satisfaction, imputation of missing features, and clean up of noisy data via energy minimization dynamics. We revisit attractor nets in light of modern deep learning methods and propose a convolutional bipartite architecture with a novel t…
Louisiana State University（路易斯安那州立大学）；Bay Area Environmental Research Institute（湾区环境研究所）；NASA Ames Research Center（美国国家航空航天局埃姆斯研究中心）
Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning. Due to the high variability inherent in satellite data, most of the current object classification approaches are not suitable for handling satellite datasets. The progress of satellite image analytics has also been inhibited by the lack of a single labeled high-resolution dataset with multiple class labels. In a preliminary version of this work, we introduced two new high resolution satellite imagery datasets (SAT-4 and SAT-6) and proposed DeepSat framew…
KTH Royal Institute of Technology（瑞典皇家理工学院）；MessageBird（MessageBird公司）；University of Washington（华盛顿大学）
Sum-Product Networks (SPNs) are hierarchical, graphical models that combine benefits of deep learning and probabilistic modeling. SPNs offer unique advantages to applications demanding exact probabilistic inference over high-dimensional, noisy inputs. Yet, compared to convolutional neural nets, they struggle with capturing complex spatial relationships in image data. To alleviate this issue, we introduce Deep Generalized Convolutional Sum-Product Networks (DGC-SPNs), which encode spatial features in a way similar to CNNs, while preserving the validity of the probabilistic SPN model. As opposed…
Imperial College London（帝国理工学院）；Department of Computing, Imperial College London, UK（帝国理工学院计算机系）
Deep Convolutional Neural Networks (DCNNs) is currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful selection of their building blocks (e.g., residual blocks, rectifiers, sophisticated normalization schemes, to mention but a few). In this paper, we propose $Π$-Nets, a new class of DCNNs. $Π$-Nets are polynomial neural networks, i.e., the output is a high-order polynomial of the input. $Π$-Nets can be implemented using special kind of skip connections and their par…
School of Computing Science（计算科学学院）；University of Glasgow（格拉斯哥大学）；OxBrdgRbtx Ltd（OxBrdgRbtx有限公司）
We demonstrate the feasibility of framing a classically learned deep neural network as an energy based model that can be processed on a one-step quantum annealer in order to exploit fast sampling times. We propose approaches to overcome two hurdles for high resolution image classification on a quantum processing unit (QPU): the required number and binary nature of the model states. With this novel method we successfully transfer a convolutional neural network to the QPU and show the potential for classification speedup of at least one order of magnitude.
Barcelona Supercomputing Center (BSC)（巴塞罗那超级计算中心（BSC））；Universitat Politècnica de Catalunya - BarcelonaTech (UPC)（加泰罗尼亚理工大学 - 巴塞罗那技术大学（UPC））；IBM T.J. Watson Research Center（IBM T.J. 沃森研究中心）
Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within a trained CNN model (in the case of image data), and reusing it for other purposes is a field of interest, as it provides access to the visual descriptors previously learnt by the CNN after processing millions of images, without requiring an expensive training phase. Contributions to this field (commonly known as feature representation transfer or transfer l…
We trained three Binarized Convolutional Neural Network architectures (LeNet-4, Network-In-Network, AlexNet) on a variety of datasets (MNIST, CIFAR-10, CIFAR-100, extended SVHN, ImageNet) using error-prone activations and tested them without errors to study the resilience of the training process. With the exception of the AlexNet when trained on the ImageNet dataset, we found that Bit Error Rates of a few percent during training do not degrade the test accuracy. Furthermore, by training the AlexNet on progressively smaller subsets of ImageNet classes, we observed increasing tolerance to activa…
Deep neural networks have demonstrated state-of-the-art performance in a variety of real-world applications. In order to obtain performance gains, these networks have grown larger and deeper, containing millions or even billions of parameters and over a thousand layers. The trade-off is that these large architectures require an enormous amount of memory, storage, and computation, thus limiting their usability. Inspired by the recent tensor ring factorization, we introduce Tensor Ring Networks (TR-Nets), which significantly compress both the fully connected layers and the convolutional layers o…
Saratoga High School（萨拉托加高中）；BRAC University JPG School of Public Health（BRAC大学JPG公共卫生学院）
Diabetes is one of the most prevalent chronic diseases in Bangladesh, and as a result, Diabetic Retinopathy (DR) is widespread in the population. DR, an eye illness caused by diabetes, can lead to blindness if it is not identified and treated in its early stages. Unfortunately, diagnosis of DR requires medically trained professionals, but Bangladesh has limited specialists in comparison to its population. Moreover, the screening process is often expensive, prohibiting many from receiving timely and proper diagnosis. To address the problem, we introduce a deep learning algorithm which screens f…
