May 6, 2019

2962 words 14 mins read

Paper Group ANR 176

Spatio-Temporal Modeling of Users’ Check-ins in Location-Based Social Networks. Intelligent Conversational Bot for Massive Online Open Courses (MOOCs). UnitBox: An Advanced Object Detection Network. CRF-CNN: Modeling Structured Information in Human Pose Estimation. Neuroevolution-Based Inverse Reinforcement Learning. Cross-validation based Nonlinea …


Title	Spatio-Temporal Modeling of Users’ Check-ins in Location-Based Social Networks
Authors	Ali Zarezade, Sina Jafarzadeh, Hamid R. Rabiee
Abstract	Social networks are getting closer to our real physical world. People share the exact location and time of their check-ins and are influenced by their friends. Modeling the spatio-temporal behavior of users in social networks is of great importance for predicting the future behavior of users, controlling the users’ movements, and finding the latent influence network. It is observed that users have periodic patterns in their movements. Also, they are influenced by the locations that their close friends recently visited. Leveraging these two observations, we propose a probabilistic model based on a doubly stochastic point process with a periodic decaying kernel for the time of check-ins and a time-varying multinomial distribution for the location of check-ins of users in the location-based social networks. We learn the model parameters using an efficient EM algorithm, which distributes over the users. Experiments on synthetic and real data gathered from Foursquare show that the proposed inference algorithm learns the parameters efficiently and our model outperforms the other alternatives in the prediction of time and location of check-ins.
Tasks
Published	2016-11-23
URL	http://arxiv.org/abs/1611.07710v2
PDF	http://arxiv.org/pdf/1611.07710v2.pdf
PWC	https://paperswithcode.com/paper/spatio-temporal-modeling-of-users-check-ins
Repo
Framework

Intelligent Conversational Bot for Massive Online Open Courses (MOOCs)


Title	Intelligent Conversational Bot for Massive Online Open Courses (MOOCs)
Authors	Ser Ling Lim, Ong Sing Goh
Abstract	Massive Online Open Courses (MOOCs) which were introduced in 2008 has since drawn attention around the world for both its advantages as well as criticism on its drawbacks. One of the issues in MOOCs which is the lack of interactivity with the instructor has brought conversational bot into the picture to fill in this gap. In this study, a prototype of MOOCs conversational bot, MOOC-bot is being developed and integrated into MOOCs website to respond to the learner inquiries using text or speech input. MOOC-bot is using the popular Artificial Intelligence Markup Language (AIML) to develop its knowledge base, leverage from AIML capability to deliver appropriate responses and can be quickly adapted to new knowledge domains. The system architecture of MOOC-bot consists of knowledge base along with AIML interpreter, chat interface, MOOCs website and Web Speech API to provide speech recognition and speech synthesis capability. The initial MOOC-bot prototype has the general knowledge from the past Loebner Prize winner - ALICE, frequent asked questions, and a content offered by Universiti Teknikal Malaysia Melaka (UTeM). The evaluation of MOOC-bot based on the past competition questions from Chatterbox Challenge (CBC) and Loebner Prize has shown that it was able to provide correct answers most of the time during the test and demonstrated the capability to prolong the conversation. The advantages of MOOC-bot such as able to provide 24-hour service that can serve different time zones, able to have knowledge in multiple domains, and can be shared by multiple sites simultaneously have outweighed its existing limitations.
Tasks	Speech Recognition, Speech Synthesis
Published	2016-01-26
URL	http://arxiv.org/abs/1601.07065v1
PDF	http://arxiv.org/pdf/1601.07065v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-conversational-bot-for-massive
Repo
Framework

