Time series modelling is essential for solving tasks such as predictive maintenance, quality control and optimisation. Deep learning is widely used for solving such problems. When managing complex manufacturing process with neural networks, engineers need to know why machine learning model made specific decision and what are possible outcomes of following model recommendation. In this paper we develop framework for capturing and explaining temporal dependencies in time series data using deep neural networks and test it on various synthetic and real world datasets.
IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）
Discovering temporal lagged and inter-dependencies in multivariate time series data is an important task. However, in many real-world applications, such as commercial cloud management, manufacturing predictive maintenance, and portfolios performance analysis, such dependencies can be non-linear and time-variant, which makes it more challenging to extract such dependencies through traditional methods such as Granger causality or clustering. In this work, we present a novel deep learning model that uses multiple layers of customized gated recurrent units (GRUs) for discovering both time lagged b…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Technicolor Research（特艺集团研究院）
High-dimensional time series prediction is needed in applications as diverse as demand forecasting and climatology. Often, such applications require methods that are both highly scalable, and deal with noisy data in terms of corruptions or missing values. Classical time series methods usually fall short of handling both these issues. In this paper, we propose to adapt matrix matrix completion approaches that have previously been successfully applied to large scale noisy data, but which fail to adequately model high-dimensional time series due to temporal dependencies. We present a novel tempor…
In todays age of data, discovering relationships between different variables is an interesting and a challenging problem. This problem becomes even more critical with regards to complex dynamical systems like weather forecasting and econometric models, which can show highly non-linear behavior. A method based on mutual information and deep neural networks is proposed as a versatile framework for discovering non-linear relationships ranging from functional dependencies to causality. We demonstrate the application of this method to actual multivariable non-linear dynamical systems. We also show …
University of Helsinki（赫尔辛基大学）；Télécom SudParis（南巴黎电信学院）；Institut Polytechnique de Paris（巴黎理工学院）；Université Côte d’Azur（蔚蓝海岸大学）；CNRS（法国国家科学研究中心）；University of Cambridge（剑桥大学）；Université Paris-Saclay（巴黎萨克雷大学）
We introduce a new general identifiable framework for principled disentanglement referred to as Structured Nonlinear Independent Component Analysis (SNICA). Our contribution is to extend the identifiability theory of deep generative models for a very broad class of structured models. While previous works have shown identifiability for specific classes of time-series models, our theorems extend this to more general temporal structures as well as to models with more complex structures such as spatial dependencies. In particular, we establish the major result that identifiability for this framewo…
Complex systems, such as airplanes, cars, or financial markets, produce multivariate time series data consisting of a large number of system measurements over a period of time. Such data can be interpreted as a sequence of states, where each state represents a prototype of system behavior. An important problem in this domain is to identify repeated sequences of states, known as motifs. Such motifs correspond to complex behaviors that capture common sequences of state transitions. For example, in automotive data, a motif of "making a turn" might manifest as a sequence of states: slowing down, t…
University of Sherbrooke（舍布鲁克大学）；University of Quebec at Montreal（魁北克大学蒙特利尔分校）
We investigate the problem of discovering and modeling regime shifts in an ecosystem comprising multiple time series known as co-evolving time series. Regime shifts refer to the changing behaviors exhibited by series at different time intervals. Learning these changing behaviors is a key step toward time series forecasting. While advances have been made, existing methods suffer from one or more of the following shortcomings: (1) failure to take relationships between time series into consideration for discovering regimes in multiple time series; (2) lack of an effective approach that models tim…
We study the problem of discovering functional dependencies (FD) from a noisy dataset. We focus on FDs that correspond to statistical dependencies in a dataset and draw connections between FD discovery and structure learning in probabilistic graphical models. We show that discovering FDs from a noisy dataset is equivalent to learning the structure of a graphical model over binary random variables, where each random variable corresponds to a functional of the dataset attributes. We build upon this observation to introduce AutoFD a conceptually simple framework in which learning functional depen…
Networks play a central role in modern data analysis, enabling us to reason about systems by studying the relationships between their parts. Most often in network analysis, the edges are given. However, in many systems it is difficult or impossible to measure the network directly. Examples of latent networks include economic interactions linking financial instruments and patterns of reciprocity in gang violence. In these cases, we are limited to noisy observations of events associated with each node. To enable analysis of these implicit networks, we develop a probabilistic model that combines …
