October 18, 2019

3156 words 15 mins read

Paper Group ANR 462

Spatiotemporal Prediction of Ambulance Demand using Gaussian Process Regression. Video Description: A Survey of Methods, Datasets and Evaluation Metrics. Variational Selection of Features for Molecular Kinetics. Redundancy Coefficient Gradual Up-weighting-based Mutual Information Feature Selection Technique for Crypto-ransomware Early Detection. Un …

Spatiotemporal Prediction of Ambulance Demand using Gaussian Process Regression


Title	Spatiotemporal Prediction of Ambulance Demand using Gaussian Process Regression
Authors	Seth Nabarro, Tristan Fletcher, John Shawe-Taylor
Abstract	Accurately predicting when and where ambulance call-outs occur can reduce response times and ensure the patient receives urgent care sooner. Here we present a novel method for ambulance demand prediction using Gaussian process regression (GPR) in time and geographic space. The method exhibits superior accuracy to MEDIC, a method which has been used in industry. The use of GPR has additional benefits such as the quantification of uncertainty with each prediction, the choice of kernel functions to encode prior knowledge and the ability to capture spatial correlation. Measures to increase the utility of GPR in the current context, with large training sets and a Poisson-distributed output, are outlined.
Tasks
Published	2018-06-28
URL	http://arxiv.org/abs/1806.10873v1
PDF	http://arxiv.org/pdf/1806.10873v1.pdf
PWC	https://paperswithcode.com/paper/spatiotemporal-prediction-of-ambulance-demand
Repo
Framework

Video Description: A Survey of Methods, Datasets and Evaluation Metrics


Title	Video Description: A Survey of Methods, Datasets and Evaluation Metrics
Authors	Nayyer Aafaq, Ajmal Mian, Wei Liu, Syed Zulqarnain Gilani, Mubarak Shah
Abstract	Video description is the automatic generation of natural language sentences that describe the contents of a given video. It has applications in human-robot interaction, helping the visually impaired and video subtitling. The past few years have seen a surge of research in this area due to the unprecedented success of deep learning in computer vision and natural language processing. Numerous methods, datasets and evaluation metrics have been proposed in the literature, calling the need for a comprehensive survey to focus research efforts in this flourishing new direction. This paper fills the gap by surveying the state of the art approaches with a focus on deep learning models; comparing benchmark datasets in terms of their domains, number of classes, and repository size; and identifying the pros and cons of various evaluation metrics like SPICE, CIDEr, ROUGE, BLEU, METEOR, and WMD. Classical video description approaches combined subject, object and verb detection with template based language models to generate sentences. However, the release of large datasets revealed that these methods can not cope with the diversity in unconstrained open domain videos. Classical approaches were followed by a very short era of statistical methods which were soon replaced with deep learning, the current state of the art in video description. Our survey shows that despite the fast-paced developments, video description research is still in its infancy due to the following reasons. Analysis of video description models is challenging because it is difficult to ascertain the contributions, towards accuracy or errors, of the visual features and the adopted language model in the final description. Existing datasets neither contain adequate visual diversity nor complexity of linguistic structures. Finally, current evaluation metrics …
Tasks	Language Modelling, Video Description
Published	2018-06-01
URL	https://arxiv.org/abs/1806.00186v4
PDF	https://arxiv.org/pdf/1806.00186v4.pdf
PWC	https://paperswithcode.com/paper/video-description-a-survey-of-methods
Repo
Framework

Variational Selection of Features for Molecular Kinetics


Title	Variational Selection of Features for Molecular Kinetics
Authors	Martin K. Scherer, Brooke E. Husic, Moritz Hoffmann, Fabian Paul, Hao Wu, Frank Noé
Abstract	The modeling of atomistic biomolecular simulations using kinetic models such as Markov state models (MSMs) has had many notable algorithmic advances in recent years. The variational principle has opened the door for a nearly fully automated toolkit for selecting models that predict the long-time kinetics from molecular dynamics simulations. However, one yet-unoptimized step of the pipeline involves choosing the features, or collective variables, from which the model should be constructed. In order to build intuitive models, these collective variables are often sought to be interpretable and familiar features, such as torsional angles or contact distances in a protein structure. However, previous approaches for evaluating the chosen features rely on constructing a full MSM, which in turn requires additional hyperparameters to be chosen, and hence leads to a computationally expensive framework. Here, we present a method to optimize the feature choice directly, without requiring the construction of the final kinetic model. We demonstrate our rigorous preprocessing algorithm on a canonical set of twelve fast-folding protein simulations, and show that our procedure leads to more efficient model selection.
Tasks	Model Selection
Published	2018-11-28
URL	http://arxiv.org/abs/1811.11714v2
PDF	http://arxiv.org/pdf/1811.11714v2.pdf
PWC	https://paperswithcode.com/paper/variational-selection-of-features-for
Repo
Framework

