January 30, 2020

3065 words 15 mins read

Paper Group ANR 330

Automatically Learning Construction Injury Precursors from Text. Vision-based Navigation Using Deep Reinforcement Learning. Learning Resolution-Invariant Deep Representations for Person Re-Identification. Survival Forests under Test: Impact of the Proportional Hazards Assumption on Prognostic and Predictive Forests for ALS Survival. Multiplicative …

Automatically Learning Construction Injury Precursors from Text


Title	Automatically Learning Construction Injury Precursors from Text
Authors	Henrietta Baker, Matthew R. Hallowell, Antoine J. -P. Tixier
Abstract	In light of the increasing availability of digitally recorded safety reports in the construction industry, it is important to develop methods to exploit these data to improve our understanding of safety incidents and ability to learn from them. In this study, we compare several approaches to automatically learn injury precursors from raw construction accident reports. More precisely, we experiment with two state-of-the-art deep learning architectures for Natural Language Processing (NLP), Convolutional Neural Networks (CNN) and Hierarchical Attention Networks (HAN), and with the established Term Frequency - Inverse Document Frequency representation (TF-IDF) + Support Vector Machine (SVM) approach. For each model, we provide a method to identify (after training) the textual patterns that are, on average, the most predictive of each safety outcome. We show that among those pieces of text, valid injury precursors can be found. The proposed methods can also be used by the user to visualize and understand the models’ predictions.
Tasks
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11769v2
PDF	https://arxiv.org/pdf/1907.11769v2.pdf
PWC	https://paperswithcode.com/paper/automatically-learning-construction-injury
Repo
Framework


Title	Vision-based Navigation Using Deep Reinforcement Learning
Authors	Jonáš Kulhánek, Erik Derner, Tim de Bruin, Robert Babuška
Abstract	Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target given by an image. To achieve this, we have extended the batched A2C algorithm with auxiliary tasks designed to improve visual navigation performance. We propose three additional auxiliary tasks: predicting the segmentation of the observation image and of the target image and predicting the depth-map. These tasks enable the use of supervised learning to pre-train a large part of the network and to reduce the number of training steps substantially. The training performance has been further improved by increasing the environment complexity gradually over time. An efficient neural network structure is proposed, which is capable of learning for multiple targets in multiple environments. Our method navigates in continuous state spaces and on the AI2-THOR environment simulator outperforms state-of-the-art goal-oriented visual navigation methods from the literature.
Tasks	Visual Navigation
Published	2019-08-08
URL	https://arxiv.org/abs/1908.03627v2
PDF	https://arxiv.org/pdf/1908.03627v2.pdf
PWC	https://paperswithcode.com/paper/vision-based-navigation-using-deep
Repo
Framework

Learning Resolution-Invariant Deep Representations for Person Re-Identification


Title	Learning Resolution-Invariant Deep Representations for Person Re-Identification
Authors	Yun-Chun Chen, Yu-Jhe Li, Xiaofei Du, Yu-Chiang Frank Wang
Abstract	Person re-identification (re-ID) solves the task of matching images across cameras and is among the research topics in vision community. Since query images in real-world scenarios might suffer from resolution loss, how to solve the resolution mismatch problem during person re-ID becomes a practical problem. Instead of applying separate image super-resolution models, we propose a novel network architecture of Resolution Adaptation and re-Identification Network (RAIN) to solve cross-resolution person re-ID. Advancing the strategy of adversarial learning, we aim at extracting resolution-invariant representations for re-ID, while the proposed model is learned in an end-to-end training fashion. Our experiments confirm that the use of our model can recognize low-resolution query images, even if the resolution is not seen during training. Moreover, the extension of our model for semi-supervised re-ID further confirms the scalability of our proposed method for real-world scenarios and applications.
Tasks	Image Super-Resolution, Person Re-Identification, Super-Resolution
Published	2019-07-25
URL	https://arxiv.org/abs/1907.10843v1
PDF	https://arxiv.org/pdf/1907.10843v1.pdf
PWC	https://paperswithcode.com/paper/learning-resolution-invariant-deep
Repo
Framework

Survival Forests under Test: Impact of the Proportional Hazards Assumption on Prognostic and Predictive Forests for ALS Survival


