Attempts from different disciplines to provide a fundamental understanding of deep learning have advanced rapidly in recent years, yet a unified framework remains relatively limited. In this article, we provide one possible way to align existing branches of deep learning theory through the lens of dynamical system and optimal control. By viewing deep neural networks as discrete-time nonlinear dynamical systems, we can analyze how information propagates through layers using mean field theory. When optimization algorithms are further recast as controllers, the ultimate goal of training processes can be formulated as an optimal control problem. In addition, we can reveal convergence and generalization properties by studying the stochastic dynamics of optimization algorithms. This viewpoint features a wide range of theoretical study from information bottleneck to statistical physics. It also provides a principled way for hyper-parameter tuning when optimal control theory is introduced. Our framework fits nicely with supervised learning and can be extended to other learning problems, such as Bayesian learning, adversarial training, and specific forms of meta learning, without efforts. The review aims to shed lights on the importance of dynamics and optimal control when developing deep learning theory.
This document aims to provide a review on learning with deep generative models (DGMs), which is an highly-active area in machine learning and more generally, artificial intelligence. This review is not meant to be a tutorial, but when necessary, we provide self-contained derivations for completeness. This review has two features. First, though there are different perspectives to classify DGMs, we choose to organize this review from the perspective of graphical modeling, because the learning methods for directed DGMs and undirected DGMs are fundamentally different. Second, we differentiate mode…
In this paper we tackle the issue of clustering trajectories of geolocalized observations. Using clustering technics based on the choice of a distance between the observations, we first provide a comprehensive review of the different distances used in the literature to compare trajectories. Then based on the limitations of these methods, we introduce a new distance : Symmetrized Segment-Path Distance (SSPD). We finally compare this new distance to the others according to their corresponding clustering results obtained using both hierarchical clustering and affinity propagation methods.
University of Freiburg（弗赖堡大学）；University of Oxford（牛津大学）
This paper examines the effect of two-sided argumentation on the perceived helpfulness of online consumer reviews. In contrast to previous works, our analysis thereby sheds light on the reception of reviews from a language-based perspective. For this purpose, we propose an intriguing text analysis approach based on distributed text representations and multi-instance learning to operationalize the two-sidedness of argumentation in review texts. A subsequent empirical analysis using a large corpus of Amazon reviews suggests that two-sided argumentation in reviews significantly increases their he…
There has been increasing attention to semi-supervised learning (SSL) approaches in machine learning to forming a classifier in situations where the training data for a classifier consists of a limited number of classified observations but a much larger number of unclassified observations. This is because the procurement of classified data can be quite costly due to high acquisition costs and subsequent financial, time, and ethical issues that can arise in attempts to provide the true class labels for the unclassified data that have been acquired. We provide here a review of statistical SSL ap…
An ultimate goal of the AI and ML fields is artificial general intelligence (AGI); although such systems remain science fiction, various models exhibit aspects of AGI. In this work, we look at neuro-symbolic (NS)approaches to visual question answering (VQA) from the perspective of AGI desiderata. We see how well these systems meet these desiderata, and how the desiderata often pull the scientist in opposing directions. It is my hope that through this work we can temper model evaluation on benchmarks with a discussion of the properties of these systems and their potential for future extension.
National University of Singapore（新加坡国立大学）；Peking University（北京大学）
We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective. In particular, we establish general sufficient conditions for universal approximation using continuous-time deep residual networks, which can also be understood as approximation theories in $L^p$ using flow maps of dynamical systems. In specific cases, rates of approximation in terms of the time horizon are also established. Overall, these results reveal that composition function approximation through flow maps present…
University of Chinese Academy of Sciences（中国科学院大学）；University of Hamburg（汉堡大学）；Guangzhou University（广州大学）
Selective attention plays an essential role in information acquisition and utilization from the environment. In the past 50 years, research on selective attention has been a central topic in cognitive science. Compared with unimodal studies, crossmodal studies are more complex but necessary to solve real-world challenges in both human experiments and computational modeling. Although an increasing number of findings on crossmodal selective attention have shed light on humans' behavioral patterns and neural underpinnings, a much better understanding is still necessary to yield the same benefit f…
CSIRO（澳大利亚联邦科学与工业研究组织）；University of New South Wales（新南威尔士大学）
Federated learning is an emerging machine learning paradigm where clients train models locally and formulate a global model based on the local model updates. To identify the state-of-the-art in federated learning and explore how to develop federated learning systems, we perform a systematic literature review from a software engineering perspective, based on 231 primary studies. Our data synthesis covers the lifecycle of federated learning system development that includes background understanding, requirement analysis, architecture design, implementation, and evaluation. We highlight and summar…
The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are one of the key questions in modern machine learning. Graph signal processing (GSP), a vibrant branch of signal processing models and algorithms that aims at handling data supported on graphs, opens new paths of research to address this challenge. In this article, we review a few important contributions made by GSP concepts and tools, such as graph filters and transforms, to the development of novel machine learning al…
Nanjing University of Science and Technology（南京理工大学）