Redundancy Coefficient Gradual Up-weighting-based Mutual Information Feature Selection Technique for Crypto-ransomware Early Detection


Title	Redundancy Coefficient Gradual Up-weighting-based Mutual Information Feature Selection Technique for Crypto-ransomware Early Detection
Authors	Bander Ali Saleh Al-rimy, Mohd Aizaini Maarof, Syed Zainudeen Mohd Shaid
Abstract	Crypto-ransomware is characterized by its irreversible effect even after the detection and removal. As such, the early detection is crucial to protect user data and files of being held to ransom. Several solutions have proposed utilizing the data extracted during the initial phases of the attacks before the encryption takes place. However, the lack of enough data at the early phases of the attack along with high dimensional features space renders the model prone to overfitting which decreases its detection accuracy. To this end, this paper proposed a novel redundancy coefficient gradual up-weighting approach that was incorporated to the calculation of redundancy term of mutual information to improve the feature selection process and enhance the accuracy of the detection model. Several machine learning classifiers were used to evaluate the detection performance of the proposed techniques. The experimental results show that the accuracy of proposed techniques achieved higher detection accuracy. Those results demonstrate the efficacy of the proposed techniques for the early detection tasks.
Tasks	Feature Selection
Published	2018-07-22
URL	http://arxiv.org/abs/1807.09574v1
PDF	http://arxiv.org/pdf/1807.09574v1.pdf
PWC	https://paperswithcode.com/paper/redundancy-coefficient-gradual-up-weighting
Repo
Framework

Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering


Title	Uncertainty Propagation in Deep Neural Networks Using Extended Kalman Filtering
Authors	Jessica S. Titensky, Hayden Jananthan, Jeremy Kepner
Abstract	Extended Kalman Filtering (EKF) can be used to propagate and quantify input uncertainty through a Deep Neural Network (DNN) assuming mild hypotheses on the input distribution. This methodology yields results comparable to existing methods of uncertainty propagation for DNNs while lowering the computational overhead considerably. Additionally, EKF allows model error to be naturally incorporated into the output uncertainty.
Tasks
Published	2018-09-17
URL	http://arxiv.org/abs/1809.06009v1
PDF	http://arxiv.org/pdf/1809.06009v1.pdf
PWC	https://paperswithcode.com/paper/uncertainty-propagation-in-deep-neural
Repo
Framework

Tunneling Neural Perception and Logic Reasoning through Abductive Learning


Title	Tunneling Neural Perception and Logic Reasoning through Abductive Learning
Authors	Wang-Zhou Dai, Qiu-Ling Xu, Yang Yu, Zhi-Hua Zhou
Abstract	Perception and reasoning are basic human abilities that are seamlessly connected as part of human intelligence. However, in current machine learning systems, the perception and reasoning modules are incompatible. Tasks requiring joint perception and reasoning ability are difficult to accomplish autonomously and still demand human intervention. Inspired by the way language experts decoded Mayan scripts by joining two abilities in an abductive manner, this paper proposes the abductive learning framework. The framework learns perception and reasoning simultaneously with the help of a trial-and-error abductive process. We present the Neural-Logical Machine as an implementation of this novel learning framework. We demonstrate that–using human-like abductive learning–the machine learns from a small set of simple hand-written equations and then generalizes well to complex equations, a feat that is beyond the capability of state-of-the-art neural network models. The abductive learning framework explores a new direction for approaching human-level learning ability.
Tasks
Published	2018-02-04
URL	http://arxiv.org/abs/1802.01173v2
PDF	http://arxiv.org/pdf/1802.01173v2.pdf
PWC	https://paperswithcode.com/paper/tunneling-neural-perception-and-logic
Repo
Framework