Title	Survival Forests under Test: Impact of the Proportional Hazards Assumption on Prognostic and Predictive Forests for ALS Survival
Authors	Natalia Korepanova, Heidi Seibold, Verena Steffen, Torsten Hothorn
Abstract	We investigate the effect of the proportional hazards assumption on prognostic and predictive models of the survival time of patients suffering from amyotrophic lateral sclerosis (ALS). We theoretically compare the underlying model formulations of several variants of survival forests and implementations thereof, including random forests for survival, conditional inference forests, Ranger, and survival forests with $L_1$ splitting, with two novel variants, namely distributional and transformation survival forests. Theoretical considerations explain the low power of log-rank-based splitting in detecting patterns in non-proportional hazards situations in survival trees and corresponding forests. This limitation can potentially be overcome by the alternative split procedures suggested herein. We empirically investigated this effect using simulation experiments and a re-analysis of the PRO-ACT database of ALS survival, giving special emphasis to both prognostic and predictive models.
Tasks
Published	2019-02-05
URL	http://arxiv.org/abs/1902.01587v1
PDF	http://arxiv.org/pdf/1902.01587v1.pdf
PWC	https://paperswithcode.com/paper/survival-forests-under-test-impact-of-the
Repo
Framework

Multiplicative Models for Recurrent Language Modeling


Title	Multiplicative Models for Recurrent Language Modeling
Authors	Diego Maupomé, Marie-Jean Meurs
Abstract	Recently, there has been interest in multiplicative recurrent neural networks for language modeling. Indeed, simple Recurrent Neural Networks (RNNs) encounter difficulties recovering from past mistakes when generating sequences due to high correlation between hidden states. These challenges can be mitigated by integrating second-order terms in the hidden-state update. One such model, multiplicative Long Short-Term Memory (mLSTM) is particularly interesting in its original formulation because of the sharing of its second-order term, referred to as the intermediate state. We explore these architectural improvements by introducing new models and testing them on character-level language modeling tasks. This allows us to establish the relevance of shared parametrization in recurrent language modeling.
Tasks	Language Modelling
Published	2019-06-30
URL	https://arxiv.org/abs/1907.00455v1
PDF	https://arxiv.org/pdf/1907.00455v1.pdf
PWC	https://paperswithcode.com/paper/multiplicative-models-for-recurrent-language
Repo
Framework

Patterns of Urban Foot Traffic Dynamics


Title	Patterns of Urban Foot Traffic Dynamics
Authors	Gregory Dobler, Jordan Vani, Trang Tran Linh Dam
Abstract	Using publicly available traffic camera data in New York City, we quantify time-dependent patterns in aggregate pedestrian foot traffic. These patterns exhibit repeatable diurnal behaviors that differ for weekdays and weekends but are broadly consistent across neighborhoods in the borough of Manhattan. Weekday patterns contain a characteristic 3-peak structure with increased foot traffic around 9:00am, 12:00-1:00pm, and 5:00pm aligned with the “9-to-5” work day in which pedestrians are on the street during their morning commute, during lunch hour, and then during their evening commute. Weekend days do not show a peaked structure, but rather increase steadily until sunset. Our study period of June 28, 2017 to September 11, 2017 contains two holidays, the 4th of July and Labor Day, and their foot traffic patterns are quantitatively similar to weekend days despite the fact that they fell on weekdays. Projecting all days in our study period onto the weekday/weekend phase space (by regressing against the average weekday and weekend day) we find that Friday foot traffic can be represented as a mixture of both the 3-peak weekday structure and non-peaked weekend structure. We also show that anomalies in the foot traffic patterns can be used for detection of events and network-level disruptions. Finally, we show that clustering of foot traffic time series generates associations between cameras that are spatially aligned with Manhattan neighborhood boundaries indicating that foot traffic dynamics encode information about neighborhood character.
Tasks	Time Series
Published	2019-10-06
URL	https://arxiv.org/abs/1910.02380v1
PDF	https://arxiv.org/pdf/1910.02380v1.pdf
PWC	https://paperswithcode.com/paper/patterns-of-urban-foot-traffic-dynamics
Repo
Framework