UnitBox: An Advanced Object Detection Network


Title	UnitBox: An Advanced Object Detection Network
Authors	Jiahui Yu, Yuning Jiang, Zhangyang Wang, Zhimin Cao, Thomas Huang
Abstract	In present object detection systems, the deep convolutional neural networks (CNNs) are utilized to predict bounding boxes of object candidates, and have gained performance advantages over the traditional region proposal methods. However, existing deep CNN methods assume the object bounds to be four independent variables, which could be regressed by the $\ell_2$ loss separately. Such an oversimplified assumption is contrary to the well-received observation, that those variables are correlated, resulting to less accurate localization. To address the issue, we firstly introduce a novel Intersection over Union ($IoU$) loss function for bounding box prediction, which regresses the four bounds of a predicted box as a whole unit. By taking the advantages of $IoU$ loss and deep fully convolutional networks, the UnitBox is introduced, which performs accurate and efficient localization, shows robust to objects of varied shapes and scales, and converges fast. We apply UnitBox on face detection task and achieve the best performance among all published methods on the FDDB benchmark.
Tasks	Face Detection, Object Detection
Published	2016-08-04
URL	http://arxiv.org/abs/1608.01471v1
PDF	http://arxiv.org/pdf/1608.01471v1.pdf
PWC	https://paperswithcode.com/paper/unitbox-an-advanced-object-detection-network
Repo
Framework

CRF-CNN: Modeling Structured Information in Human Pose Estimation


Title	CRF-CNN: Modeling Structured Information in Human Pose Estimation
Authors	Xiao Chu, Wanli Ouyang, Hongsheng Li, Xiaogang Wang
Abstract	Deep convolutional neural networks (CNN) have achieved great success. On the other hand, modeling structural information has been proved critical in many vision problems. It is of great interest to integrate them effectively. In a classical neural network, there is no message passing between neurons in the same layer. In this paper, we propose a CRF-CNN framework which can simultaneously model structural information in both output and hidden feature layers in a probabilistic way, and it is applied to human pose estimation. A message passing scheme is proposed, so that in various layers each body joint receives messages from all the others in an efficient way. Such message passing can be implemented with convolution between features maps in the same layer, and it is also integrated with feedforward propagation in neural networks. Finally, a neural network implementation of end-to-end learning CRF-CNN is provided. Its effectiveness is demonstrated through experiments on two benchmark datasets.
Tasks	Pose Estimation
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00468v1
PDF	http://arxiv.org/pdf/1611.00468v1.pdf
PWC	https://paperswithcode.com/paper/crf-cnn-modeling-structured-information-in
Repo
Framework

Neuroevolution-Based Inverse Reinforcement Learning


Title	Neuroevolution-Based Inverse Reinforcement Learning
Authors	Karan K. Budhraja, Tim Oates
Abstract	The problem of Learning from Demonstration is targeted at learning to perform tasks based on observed examples. One approach to Learning from Demonstration is Inverse Reinforcement Learning, in which actions are observed to infer rewards. This work combines a feature based state evaluation approach to Inverse Reinforcement Learning with neuroevolution, a paradigm for modifying neural networks based on their performance on a given task. Neural networks are used to learn from a demonstrated expert policy and are evolved to generate a policy similar to the demonstration. The algorithm is discussed and evaluated against competitive feature-based Inverse Reinforcement Learning approaches. At the cost of execution time, neural networks allow for non-linear combinations of features in state evaluations. These valuations may correspond to state value or state reward. This results in better correspondence to observed examples as opposed to using linear combinations. This work also extends existing work on Bayesian Non-Parametric Feature Construction for Inverse Reinforcement Learning by using non-linear combinations of intermediate data to improve performance. The algorithm is observed to be specifically suitable for a linearly solvable non-deterministic Markov Decision Processes in which multiple rewards are sparsely scattered in state space. A conclusive performance hierarchy between evaluated algorithms is presented.
Tasks
Published	2016-08-09
URL	http://arxiv.org/abs/1608.02971v1
PDF	http://arxiv.org/pdf/1608.02971v1.pdf
PWC	https://paperswithcode.com/paper/neuroevolution-based-inverse-reinforcement
Repo
Framework