University of Notre Dame（圣母大学）；Lawrence Livermore National Laboratories（劳伦斯利弗莫尔国家实验室）
Imputation of missing data is a task that plays a vital role in a number of engineering and science applications. Often such missing data arise in experimental observations from limitations of sensors or post-processing transformation errors. Other times they arise from numerical and algorithmic constraints in computer simulations. One such instance and the application emphasis of this paper are numerical simulations of storm surge. The simulation data corresponds to time-series surge predictions over a number of save points within the geographic domain of interest, creating a spatio-temporal …
North Carolina State University（北卡罗来纳州立大学）；Pacific Northwest National Lab（太平洋西北国家实验室）；Texas A&M（德克萨斯农工大学）
This paper presents a novel, automated, generative adversarial networks (GAN) based synthetic feeder generation mechanism, abbreviated as FeederGAN. FeederGAN digests real feeder models represented by directed graphs via a deep learning framework powered by GAN and graph convolutional networks (GCN). Information of a distribution feeder circuit is extracted from its model input files so that the device connectivity is mapped onto the adjacency matrix and the device characteristics, such as circuit types (i.e., 3-phase, 2-phase, and 1-phase) and component attributes (e.g., length and current ra…
Beyond the generally deployed features for microstructure property prediction this study aims to improve the machine learned prediction by developing novel feature descriptors. Therefore, Bayesian infused data mining is conducted to acquire samples containing characteristics inexplicable to the current feature set, and suitable feature descriptors to describe these characteristics are proposed. The iterative development of feature descriptors resulted in 37 novel features, being able to reduce the prediction error by roughly one third. To further improve the predictive model, convolutional neu…
Motivated by the idea that criticality and universality of phase transitions might play a crucial role in achieving and sustaining learning and intelligent behaviour in biological and artificial networks, we analyse a theoretical and a pragmatic experimental set up for critical phenomena in deep learning. On the theoretical side, we use results from statistical physics to carry out critical point calculations in feed-forward/fully connected networks, while on the experimental side we set out to find traces of criticality in deep neural networks. This is our first step in a series of upcoming i…
Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible. To understand this approximate invertibility phenomenon and how to leverage it more effectively, we focus on a theoretical explanation and develop a mathematical model of sparse signal recovery that is consistent with CNNs with random weights. We give an exact connection to a particular model of model-based compressive sensing (and its recovery algorithms) and random-weight CNNs. We show empirically that several learned networks are consistent with our mathematical analysis and …
University of California, Irvine（加州大学尔湾分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
Mass segmentation provides effective morphological features which are important for mass diagnosis. In this work, we propose a novel end-to-end network for mammographic mass segmentation which employs a fully convolutional network (FCN) to model a potential function, followed by a CRF to perform structured learning. Because the mass distribution varies greatly with pixel position, the FCN is combined with a position priori. Further, we employ adversarial training to eliminate over-fitting due to the small sizes of mammogram datasets. Multi-scale FCN is employed to improve the segmentation perf…
Parallel Layer Normalization for Universal Approximation
State Key Laboratory of Complex and Critical Software Environment (SKLCCSE)（复杂与关键软件环境国家重点实验室）；Beihang University（北京航空航天大学）；Hangzhou International Innovation Institute（杭州国际创新研究院）
Bigo Inc.（Bigo公司）；Beihang University（北京航空航天大学）；IBM China CIC（IBM中国创新中心）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
We present a probabilistic forecasting framework based on convolutional neural network for multiple related time series forecasting. The framework can be applied to estimate probability density under both parametric and non-parametric settings. More specifically, stacked residual blocks based on dilated causal convolutional nets are constructed to capture the temporal dependencies of the series. Combined with representation learning, our approach is able to learn complex patterns such as seasonality, holiday effects within and across series, and to leverage those patterns for more accurate for…