Distributed filtered hyperinterpolation for noisy data on the sphere


Title	Distributed filtered hyperinterpolation for noisy data on the sphere
Authors	Shao-Bo Lin, Yu Guang Wang, Ding-Xuan Zhou
Abstract	Problems in astrophysics, space weather research and geophysics usually need to analyze noisy big data on the sphere. This paper develops distributed filtered hyperinterpolation for noisy data on the sphere, which assigns the data fitting task to multiple servers to find a good approximation of the mapping of input and output data. For each server, the approximation is a filtered hyperinterpolation on the sphere by a small proportion of quadrature nodes. The distributed strategy allows parallel computing for data processing and model selection and thus reduces computational cost for each server while preserves the approximation capability compared to the filtered hyperinterpolation. We prove quantitative relation between the approximation capability of distributed filtered hyperinterpolation and the numbers of input data and servers. Numerical examples show the efficiency and accuracy of the proposed method.
Tasks	Model Selection
Published	2019-10-06
URL	https://arxiv.org/abs/1910.02434v1
PDF	https://arxiv.org/pdf/1910.02434v1.pdf
PWC	https://paperswithcode.com/paper/distributed-filtered-hyperinterpolation-for
Repo
Framework

A Hybrid Traffic Speed Forecasting Approach Integrating Wavelet Transform and Motif-based Graph Convolutional Recurrent Neural Network


Title	A Hybrid Traffic Speed Forecasting Approach Integrating Wavelet Transform and Motif-based Graph Convolutional Recurrent Neural Network
Authors	Na Zhang, Xuefeng Guan, Jun Cao, Xinglei Wang, Huayi Wu
Abstract	Traffic forecasting is crucial for urban traffic management and guidance. However, existing methods rarely exploit the time-frequency properties of traffic speed observations, and often neglect the propagation of traffic flows from upstream to downstream road segments. In this paper, we propose a hybrid approach that learns the spatio-temporal dependency in traffic flows and predicts short-term traffic speeds on a road network. Specifically, we employ wavelet transform to decompose raw traffic data into several components with different frequency sub-bands. A Motif-based Graph Convolutional Recurrent Neural Network (Motif-GCRNN) and Auto-Regressive Moving Average (ARMA) are used to train and predict low-frequency components and high-frequency components, respectively. In the Motif-GCRNN framework, we integrate Graph Convolutional Networks (GCNs) with local sub-graph structures - Motifs - to capture the spatial correlations among road segments, and apply Long Short-Term Memory (LSTM) to extract the short-term and periodic patterns in traffic speeds. Experiments on a traffic dataset collected in Chengdu, China, demonstrate that the proposed hybrid method outperforms six state-of-art prediction methods.
Tasks
Published	2019-04-14
URL	http://arxiv.org/abs/1904.06656v1
PDF	http://arxiv.org/pdf/1904.06656v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-traffic-speed-forecasting-approach
Repo
Framework

Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks


Title	Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks
Authors	Massimo Fornasier, Timo Klock, Michael Rauchensteiner
Abstract	We address the structure identification and the uniform approximation of two fully nonlinear layer neural networks of the type $f(x)=1^T h(B^T g(A^T x))$ on $\mathbb R^d$ from a small number of query samples. We approach the problem by sampling actively finite difference approximations to Hessians of the network. Gathering several approximate Hessians allows reliably to approximate the matrix subspace $\mathcal W$ spanned by symmetric tensors $a_1 \otimes a_1 ,\dots,a_{m_0}\otimes a_{m_0}$ formed by weights of the first layer together with the entangled symmetric tensors $v_1 \otimes v_1 ,\dots,v_{m_1}\otimes v_{m_1}$, formed by suitable combinations of the weights of the first and second layer as $v_\ell=A G_0 b_\ell/\A G_0 b_\ell_2$, $\ell \in [m_1]$, for a diagonal matrix $G_0$ depending on the activation functions of the first layer. The identification of the 1-rank symmetric tensors within $\mathcal W$ is then performed by the solution of a robust nonlinear program. We provide guarantees of stable recovery under a posteriori verifiable conditions. We further address the correct attribution of approximate weights to the first or second layer. By using a suitably adapted gradient descent iteration, it is possible then to estimate, up to intrinsic symmetries, the shifts of the activations functions of the first layer and compute exactly the matrix $G_0$. Our method of identification of the weights of the network is fully constructive, with quantifiable sample complexity, and therefore contributes to dwindle the black-box nature of the network training phase. We corroborate our theoretical results by extensive numerical experiments.
Tasks
Published	2019-06-30
URL	https://arxiv.org/abs/1907.00485v1
PDF	https://arxiv.org/pdf/1907.00485v1.pdf
PWC	https://paperswithcode.com/paper/robust-and-resource-efficient-identification
Repo
Framework