Cross-validation based Nonlinear Shrinkage


Title	Cross-validation based Nonlinear Shrinkage
Authors	Daniel Bartz
Abstract	Many machine learning algorithms require precise estimates of covariance matrices. The sample covariance matrix performs poorly in high-dimensional settings, which has stimulated the development of alternative methods, the majority based on factor models and shrinkage. Recent work of Ledoit and Wolf has extended the shrinkage framework to Nonlinear Shrinkage (NLS), a more powerful covariance estimator based on Random Matrix Theory. Our contribution shows that, contrary to claims in the literature, cross-validation based covariance matrix estimation (CVC) yields comparable performance at strongly reduced complexity and runtime. On two real world data sets, we show that the CVC estimator yields superior results than competing shrinkage and factor based methods.
Tasks
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00798v1
PDF	http://arxiv.org/pdf/1611.00798v1.pdf
PWC	https://paperswithcode.com/paper/cross-validation-based-nonlinear-shrinkage
Repo
Framework

PATH: Person Authentication using Trace Histories


Title	PATH: Person Authentication using Trace Histories
Authors	Upal Mahbub, Rama Chellappa
Abstract	In this paper, a solution to the problem of Active Authentication using trace histories is addressed. Specifically, the task is to perform user verification on mobile devices using historical location traces of the user as a function of time. Considering the movement of a human as a Markovian motion, a modified Hidden Markov Model (HMM)-based solution is proposed. The proposed method, namely the Marginally Smoothed HMM (MSHMM), utilizes the marginal probabilities of location and timing information of the observations to smooth-out the emission probabilities while training. Hence, it can efficiently handle unforeseen observations during the test phase. The verification performance of this method is compared to a sequence matching (SM) method , a Markov Chain-based method (MC) and an HMM with basic Laplace Smoothing (HMM-lap). Experimental results using the location information of the UMD Active Authentication Dataset-02 (UMDAA02) and the GeoLife dataset are presented. The proposed MSHMM method outperforms the compared methods in terms of equal error rate (EER). Additionally, the effects of different parameters on the proposed method are discussed.
Tasks
Published	2016-10-25
URL	http://arxiv.org/abs/1610.07935v1
PDF	http://arxiv.org/pdf/1610.07935v1.pdf
PWC	https://paperswithcode.com/paper/path-person-authentication-using-trace
Repo
Framework

Comparing Face Detection and Recognition Techniques


Title	Comparing Face Detection and Recognition Techniques
Authors	Jyothi Korra
Abstract	This paper implements and compares different techniques for face detection and recognition. One is find where the face is located in the images that is face detection and second is face recognition that is identifying the person. We study three techniques in this paper: Face detection using self organizing map (SOM), Face recognition by projection and nearest neighbor and Face recognition using SVM.
Tasks	Face Detection, Face Recognition
Published	2016-04-19
URL	http://arxiv.org/abs/1610.04575v1
PDF	http://arxiv.org/pdf/1610.04575v1.pdf
PWC	https://paperswithcode.com/paper/comparing-face-detection-and-recognition
Repo
Framework

Learning Multivariate Log-concave Distributions


Title	Learning Multivariate Log-concave Distributions
Authors	Ilias Diakonikolas, Daniel M. Kane, Alistair Stewart
Abstract	We study the problem of estimating multivariate log-concave probability density functions. We prove the first sample complexity upper bound for learning log-concave densities on $\mathbb{R}^d$, for all $d \geq 1$. Prior to our work, no upper bound on the sample complexity of this learning problem was known for the case of $d>3$. In more detail, we give an estimator that, for any $d \ge 1$ and $\epsilon>0$, draws $\tilde{O}_d \left( (1/\epsilon)^{(d+5)/2} \right)$ samples from an unknown target log-concave density on $\mathbb{R}^d$, and outputs a hypothesis that (with high probability) is $\epsilon$-close to the target, in total variation distance. Our upper bound on the sample complexity comes close to the known lower bound of $\Omega_d \left( (1/\epsilon)^{(d+1)/2} \right)$ for this problem.
Tasks
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08188v2
PDF	http://arxiv.org/pdf/1605.08188v2.pdf
PWC	https://paperswithcode.com/paper/learning-multivariate-log-concave
Repo
Framework