Big data have the characteristics of enormous volume, high velocity, diversity, value-sparsity, and uncertainty, which lead the knowledge learning from them full of challenges. With the emergence of crowdsourcing, versatile information can be obtained on-demand so that the wisdom of crowds is easily involved to facilitate the knowledge learning process. During the past thirteen years, researchers in the AI community made great efforts to remove the obstacles in the field of learning from crowds. This concentrated survey paper comprehensively reviews the technical progress in crowdsourcing lear…
Learning representations of data is an important problem in statistics and machine learning. While the origin of learning representations can be traced back to factor analysis and multidimensional scaling in statistics, it has become a central theme in deep learning with important applications in computer vision and computational neuroscience. In this article, we review recent advances in learning representations from a statistical perspective. In particular, we review the following two themes: (a) unsupervised learning of vector representations and (b) learning of both vector and matrix repre…
The success of neural networks builds to a large extent on their ability to create internal knowledge representations from real-world high-dimensional data, such as images, sound, or text. Approaches to extract and present these representations, in order to explain the neural network's decisions, is an active and multifaceted research field. To gain a deeper understanding of a central aspect of this field, we have performed a targeted review focusing on research that aims to associate internal representations with human understandable concepts. In doing this, we added a perspective on the exis…
In this tutorial article, we aim to provide the reader with the conceptual tools needed to get started on research on offline reinforcement learning algorithms: reinforcement learning algorithms that utilize previously collected data, without additional online data collection. Offline reinforcement learning algorithms hold tremendous promise for making it possible to turn large datasets into powerful decision making engines. Effective offline reinforcement learning methods would be able to extract policies with the maximum possible utility out of the available data, thereby allowing automation…
U. Montreal（蒙特利尔大学）；Canadian Institute for Advanced Research (CIFAR)（加拿大高等研究院）
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, cover…
Zhejiang University（浙江大学）；University of Oxford（牛津大学）；The University of Edinburgh（爱丁堡大学）
Zero-shot learning (ZSL) which aims at predicting classes that have never appeared during the training using external knowledge (a.k.a. side information) has been widely investigated. In this paper we present a literature review towards ZSL in the perspective of external knowledge, where we categorize the external knowledge, review their methods and compare different external knowledge. With the literature review, we further discuss and outlook the role of symbolic knowledge in addressing ZSL and other machine learning sample shortage issues.
A fall is an abnormal activity that occurs rarely; however, missing to identify falls can have serious health and safety implications on an individual. Due to the rarity of occurrence of falls, there may be insufficient or no training data available for them. Therefore, standard supervised machine learning methods may not be directly applied to handle this problem. In this paper, we present a taxonomy for the study of fall detection from the perspective of availability of fall data. The proposed taxonomy is independent of the type of sensors used and specific feature extraction/selection metho…
The Pennsylvania State University（宾夕法尼亚州立大学）；Tsinghua University（清华大学）；Google Brain（谷歌大脑）；Facebook（脸书）
In many applications of computer graphics, art and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph or layout, and have a computer system automatically generate photo-realistic images that adhere to the input content. While classic works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile im…
Ecole Polytechnique, Institut Polytechnique de Paris（巴黎理工学院巴黎综合理工学院）；University of Waikato（怀卡托大学）
The family of methods collectively known as classifier chains has become a popular approach to multi-label learning problems. This approach involves linking together off-the-shelf binary classifiers in a chain structure, such that class label predictions become features for other classifiers. Such methods have proved flexible and effective and have obtained state-of-the-art empirical performance across many datasets and multi-label evaluation metrics. This performance led to further studies of how exactly it works, and how it could be improved, and in the recent decade numerous studies have ex…
Mila（米拉研究所）；McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）；IBM Research（IBM研究院）；DeepMind（深度思维）
In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We begin by discussing our perspective on why RL is a natural fit for studying continual learning. We then provide a taxonomy of different continual RL formulations by mathematically characterizing two key properties of non-stationarity, namely, the scope and driver non-stationarity. This offers a unified view of various formulations. Next, we review and present a taxonomy of continual RL approaches. We go on to d…
Anomaly detection is concerned with identifying data patterns that deviate remarkably from the expected behaviour. This is an important research problem, due to its broad set of application domains, from data analysis to e-health, cybersecurity, predictive maintenance, fault prevention, and industrial automation. Herein, we review state-of-the-art methods that may be employed to detect anomalies in the specific area of sensor systems, which poses hard challenges in terms of information fusion, data volumes, data speed, and network/energy efficiency, to mention but the most pressing ones. In th…
Data scientists often develop machine learning models to solve a variety of problems in the industry and academy but not without facing several challenges in terms of Model Development. The problems regarding Machine Learning Development involves the fact that such professionals do not realize that they usually perform ad-hoc practices that could be improved by the adoption of activities presented in the Software Engineering Development Lifecycle. Of course, since machine learning systems are different from traditional Software systems, some differences in their respective development processe…
Regressing the vector field of a dynamical system from a finite number of observed states is a natural way to learn surrogate models for such systems. We present variants of cross-validation (Kernel Flows \cite{Owhadi19} and its variants based on Maximum Mean Discrepancy and Lyapunov exponents) as simple approaches for learning the kernel used in these emulators.