PAC Statistical Model Checking for Markov Decision Processes and Stochastic Games


Title	PAC Statistical Model Checking for Markov Decision Processes and Stochastic Games
Authors	Pranav Ashok, Jan Křetínský, Maximilian Weininger
Abstract	Statistical model checking (SMC) is a technique for analysis of probabilistic systems that may be (partially) unknown. We present an SMC algorithm for (unbounded) reachability yielding probably approximately correct (PAC) guarantees on the results. We consider both the setting (i) with no knowledge of the transition function (with the only quantity required a bound on the minimum transition probability) and (ii) with knowledge of the topology of the underlying graph. On the one hand, it is the first algorithm for stochastic games. On the other hand, it is the first practical algorithm even for Markov decision processes. Compared to previous approaches where PAC guarantees require running times longer than the age of universe even for systems with a handful of states, our algorithm often yields reasonably precise results within minutes, not requiring the knowledge of mixing time or the topology of the whole model.
Tasks
Published	2019-05-10
URL	https://arxiv.org/abs/1905.04403v2
PDF	https://arxiv.org/pdf/1905.04403v2.pdf
PWC	https://paperswithcode.com/paper/pac-statistical-model-checking-for-markov
Repo
Framework

Context-Aware Graph Attention Networks


Title	Context-Aware Graph Attention Networks
Authors	Bo Jiang, Leiling Wang, Jin Tang, Bin Luo
Abstract	Graph Neural Networks (GNNs) have been widely studied for graph data representation and learning. However, existing GNNs generally conduct context-aware learning on node feature representation only which usually ignores the learning of edge (weight) representation. In this paper, we propose a novel unified GNN model, named Context-aware Adaptive Graph Attention Network (CaGAT). CaGAT aims to learn a context-aware attention representation for each graph edge by further exploiting the context relationships among different edges. In particular, CaGAT conducts context-aware learning on both node feature representation and edge (weight) representation simultaneously and cooperatively in a unified manner which can boost their respective performance in network training. We apply CaGAT on semi-supervised learning tasks. Promising experimental results on several benchmark datasets demonstrate the effectiveness and benefits of CaGAT.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1910.01736v1
PDF	https://arxiv.org/pdf/1910.01736v1.pdf
PWC	https://paperswithcode.com/paper/context-aware-graph-attention-networks
Repo
Framework

Technical Report: Fast Robot Arm Inverse Kinematics and Path Planning Under Complex Obstacle Constraint


Title	Technical Report: Fast Robot Arm Inverse Kinematics and Path Planning Under Complex Obstacle Constraint
Authors	David W. Arathorn
Abstract	Described here is a simple, reliable method for rapid computation of robot arm inverse kinematic solutions and motion path plans in the presence of complex obstructions. The method is based on a restricted form of the MSC (map-seeking circuit) algorithm, optimized to exploit the characteristics of practical arm configurations. MSC representation naturally incorporates both arm and obstacle geometries. The consequent performance on modern hardware is suitable for applications requiring real-time response. On high-end GPGPU hardware computation of both final pose for an 8 DOF arm and a smooth obstacle-avoiding motion path to that pose takes approximately 200msec.
Tasks
Published	2019-06-25
URL	https://arxiv.org/abs/1906.10678v4
PDF	https://arxiv.org/pdf/1906.10678v4.pdf
PWC	https://paperswithcode.com/paper/technical-report-fast-robot-arm-inverse
Repo
Framework

A Novel Deep Learning Pipeline for Retinal Vessel Detection in Fluorescein Angiography