Explaining Predictions of Non-Linear Classifiers in NLP


Title	Explaining Predictions of Non-Linear Classifiers in NLP
Authors	Leila Arras, Franziska Horn, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek
Abstract	Layer-wise relevance propagation (LRP) is a recently proposed technique for explaining predictions of complex non-linear classifiers in terms of input variables. In this paper, we apply LRP for the first time to natural language processing (NLP). More precisely, we use it to explain the predictions of a convolutional neural network (CNN) trained on a topic categorization task. Our analysis highlights which words are relevant for a specific prediction of the CNN. We compare our technique to standard sensitivity analysis, both qualitatively and quantitatively, using a “word deleting” perturbation experiment, a PCA analysis, and various visualizations. All experiments validate the suitability of LRP for explaining the CNN predictions, which is also in line with results reported in recent image classification studies.
Tasks	Image Classification
Published	2016-06-23
URL	http://arxiv.org/abs/1606.07298v1
PDF	http://arxiv.org/pdf/1606.07298v1.pdf
PWC	https://paperswithcode.com/paper/explaining-predictions-of-non-linear
Repo
Framework

Improved graph-based SFA: Information preservation complements the slowness principle


Title	Improved graph-based SFA: Information preservation complements the slowness principle
Authors	Alberto N. Escalante-B., Laurenz Wiskott
Abstract	Slow feature analysis (SFA) is an unsupervised-learning algorithm that extracts slowly varying features from a multi-dimensional time series. A supervised extension to SFA for classification and regression is graph-based SFA (GSFA). GSFA is based on the preservation of similarities, which are specified by a graph structure derived from the labels. It has been shown that hierarchical GSFA (HGSFA) allows learning from images and other high-dimensional data. The feature space spanned by HGSFA is complex due to the composition of the nonlinearities of the nodes in the network. However, we show that the network discards useful information prematurely before it reaches higher nodes, resulting in suboptimal global slowness and an under-exploited feature space. To counteract these problems, we propose an extension called hierarchical information-preserving GSFA (HiGSFA), where information preservation complements the slowness-maximization goal. We build a 10-layer HiGSFA network to estimate human age from facial photographs of the MORPH-II database, achieving a mean absolute error of 3.50 years, improving the state-of-the-art performance. HiGSFA and HGSFA support multiple-labels and offer a rich feature space, feed-forward training, and linear complexity in the number of samples and dimensions. Furthermore, HiGSFA outperforms HGSFA in terms of feature slowness, estimation accuracy and input reconstruction, giving rise to a promising hierarchical supervised-learning approach.
Tasks	Time Series
Published	2016-01-15
URL	http://arxiv.org/abs/1601.03945v1
PDF	http://arxiv.org/pdf/1601.03945v1.pdf
PWC	https://paperswithcode.com/paper/improved-graph-based-sfa-information
Repo
Framework

Practical Introduction to Clustering Data


Title	Practical Introduction to Clustering Data
Authors	Alexander K. Hartmann
Abstract	Data clustering is an approach to seek for structure in sets of complex data, i.e., sets of “objects”. The main objective is to identify groups of objects which are similar to each other, e.g., for classification. Here, an introduction to clustering is given and three basic approaches are introduced: the k-means algorithm, neighbour-based clustering, and an agglomerative clustering method. For all cases, C source code examples are given, allowing for an easy implementation.
Tasks
Published	2016-02-16
URL	http://arxiv.org/abs/1602.05124v1
PDF	http://arxiv.org/pdf/1602.05124v1.pdf
PWC	https://paperswithcode.com/paper/practical-introduction-to-clustering-data
Repo
Framework

ZNNi - Maximizing the Inference Throughput of 3D Convolutional Networks on Multi-Core CPUs and GPUs