A Novel ILP Framework for Summarizing Content with High Lexical Variety


Title	A Novel ILP Framework for Summarizing Content with High Lexical Variety
Authors	Wencan Luo, Fei Liu, Zitao Liu, Diane Litman
Abstract	Summarizing content contributed by individuals can be challenging, because people make different lexical choices even when describing the same events. However, there remains a significant need to summarize such content. Examples include the student responses to post-class reflective questions, product reviews, and news articles published by different news agencies related to the same events. High lexical diversity of these documents hinders the system’s ability to effectively identify salient content and reduce summary redundancy. In this paper, we overcome this issue by introducing an integer linear programming-based summarization framework. It incorporates a low-rank approximation to the sentence-word co-occurrence matrix to intrinsically group semantically-similar lexical items. We conduct extensive experiments on datasets of student responses, product reviews, and news documents. Our approach compares favorably to a number of extractive baselines as well as a neural abstractive summarization system. The paper finally sheds light on when and why the proposed framework is effective at summarizing content with high lexical variety.
Tasks	Abstractive Text Summarization
Published	2018-07-25
URL	http://arxiv.org/abs/1807.09671v1
PDF	http://arxiv.org/pdf/1807.09671v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-ilp-framework-for-summarizing-content
Repo
Framework

Hierarchically Learned View-Invariant Representations for Cross-View Action Recognition


Title	Hierarchically Learned View-Invariant Representations for Cross-View Action Recognition
Authors	Yang Liu, Zhaoyang Lu, Jing Li, Tao Yang
Abstract	Recognizing human actions from varied views is challenging due to huge appearance variations in different views. The key to this problem is to learn discriminant view-invariant representations generalizing well across views. In this paper, we address this problem by learning view-invariant representations hierarchically using a novel method, referred to as Joint Sparse Representation and Distribution Adaptation (JSRDA). To obtain robust and informative feature representations, we first incorporate a sample-affinity matrix into the marginalized stacked denoising Autoencoder (mSDA) to obtain shared features, which are then combined with the private features. In order to make the feature representations of videos across views transferable, we then learn a transferable dictionary pair simultaneously from pairs of videos taken at different views to encourage each action video across views to have the same sparse representation. However, the distribution difference across views still exists because a unified subspace where the sparse representations of one action across views are the same may not exist when the view difference is large. Therefore, we propose a novel unsupervised distribution adaptation method that learns a set of projections that project the source and target views data into respective low-dimensional subspaces where the marginal and conditional distribution differences are reduced simultaneously. Therefore, the finally learned feature representation is view-invariant and robust for substantial distribution difference across views even the view difference is large. Experimental results on four multiview datasets show that our approach outperforms the state-ofthe-art approaches.
Tasks	Denoising, Temporal Action Localization
Published	2018-09-03
URL	https://arxiv.org/abs/1809.00421v2
PDF	https://arxiv.org/pdf/1809.00421v2.pdf
PWC	https://paperswithcode.com/paper/hierarchically-learned-view-invariant
Repo
Framework

PIVETed-Granite: Computational Phenotypes through Constrained Tensor Factorization


Title	PIVETed-Granite: Computational Phenotypes through Constrained Tensor Factorization
Authors	Jette Henderson, Bradley A. Malin, Joyce C. Ho, Joydeep Ghosh
Abstract	It has been recently shown that sparse, nonnegative tensor factorization of multi-modal electronic health record data is a promising approach to high-throughput computational phenotyping. However, such approaches typically do not leverage available domain knowledge while extracting the phenotypes; hence, some of the suggested phenotypes may not map well to clinical concepts or may be very similar to other suggested phenotypes. To address these issues, we present a novel, automatic approach called PIVETed-Granite that mines existing biomedical literature (PubMed) to obtain cannot-link constraints that are then used as side-information during a tensor-factorization based computational phenotyping process. The resulting improvements are clearly observed in experiments using a large dataset from VUMC to identify phenotypes for hypertensive patients.
Tasks	Computational Phenotyping
Published	2018-08-08
URL	http://arxiv.org/abs/1808.02602v1
PDF	http://arxiv.org/pdf/1808.02602v1.pdf
PWC	https://paperswithcode.com/paper/piveted-granite-computational-phenotypes
Repo
Framework