University of Science and Technology of China（中国科学技术大学）；Institute of Intelligent Machines, Chinese Academy of Sciences（中国科学院合肥智能机械研究所）；Mississippi State University（密西西比州立大学）；Sichuan University（四川大学）；Southwest Jiaotong University（西南交通大学）；Central South University（中南大学）
Humans' continual learning (CL) ability is closely related to Stability Versus Plasticity Dilemma that describes how humans achieve ongoing learning capacity and preservation for learned information. The notion of CL has always been present in artificial intelligence (AI) since its births. This paper proposes a comprehensive review of CL. Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism. Analogous to biological counterpart, "smart" AI ag…
The Lipschitz constant of neural networks has been established as a key quantity to enforce the robustness to adversarial examples. In this paper, we tackle the problem of building $1$-Lipschitz Neural Networks. By studying Residual Networks from a continuous time dynamical system perspective, we provide a generic method to build $1$-Lipschitz Neural Networks and show that some previous approaches are special cases of this framework. Then, we extend this reasoning and show that ResNet flows derived from convex potentials define $1$-Lipschitz transformations, that lead us to define the {\em Con…
Surrogates for Physics-based and Data-driven Modelling of Parametric Systems: Review and New Perspectives
Laboratori de Càlcul Numeric (LaCàN), E.T.S. de Ingeniería de Caminos, Canales y Puertos, Universitat Politècnica de Catalunya - BarcelonaTech (UPC)（计算数值实验室（LaCàN），土木工程系，加泰罗尼亚理工大学-巴塞罗那科技大学）；Centre Internacional de Mètodes Numèrics en Enginyeria (CIMNE)（国际数值工程方法中心）
Beihang University（北京航空航天大学）；University of California, San Diego（加州大学圣地亚哥分校）
As an emerging technique, Federated Learning (FL) can jointly train a global model with the data remaining locally, which effectively solves the problem of data privacy protection through the encryption mechanism. The clients train their local model, and the server aggregates models until convergence. In this process, the server uses an incentive mechanism to encourage clients to contribute high-quality and large-volume data to improve the global model. Although some works have applied FL to the Internet of Things (IoT), medicine, manufacturing, etc., the application of FL is still in its infa…
Iowa State University（爱荷华州立大学）；The Hong Kong Polytechnic University（香港理工大学）；Swiss Federal Institute of Technology Lausanne（洛桑联邦理工学院）；National Institute of Standards and Technology（美国国家标准与技术研究院）；GE Research（通用电气研究中心）；Seoul National University（首尔国立大学）；University of California, San Diego（加州大学圣地亚哥分校）；Vanderbilt University（范德堡大学）
As an emerging technology in the era of Industry 4.0, digital twin is gaining unprecedented attention because of its promise to further optimize process design, quality control, health monitoring, decision and policy making, and more, by comprehensively modeling the physical world as a group of interconnected digital models. In a two-part series of papers, we examine the fundamental role of different modeling techniques, twinning enabling technologies, and uncertainty quantification and optimization methods commonly used in digital twins. This second paper presents a literature review of key e…
National Heart and Lung Institute, Faculty of Medicine, Imperial College London（帝国理工学院医学院国家心肺研究所）；Department of Bioengineering, Faculty of Engineering, Imperial College London（帝国理工学院工程系生物工程系）；Royal Brompton Hospital（皇家布朗普顿医院）
Various structures in human physiology follow a treelike morphology, which often expresses complexity at very fine scales. Examples of such structures are intrathoracic airways, retinal blood vessels, and hepatic blood vessels. Large collections of 2D and 3D images have been made available by medical imaging modalities such as magnetic resonance imaging (MRI), computed tomography (CT), Optical coherence tomography (OCT) and ultrasound in which the spatial arrangement can be observed. Segmentation of these structures in medical imaging is of great importance since the analysis of the structure …