Reconstructing the causal relationships behind the phenomena we observe is a fundamental challenge in all areas of science. Discovering causal relationships through experiments is often infeasible, unethical, or expensive in complex systems. However, increases in computational power allow us to process the ever-growing amount of data that modern science generates, leading to an emerging interest in the causal discovery problem from observational data. This work evaluates the LPCMCI algorithm, which aims to find generators compatible with a multi-dimensional, highly autocorrelated time series w…
In recent years, the rapid growth in technology has increased the opportunity for longitudinal human behavioral studies. Rich multimodal data, from wearables like Fitbit, online social networks, mobile phones etc. can be collected in natural environments. Uncovering the underlying low-dimensional structure of noisy multi-way data in an unsupervised setting is a challenging problem. Tensor factorization has been successful in extracting the interconnected low-dimensional descriptions of multi-way data. In this paper, we apply non-negative tensor factorization on a real-word wearable sensor data…
Weak-PDE-Net: Discovering Open-Form PDEs via Differentiable Symbolic Networks and Weak Formulation
School of Mathematical Sciences, East China Normal University（东华大学数学科学学院）；Institute of Applied Physics and Computational Mathematics（应用物理与计算数学研究所）；Institute of Artificial Intelligence, Beihang University（北航人工智能研究所）；Shanghai Zhangjiang Institute of Mathematics（上海张江数学研究所）；Academy for Advanced Interdisciplinary Studies, Northeast Normal University（东北师范大学先进交叉学科研究院）
Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）
In this paper we demonstrate that $\textit{context free grammar (CFG) based methods for grammar induction benefit from modeling lexical dependencies}$. This contrasts to the most popular current methods for grammar induction, which focus on discovering $\textit{either}$ constituents $\textit{or}$ dependencies. Previous approaches to marry these two disparate syntactic formalisms (e.g. lexicalized PCFGs) have been plagued by sparsity, making them unsuitable for unsupervised grammar induction. However, in this work, we present novel neural models of lexicalized PCFGs which allow us to overcome s…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Illinois Institute of Technology（伊利诺伊理工学院）
With the rapid increase of valuable observational, experimental and simulating data for complex systems, great efforts are being devoted to discovering governing laws underlying the evolution of these systems. However, the existing techniques are limited to extract governing laws from data as either deterministic differential equations or stochastic differential equations with Gaussian noise. In the present work, we develop a new data-driven approach to extract stochastic dynamical systems with non-Gaussian symmetric Lévy noise, as well as Gaussian noise. First, we establish a feasible theoret…
Physics-constrained robust learning of open-form partial differential equations from limited and noisy data
College of Engineering, Peking University（北京大学工学院）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（东方理工大学宁波数字孪生研究院）；School of Environmental Science and Engineering, Southern University of Science and Technology（南方科技大学环境科学与工程学院）；Eastern Institute for Advanced Study, Eastern Institute of Technology（东方理工大学东方高等研究院）
Some challenging problems in tracking multiple objects include the time-dependent cardinality, unordered measurements and object parameter labeling. In this paper, we employ Bayesian Bayesian nonparametric methods to address these challenges. In particular, we propose modeling the multiple object parameter state prior using the dependent Dirichlet and Pitman-Yor processes. These nonparametric models have been shown to be more flexible and robust, when compared to existing methods, for estimating the time-varying number of objects, providing object labeling and identifying measurement to object…
Newcastle University（纽卡斯尔大学）；PUC-Rio（里约热内卢天主教大学）；Universidad Federal Fluminense（弗卢米嫩塞联邦大学）
Tropical diseases like \textit{Chikungunya} and \textit{Zika} have come to prominence in recent years as the cause of serious, long-lasting, population-wide health problems. In large countries like Brasil, traditional disease prevention programs led by health authorities have not been particularly effective. We explore the hypothesis that monitoring and analysis of social media content streams may effectively complement such efforts. Specifically, we aim to identify selected members of the public who are likely to be sensitive to virus combat initiatives that are organised in local communities…
The Exploration of Error Bounds in Classification with Noisy Labels
The Hong Kong University of Science and Technology（香港科学与技术大学）；School of Mathematics and Statistics（数学与统计学学院）；Huazhong University of Science and Technology（华中科技大学）；The University of Hong Kong（香港大学）
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex temporal dependencies that imply variable-length semantic flows and their compositions, and those are hard to be captured by conventional methods. Here, we propose Temporal Dependency Networks (TDNs) for learning video data by discovering these complex structures of the videos. The TDNs represent video as a graph whose nodes and edges correspond to frames of …