Optimization of neural networks via finite-value quantum fluctuations


Title	Optimization of neural networks via finite-value quantum fluctuations
Authors	Masayuki Ohzeki, Shuntaro Okada, Masayoshi Terabe, Shinichiro Taguchi
Abstract	We numerically test an optimization method for deep neural networks (DNNs) using quantum fluctuations inspired by quantum annealing. For efficient optimization, our method utilizes the quantum tunneling effect beyond the potential barriers. The path integral formulation of the DNN optimization generates an attracting force to simulate the quantum tunneling effect. In the standard quantum annealing method, the quantum fluctuations will vanish at the last stage of optimization. In this study, we propose a learning protocol that utilizes a finite value for quantum fluctuations strength to obtain higher generalization performance, which is a type of robustness. We demonstrate the performance of our method using two well-known open datasets: the MNIST dataset and the Olivetti face dataset. Although computational costs prevent us from testing our method on large datasets with high-dimensional data, results show that our method can enhance generalization performance by induction of the finite value for quantum fluctuations.
Tasks
Published	2018-07-01
URL	http://arxiv.org/abs/1807.00414v1
PDF	http://arxiv.org/pdf/1807.00414v1.pdf
PWC	https://paperswithcode.com/paper/optimization-of-neural-networks-via-finite
Repo
Framework

AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation


Title	AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation
Authors	Masataka Yamaguchi, Yuma Koizumi, Noboru Harada
Abstract	We tackle unsupervised anomaly detection (UAD), a problem of detecting data that significantly differ from normal data. UAD is typically solved by using density estimation. Recently, deep neural network (DNN)-based density estimators, such as Normalizing Flows, have been attracting attention. However, one of their drawbacks is the difficulty in adapting them to the change in the normal data’s distribution. To address this difficulty, we propose AdaFlow, a new DNN-based density estimator that can be easily adapted to the change of the distribution. AdaFlow is a unified model of a Normalizing Flow and Adaptive Batch-Normalizations, a module that enables DNNs to adapt to new distributions. AdaFlow can be adapted to a new distribution by just conducting forward propagation once per sample; hence, it can be used on devices that have limited computational resources. We have confirmed the effectiveness of the proposed model through an anomaly detection in a sound task. We also propose a method of applying AdaFlow to the unpaired cross-domain translation problem, in which one has to train a cross-domain translation model with only unpaired samples. We have confirmed that our model can be used for the cross-domain translation problem through experiments on image datasets.
Tasks	Anomaly Detection, Density Estimation, Unsupervised Anomaly Detection
Published	2018-12-14
URL	http://arxiv.org/abs/1812.05796v2
PDF	http://arxiv.org/pdf/1812.05796v2.pdf
PWC	https://paperswithcode.com/paper/adaflow-domain-adaptive-density-estimator
Repo
Framework

Learning What to Remember: Long-term Episodic Memory Networks for Learning from Streaming Data


Title	Learning What to Remember: Long-term Episodic Memory Networks for Learning from Streaming Data
Authors	Hyunwoo Jung, Moonsu Han, Minki Kang, Sungju Hwang
Abstract	Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning scenario where the model receives unlimited length of data stream as an input which contains vast majority of uninformative entries. We tackle this problem by proposing a memory network fit for long-term lifelong learning scenario, which we refer to as Long-term Episodic Memory Networks (LEMN), that features a RNN-based retention agent that learns to replace less important memory entries based on the retention probability generated on each entry that is learned to identify data instances of generic importance relative to other memory entries, as well as its historical importance. Such learning of retention agent allows our long-term episodic memory network to retain memory entries of generic importance for a given task. We validate our model on a path-finding task as well as synthetic and real question answering tasks, on which our model achieves significant improvements over the memory augmented networks with rule-based memory scheduling as well as an RL-based baseline that does not consider relative or historical importance of the memory.
Tasks	Question Answering
Published	2018-12-11
URL	http://arxiv.org/abs/1812.04227v1
PDF	http://arxiv.org/pdf/1812.04227v1.pdf
PWC	https://paperswithcode.com/paper/learning-what-to-remember-long-term-episodic
Repo
Framework