Title	ZNNi - Maximizing the Inference Throughput of 3D Convolutional Networks on Multi-Core CPUs and GPUs
Authors	Aleksandar Zlateski, Kisuk Lee, H. Sebastian Seung
Abstract	Sliding window convolutional networks (ConvNets) have become a popular approach to computer vision problems such as image segmentation, and object detection and localization. Here we consider the problem of inference, the application of a previously trained ConvNet, with emphasis on 3D images. Our goal is to maximize throughput, defined as average number of output voxels computed per unit time. Other things being equal, processing a larger image tends to increase throughput, because fractionally less computation is wasted on the borders of the image. It follows that an apparently slower algorithm may end up having higher throughput if it can process a larger image within the constraint of the available RAM. We introduce novel CPU and GPU primitives for convolutional and pooling layers, which are designed to minimize memory overhead. The primitives include convolution based on highly efficient pruned FFTs. Our theoretical analyses and empirical tests reveal a number of interesting findings. For some ConvNet architectures, cuDNN is outperformed by our FFT-based GPU primitives, and these in turn can be outperformed by our CPU primitives. The CPU manages to achieve higher throughput because of its fast access to more RAM. A novel primitive in which the GPU accesses host RAM can significantly increase GPU throughput. Finally, a CPU-GPU algorithm achieves the greatest throughput of all, 10x or more than other publicly available implementations of sliding window 3D ConvNets. All of our code has been made available as open source project.
Tasks	Object Detection, Semantic Segmentation
Published	2016-06-17
URL	http://arxiv.org/abs/1606.05688v1
PDF	http://arxiv.org/pdf/1606.05688v1.pdf
PWC	https://paperswithcode.com/paper/znni-maximizing-the-inference-throughput-of
Repo
Framework

Exploiting Lists of Names for Named Entity Identification of Financial Institutions from Unstructured Documents


Title	Exploiting Lists of Names for Named Entity Identification of Financial Institutions from Unstructured Documents
Authors	Zheng Xu, Douglas Burdick, Louiqa Raschid
Abstract	There is a wealth of information about financial systems that is embedded in document collections. In this paper, we focus on a specialized text extraction task for this domain. The objective is to extract mentions of names of financial institutions, or FI names, from financial prospectus documents, and to identify the corresponding real world entities, e.g., by matching against a corpus of such entities. The tasks are Named Entity Recognition (NER) and Entity Resolution (ER); both are well studied in the literature. Our contribution is to develop a rule-based approach that will exploit lists of FI names for both tasks; our solution is labeled Dict-based NER and Rank-based ER. Since the FI names are typically represented by a root, and a suffix that modifies the root, we use these lists of FI names to create specialized root and suffix dictionaries. To evaluate the effectiveness of our specialized solution for extracting FI names, we compare Dict-based NER with a general purpose rule-based NER solution, ORG NER. Our evaluation highlights the benefits and limitations of specialized versus general purpose approaches, and presents additional suggestions for tuning and customization for FI name extraction. To our knowledge, our proposed solutions, Dict-based NER and Rank-based ER, and the root and suffix dictionaries, are the first attempt to exploit specialized knowledge, i.e., lists of FI names, for rule-based NER and ER.
Tasks	Entity Resolution, Named Entity Recognition
Published	2016-02-14
URL	http://arxiv.org/abs/1602.04427v2
PDF	http://arxiv.org/pdf/1602.04427v2.pdf
PWC	https://paperswithcode.com/paper/exploiting-lists-of-names-for-named-entity
Repo
Framework

Propositional Abduction with Implicit Hitting Sets


Title	Propositional Abduction with Implicit Hitting Sets
Authors	Alexey Ignatiev, Antonio Morgado, Joao Marques-Silva
Abstract	Logic-based abduction finds important applications in artificial intelligence and related areas. One application example is in finding explanations for observed phenomena. Propositional abduction is a restriction of abduction to the propositional domain, and complexity-wise is in the second level of the polynomial hierarchy. Recent work has shown that exploiting implicit hitting sets and propositional satisfiability (SAT) solvers provides an efficient approach for propositional abduction. This paper investigates this earlier work and proposes a number of algorithmic improvements. These improvements are shown to yield exponential reductions in the number of SAT solver calls. More importantly, the experimental results show significant performance improvements compared to the the best approaches for propositional abduction.
Tasks
Published	2016-04-27
URL	http://arxiv.org/abs/1604.08229v1
PDF	http://arxiv.org/pdf/1604.08229v1.pdf
PWC	https://paperswithcode.com/paper/propositional-abduction-with-implicit-hitting
Repo
Framework