Accurate and timely estimation of precipitation is critical for issuing hazard warnings (e.g., for flash floods or landslides). Current remotely sensed precipitation products have a few hours of latency, associated with the acquisition and processing of satellite data. By applying a robust nowcasting system to these products, it is (in principle) possible to reduce this latency and improve their applicability, value, and impact. However, the development of such a system is complicated by the chaotic nature of the atmosphere, and the consequent rapid changes that can occur in the structures of …
Facebook AI Research（Facebook人工智能研究院）；University of Le Mans（勒芒大学）
The dominant approach for many NLP tasks are recurrent neural networks, in particular LSTMs, and convolutional neural networks. However, these architectures are rather shallow in comparison to the deep convolutional networks which have pushed the state-of-the-art in computer vision. We present a new architecture (VDCNN) for text processing which operates directly at the character level and uses only small convolutions and pooling operations. We are able to show that the performance of this model increases with depth: using up to 29 convolutional layers, we report improvements over the state-of…
Deep learning has been widely applied and brought breakthroughs in speech recognition, computer vision, and many other domains. The involved deep neural network architectures and computational issues have been well studied in machine learning. But there lacks a theoretical foundation for understanding the approximation or generalization ability of deep learning methods generated by the network architectures such as deep convolutional neural networks having convolutional structures. Here we show that a deep convolutional neural network (CNN) is universal, meaning that it can be used to approxim…
University of Toronto（多伦多大学）；University of British Columbia（不列颠哥伦比亚大学）
This work investigates how using reduced precision data in Convolutional Neural Networks (CNNs) affects network accuracy during classification. More specifically, this study considers networks where each layer may use different precision data. Our key result is the observation that the tolerance of CNNs to reduced precision data not only varies across networks, a well established observation, but also within networks. Tuning precision per layer is appealing as it could enable energy and performance improvements. In this paper we study how error tolerance across layers varies and propose a meth…
Xi’an Jiaotong University（西安交通大学）；City University of Hong Kong（香港城市大学）
Compared with avid research activities of deep convolutional neural networks (DCNNs) in practice, the study of theoretical behaviors of DCNNs lags heavily behind. In particular, the universal consistency of DCNNs remains open. In this paper, we prove that implementing empirical risk minimization on DCNNs with expansive convolution (with zero-padding) is strongly universally consistent. Motivated by the universal consistency, we conduct a series of experiments to show that without any fully connected layers, DCNNs with expansive convolution perform not worse than the widely used deep neural net…
Predictive process monitoring aims to predict future characteristics of an ongoing process case, such as case outcome or remaining timestamp. Recently, several predictive process monitoring methods based on deep learning such as Long Short-Term Memory or Convolutional Neural Network have been proposed to address the problem of next event prediction. However, due to insufficient training data or sub-optimal network configuration and architecture, these approaches do not generalize well the problem at hand. This paper proposes a novel adversarial training framework to address this shortcoming, b…
Nanjing University of Information Science & Technology（南京信息工程大学）
Cerebrovascular accident, or commonly known as stroke, is an acute disease with extreme impact on patients and healthcare systems and is the second largest cause of death worldwide. Fast and precise stroke lesion detection and location is an extreme important process with regards to stroke diagnosis, treatment, and prognosis. Except from the manual segmentation approach, machine learning based segmentation methods are the most promising ones when considering efficiency and accuracy, and convolutional neural network based models are the first of its kind. However, most of these neural network m…
Hyperspectral image (HSI) consists of hundreds of continuous narrow bands with high spectral correlation, which would lead to the so-called Hughes phenomenon and the high computational cost in processing. Band selection has been proven effective in avoiding such problems by removing the redundant bands. However, many of existing band selection methods separately estimate the significance for every single band and cannot fully consider the nonlinear and global interaction between spectral bands. In this paper, by assuming that a complete HSI can be reconstructed from its few informative bands, …