Real-Time Shape Tracking of Facial Landmarks


Title	Real-Time Shape Tracking of Facial Landmarks
Authors	Hyungjoon Kim, Hyeonwoo Kim, Eenjun Hwang
Abstract	Detection of facial landmarks and accurate tracking of their shape are essential in real-time virtual makeup applications, where users can see the makeups effect by moving their face in different directions. Typical face tracking techniques detect diverse facial landmarks and track them using a point tracker such as the Kanade-Lucas-Tomasi (KLT) point tracker. Typically, 5 or 64 points are used for tracking a face. Even though these points are sufficient to track the approximate locations of facial landmarks, they are not sufficient to track the exact shape of facial landmarks. In this paper, we propose a method that can track the exact shape of facial landmarks in real-time by combining a deep learning technique and a point tracker. We detect facial landmarks accurately using SegNet, which performs semantic segmentation based on deep learning. Edge points of detected landmarks are tracked using the KLT point tracker. In spite of its popularity, the KLT point tracker suffers from the point loss problem. We solve this problem by executing SegNet periodically to calculate the shape of facial landmarks. That is, by combining the two techniques, we can avoid the computational overhead of SegNet for real-time shape tracking and the point loss problem of the KLT point tracker. We performed several experiments to evaluate the performance of our method and report some of the results herein.
Tasks	Semantic Segmentation
Published	2018-07-14
URL	http://arxiv.org/abs/1807.05333v1
PDF	http://arxiv.org/pdf/1807.05333v1.pdf
PWC	https://paperswithcode.com/paper/real-time-shape-tracking-of-facial-landmarks
Repo
Framework

Similarity based hierarchical clustering of physiological parameters for the identification of health states - a feasibility study


Title	Similarity based hierarchical clustering of physiological parameters for the identification of health states - a feasibility study
Authors	Fabian Schrumpf, Gerold Bausch, Matthias Sturm, Mirco Fuchs
Abstract	This paper introduces a new unsupervised method for the clustering of physiological data into health states based on their similarity. We propose an iterative hierarchical clustering approach that combines health states according to a similarity constraint to new arbitrary health states. We applied method to experimental data in which the physical strain of subjects was systematically varied. We derived health states based on parameters extracted from ECG data. The occurrence of health states shows a high temporal correlation to the experimental phases of the physical exercise. We compared our method to other clustering algorithms and found a significantly higher accuracy with respect to the identification of health states.
Tasks
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09592v1
PDF	http://arxiv.org/pdf/1803.09592v1.pdf
PWC	https://paperswithcode.com/paper/similarity-based-hierarchical-clustering-of
Repo
Framework

A Scalable Machine Learning Approach for Inferring Probabilistic US-LI-RADS Categorization


Title	A Scalable Machine Learning Approach for Inferring Probabilistic US-LI-RADS Categorization
Authors	Imon Banerjee, Hailey H. Choi, Terry Desser, Daniel L. Rubin
Abstract	We propose a scalable computerized approach for large-scale inference of Liver Imaging Reporting and Data System (LI-RADS) final assessment categories in narrative ultrasound (US) reports. Although our model was trained on reports created using a LI-RADS template, it was also able to infer LI-RADS scoring for unstructured reports that were created before the LI-RADS guidelines were established. No human-labelled data was required in any step of this study; for training, LI-RADS scores were automatically extracted from those reports that contained structured LI-RADS scores, and it translated the derived knowledge to reasoning on unstructured radiology reports. By providing automated LI-RADS categorization, our approach may enable standardizing screening recommendations and treatment planning of patients at risk for hepatocellular carcinoma, and it may facilitate AI-based healthcare research with US images by offering large scale text mining and data gathering opportunities from standard hospital clinical data repositories.
Tasks
Published	2018-06-15
URL	http://arxiv.org/abs/1806.07346v1
PDF	http://arxiv.org/pdf/1806.07346v1.pdf
PWC	https://paperswithcode.com/paper/a-scalable-machine-learning-approach-for
Repo
Framework