Peking University（北京大学）；Southern University of Science and Technology（南方科技大学）；Peng Cheng Laboratory（鹏城实验室）
In recent years, data-driven methods have been developed to learn dynamical systems and partial differential equations (PDE). The goal of such work is discovering unknown physics and the corresponding equations. However, prior to achieving this goal, major challenges remain to be resolved, including learning PDE under noisy data and limited discrete data. To overcome these challenges, in this work, a deep-learning based data-driven method, called DL-PDE, is developed to discover the governing PDEs of underlying physical processes. The DL-PDE method combines deep learning via neural networks an…
Simula Research Laboratory（Simula研究实验室）；Navtor AS（Navtor公司）
Vessel navigation is influenced by various factors, such as dynamic environmental factors that change over time or static features such as vessel type or depth of the ocean. These dynamic and static navigational factors impose limitations on vessels, such as long waiting times in regions outside the actual ports, and we call these waiting regions gateway ports. Identifying gateway ports and their associated features such as congestion and available utilities can enhance vessel navigation by planning on fuel optimization or saving time in cargo operation. In this paper, we propose a novel tempo…
Discovering Governing Equations in the Presence of Uncertainty
Ridwan Olabiyi School of Computing and Augmented Intelligence, Arizona State University（Ridwan Olabiyi 计算与增强智能学院，亚利桑那州立大学）；Han Hu Department of Mechanical Engineering, University of Arkansas（Han Hu 机械工程系，阿肯色大学）；Ashif Iquebal School of Computing and Augmented Intelligence, Arizona State University（Ashif Iquebal 计算与增强智能学院，亚利桑那州立大学）
Learning both hierarchical and temporal representation has been among the long-standing challenges of recurrent neural networks. Multiscale recurrent neural networks have been considered as a promising approach to resolve this issue, yet there has been a lack of empirical evidence showing that this type of models can actually capture the temporal dependencies by discovering the latent hierarchical structure of the sequence. In this paper, we propose a novel multiscale approach, called the hierarchical multiscale recurrent neural networks, which can capture the latent hierarchical structure in …
Representing Outcome-driven Higher-order Dependencies in Graphs of Disease Trajectories
Lucy Family Institute for Data and Society, University of Notre Dame（圣母大学露西家庭数据与社会研究所）；Children’s Mercy, University of Missouri-Kansas City School of Medicine（密苏里大学堪萨斯城分校医学院儿童慈善医院）
Bilingual lexicons and phrase tables are critical resources for modern Machine Translation systems. Although recent results show that without any seed lexicon or parallel data, highly accurate bilingual lexicons can be learned using unsupervised methods, such methods rely on the existence of large, clean monolingual corpora. In this work, we utilize a single Skip-gram model trained on a multilingual corpus yielding polyglot word embeddings, and present a novel finding that a surprisingly simple constrained nearest-neighbor sampling technique in this embedding space can retrieve bilingual lexic…
Machine Learning Hamiltonian Dynamical Systems with Sparse and Noisy Data
The Mathematical Institute, University of Oxford, Oxford OX2 6GG, United Kingdom（牛津大学数学研究所）；Center for Theoretical Physics, St. Stephen's College, University of Delhi, Delhi 110007, India（德里大学斯特金学院理论物理中心）
One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpropagation through Time (TBPTT), categorically forbids learning dependencies beyond the truncation horizon. In contrast, the online training algorithm Real Time Recurrent Learning (RTRL) provides untruncated gradients, with the disadvantage of impractically large computational costs. Recently published approaches reduce these costs by providing noisy approximations of RTRL. We present a new approximation algorithm of …
Classical sequential models employed in time-series prediction rely on learning the mappings from the past to the future instances by way of a hidden state. The Hidden states characterise the historical information and encode the required temporal dependencies. However, most existing sequential models operate within finite-dimensional Euclidean spaces which offer limited functionality when employed in modelling physics relevant data. Alternatively recent work with neural operator learning within the Fourier space has shown efficient strategies for parameterising Partial Differential Equations …
Latent Manifold Reconstruction and Representation with Topological and Geometrical Regularization
Southern University of Science and Technology（南方科技大学）；Shenzhen University of Advanced Technology（深圳先进技术大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）
Noisy-OR Bayesian Networks (BNs) are a family of probabilistic graphical models which express rich statistical dependencies in binary data. Variational inference (VI) has been the main method proposed to learn noisy-OR BNs with complex latent structures (Jaakkola & Jordan, 1999; Ji et al., 2020; Buhai et al., 2020). However, the proposed VI approaches either (a) use a recognition network with standard amortized inference that cannot induce ``explaining-away''; or (b) assume a simple mean-field (MF) posterior which is vulnerable to bad local optima. Existing MF VI methods also update the MF par…
Discovery of partial differential equations from highly noisy and sparse data with physics-informed information criterion