Title	A Novel Deep Learning Pipeline for Retinal Vessel Detection in Fluorescein Angiography
Authors	Li Ding, Mohammad H. Bawany, Ajay E. Kuriyan, Rajeev S. Ramchandran, Charles C. Wykoff, Gaurav Sharma
Abstract	While recent advances in deep learning have significantly advanced the state of the art for vessel detection in color fundus (CF) images, the success for detecting vessels in fluorescein angiography (FA) has been stymied due to the lack of labeled ground truth datasets. We propose a novel pipeline to detect retinal vessels in FA images using deep neural networks that reduces the effort required for generating labeled ground truth data by combining two key components: cross-modality transfer and human-in-the-loop learning. The cross-modality transfer exploits concurrently captured CF and fundus FA images. Binary vessels maps are first detected from CF images with a pre-trained neural network and then are geometrically registered with and transferred to FA images via robust parametric chamfer alignment to a preliminary FA vessel detection obtained with an unsupervised technique. Using the transferred vessels as initial ground truth labels for deep learning, the human-in-the-loop approach progressively improves the quality of the ground truth labeling by iterating between deep-learning and labeling. The approach significantly reduces manual labeling effort while increasing engagement. We highlight several important considerations for the proposed methodology and validate the performance on three datasets. Experimental results demonstrate that the proposed pipeline significantly reduces the annotation effort and the resulting deep learning methods outperform prior existing FA vessel detection methods by a significant margin. A new public dataset, RECOVERY-FA19, is introduced that includes high-resolution ultra-widefield images and accurately labeled ground truth binary vessel maps.
Tasks
Published	2019-07-05
URL	https://arxiv.org/abs/1907.02946v1
PDF	https://arxiv.org/pdf/1907.02946v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-deep-learning-pipeline-for-retinal
Repo
Framework

A Note on Quantum Markov Models


Title	A Note on Quantum Markov Models
Authors	Christino Tamon, Weichen Xie
Abstract	The study of Markov models is central to control theory and machine learning. A quantum analogue of partially observable Markov decision process was studied in (Barry, Barry, and Aaronson, Phys. Rev. A, 90, 2014). It was proved that goal-state reachability is undecidable in the quantum setting, whereas it is decidable classically. In contrast to this classical-to-quantum transition from decidable to undecidable, we observe that the problem of approximating the optimal policy which maximizes the average discounted reward over an infinite horizon remains decidable in the quantum setting. Given that most relevant problems related to Markov decision process are undecidable classically (which immediately implies undecidability in the quantum case), this provides one of the few examples where the quantum problem is tractable.
Tasks
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01953v1
PDF	https://arxiv.org/pdf/1911.01953v1.pdf
PWC	https://paperswithcode.com/paper/a-note-on-quantum-markov-models
Repo
Framework

Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning


Title	Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning
Authors	Yichen Jiang, Mohit Bansal
Abstract	Multi-hop QA requires a model to connect multiple pieces of evidence scattered in a long context to answer the question. The recently proposed HotpotQA (Yang et al., 2018) dataset is comprised of questions embodying four different multi-hop reasoning paradigms (two bridge entity setups, checking multiple properties, and comparing two entities), making it challenging for a single neural network to handle all four. In this work, we present an interpretable, controller-based Self-Assembling Neural Modular Network (Hu et al., 2017, 2018) for multi-hop reasoning, where we design four novel modules (Find, Relocate, Compare, NoOp) to perform unique types of language reasoning. Based on a question, our layout controller RNN dynamically infers a series of reasoning modules to construct the entire network. Empirically, we show that our dynamic, multi-hop modular network achieves significant improvements over the static, single-hop baseline (on both regular and adversarial evaluation). We further demonstrate the interpretability of our model via three analyses. First, the controller can softly decompose the multi-hop question into multiple single-hop sub-questions to promote compositional reasoning behavior of the main network. Second, the controller can predict layouts that conform to the layouts designed by human experts. Finally, the intermediate module can infer the entity that connects two distantly-located supporting facts by addressing the sub-question from the controller.
Tasks
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05803v2
PDF	https://arxiv.org/pdf/1909.05803v2.pdf
PWC	https://paperswithcode.com/paper/self-assembling-modular-networks-for
Repo
Framework