College of Engineering, Peking University（北京大学工学院）；Institute of Applied Physics and Computational Mathematics（应用物理与计算数学研究所）；Southern University of Science and Technology（南方科技大学）；Peng Cheng Laboratory（鹏城实验室）
Quantum machine learning has proven to be a fruitful area in which to search for potential applications of quantum computers. This is particularly true for those available in the near term, so called noisy intermediate-scale quantum (NISQ) devices. In this Thesis, we develop and study three quantum machine learning applications suitable for NISQ computers, ordered in terms of increasing complexity of data presented to them. These algorithms are variational in nature and use parameterised quantum circuits (PQCs) as the underlying quantum machine learning model. The first application area is qua…
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex dependency structures that imply variable-length semantic flows and their compositions, and those are hard to be captured by conventional methods. Here, we propose Cut-Based Graph Learning Networks (CB-GLNs) for learning video data by discovering these complex structures of the video. The CB-GLNs represent video data as a graph, with nodes and edges correspon…
Artificial Intelligence Research Institute (IIIA-CSIC)（人工智能研究所（IIIA-CSIC））；Centre de Recerca Matemàtica（数学研究中心）
The detection of very similar patterns in a time series, commonly called motifs, has received continuous and increasing attention from diverse scientific communities. In particular, recent approaches for discovering similar motifs of different lengths have been proposed. In this work, we show that such variable-length similarity-based motifs cannot be directly compared, and hence ranked, by their normalized dissimilarities. Specifically, we find that length-normalized motif dissimilarities still have intrinsic dependencies on the motif length, and that lowest dissimilarities are particularly a…
BioArc: Discovering Optimal Neural Architectures for Biological Foundation Models
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA（弗吉尼亚理工学院计算机科学系）；Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA（弗吉尼亚理工学院电气与计算机工程系）；Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA（卡内基梅隆大学计算机科学系）；Department of Biomedical Data Science, Stanford University, Stanford, CA, USA（斯坦福大学生物医学数据科学系）
Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）；The Australian National University（澳大利亚国立大学）
Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, their performance is limited on real-noisy photographs and requires multiple stage network modeling. To advance the practicability of denoising algorithms, this paper proposes a novel single-stage blind real image denoising network (RIDNet) by employing a modular architecture. We use a residual on the residual structure to ease the flow of low-frequency information and apply feature attention to exploit the channel dependencies. Furthermore, the evaluation in terms of qu…
Seagate Technology（希捷科技）；Florida Atlantic University（佛罗里达大西洋大学）；University of Chicago（芝加哥大学）；University of Cincinnati（辛辛那提大学）；Stanford University（斯坦福大学）；Case Western Reserve University（凯斯西储大学）
In the era of big data, data-driven based classification has become an essential method in smart manufacturing to guide production and optimize inspection. The industrial data obtained in practice is usually time-series data collected by soft sensors, which are highly nonlinear, nonstationary, imbalanced, and noisy. Most existing soft-sensing machine learning models focus on capturing either intra-series temporal dependencies or pre-defined inter-series correlations, while ignoring the correlation between labels as each instance is associated with multiple labels simultaneously. In this paper,…
Hadoop MapReduce is a framework for distributed storage and processing of large datasets that is quite popular in big data analytics. It has various configuration parameters (knobs) which play an important role in deciding the performance i.e., the execution time of a given big data processing job. Default values of these parameters do not always result in good performance and hence it is important to tune them. However, there is inherent difficulty in tuning the parameters due to two important reasons - firstly, the parameter search space is large and secondly, there are cross-parameter inter…
We introduce a framework for reasoning about what meaning is captured by the neurons in a trained neural network. We provide a strategy for discovering meaning by training a second model (referred to as an observer model) to classify the state of the model it observes (an object model) in relation to attributes of the underlying dataset. We implement and evaluate observer models in the context of a specific set of classification problems, employ heat maps for visualizing the relevance of components of an object model in the context of linear observer models, and use these visualizations to ext…
Neural networks represent data as projections on trained weights in a high dimensional manifold. The trained weights act as a knowledge base consisting of causal class dependencies. Inference built on features that identify these dependencies is termed as feed-forward inference. Such inference mechanisms are justified based on classical cause-to-effect inductive reasoning models. Inductive reasoning based feed-forward inference is widely used due to its mathematical simplicity and operational ease. Nevertheless, feed-forward models do not generalize well to untrained situations. To alleviate t…
