July 28, 2019

2996 words 15 mins read

Paper Group ANR 201

Secure Classification With Augmented Features. Shallow and Deep Networks Intrusion Detection System: A Taxonomy and Survey. Learning from Ontology Streams with Semantic Concept Drift. Spoken Language Biomarkers for Detecting Cognitive Impairment. Scalable Person Re-identification on Supervised Smoothed Manifold. Theoretical Analysis of Stochastic S …

Secure Classification With Augmented Features


Title	Secure Classification With Augmented Features
Authors	Chenping Hou, Ling-Li Zeng, Dewen Hu
Abstract	With the evolution of data collection ways, it is possible to produce abundant data described by multiple feature sets. Previous studies show that including more features does not necessarily bring positive effect. How to prevent the augmented features worsening classification performance is crucial but rarely studied. In this paper, we study this challenging problem by proposing a secure classification approach, whose accuracy is never degenerated when exploiting augmented features. We propose two ways to achieve the security of our method named as SEcure Classification (SEC). Firstly, to leverage augmented features, we learn various types of classifiers and adapt them by employing a specially designed robust loss. It provides various candidate classifiers to meet the following assumption of security operation. Secondly, we integrate all candidate classifiers by approximately maximizing the performance improvement. Under a mild assumption, the integrated classifier has theoretical security guarantee. Several new optimization methods have been developed to accommodate the problems with proved convergence. Besides evaluating SEC on 16 data sets, we also apply SEC in the application of diagnostic classification of schizophrenia since it has vast application potentiality. Experimental results demonstrate the effectiveness of SEC in both tackling security problem and discriminating schizophrenic patients from healthy controls.
Tasks
Published	2017-11-01
URL	http://arxiv.org/abs/1711.00239v1
PDF	http://arxiv.org/pdf/1711.00239v1.pdf
PWC	https://paperswithcode.com/paper/secure-classification-with-augmented-features
Repo
Framework

Shallow and Deep Networks Intrusion Detection System: A Taxonomy and Survey


Title	Shallow and Deep Networks Intrusion Detection System: A Taxonomy and Survey
Authors	Elike Hodo, Xavier Bellekens, Andrew Hamilton, Christos Tachtatzis, Robert Atkinson
Abstract	Intrusion detection has attracted a considerable interest from researchers and industries. The community, after many years of research, still faces the problem of building reliable and efficient IDS that are capable of handling large quantities of data, with changing patterns in real time situations. The work presented in this manuscript classifies intrusion detection systems (IDS). Moreover, a taxonomy and survey of shallow and deep networks intrusion detection systems is presented based on previous and current works. This taxonomy and survey reviews machine learning techniques and their performance in detecting anomalies. Feature selection which influences the effectiveness of machine learning (ML) IDS is discussed to explain the role of feature selection in the classification and training phase of ML IDS. Finally, a discussion of the false and true positive alarm rates is presented to help researchers model reliable and efficient machine learning based intrusion detection systems.
Tasks	Feature Selection, Intrusion Detection
Published	2017-01-09
URL	http://arxiv.org/abs/1701.02145v1
PDF	http://arxiv.org/pdf/1701.02145v1.pdf
PWC	https://paperswithcode.com/paper/shallow-and-deep-networks-intrusion-detection
Repo
Framework

Learning from Ontology Streams with Semantic Concept Drift


Title	Learning from Ontology Streams with Semantic Concept Drift
Authors	Freddy Lecue, Jiaoyan Chen, Jeff Pan, Huajun Chen
Abstract	Data stream learning has been largely studied for extracting knowledge structures from continuous and rapid data records. In the semantic Web, data is interpreted in ontologies and its ordered sequence is represented as an ontology stream. Our work exploits the semantics of such streams to tackle the problem of concept drift i.e., unexpected changes in data distribution, causing most of models to be less accurate as time passes. To this end we revisited (i) semantic inference in the context of supervised stream learning, and (ii) models with semantic embeddings. The experiments show accurate prediction with data from Dublin and Beijing.
Tasks
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07466v1
PDF	http://arxiv.org/pdf/1704.07466v1.pdf
PWC	https://paperswithcode.com/paper/learning-from-ontology-streams-with-semantic
Repo
Framework

Spoken Language Biomarkers for Detecting Cognitive Impairment


Title	Spoken Language Biomarkers for Detecting Cognitive Impairment
Authors	Tuka Alhanai, Rhoda Au, James Glass
Abstract	In this study we developed an automated system that evaluates speech and language features from audio recordings of neuropsychological examinations of 92 subjects in the Framingham Heart Study. A total of 265 features were used in an elastic-net regularized binomial logistic regression model to classify the presence of cognitive impairment, and to select the most predictive features. We compared performance with a demographic model from 6,258 subjects in the greater study cohort (0.79 AUC), and found that a system that incorporated both audio and text features performed the best (0.92 AUC), with a True Positive Rate of 29% (at 0% False Positive Rate) and a good model fit (Hosmer-Lemeshow test > 0.05). We also found that decreasing pitch and jitter, shorter segments of speech, and responses phrased as questions were positively associated with cognitive impairment.
Tasks
Published	2017-10-20
URL	http://arxiv.org/abs/1710.07551v1
PDF	http://arxiv.org/pdf/1710.07551v1.pdf
PWC	https://paperswithcode.com/paper/spoken-language-biomarkers-for-detecting
Repo
Framework

Scalable Person Re-identification on Supervised Smoothed Manifold


Title	Scalable Person Re-identification on Supervised Smoothed Manifold
Authors	Song Bai, Xiang Bai, Qi Tian
Abstract	Most existing person re-identification algorithms either extract robust visual features or learn discriminative metrics for person images. However, the underlying manifold which those images reside on is rarely investigated. That raises a problem that the learned metric is not smooth with respect to the local geometry structure of the data manifold. In this paper, we study person re-identification with manifold-based affinity learning, which did not receive enough attention from this area. An unconventional manifold-preserving algorithm is proposed, which can 1) make the best use of supervision from training data, whose label information is given as pairwise constraints; 2) scale up to large repositories with low on-line time complexity; and 3) be plunged into most existing algorithms, serving as a generic postprocessing procedure to further boost the identification accuracies. Extensive experimental results on five popular person re-identification benchmarks consistently demonstrate the effectiveness of our method. Especially, on the largest CUHK03 and Market-1501, our method outperforms the state-of-the-art alternatives by a large margin with high efficiency, which is more appropriate for practical applications.
Tasks	Person Re-Identification
Published	2017-03-24
URL	http://arxiv.org/abs/1703.08359v1
PDF	http://arxiv.org/pdf/1703.08359v1.pdf
PWC	https://paperswithcode.com/paper/scalable-person-re-identification-on
Repo
Framework

Theoretical Analysis of Stochastic Search Algorithms


Title	Theoretical Analysis of Stochastic Search Algorithms
Authors	Per Kristian Lehre, Pietro S. Oliveto
Abstract	Theoretical analyses of stochastic search algorithms, albeit few, have always existed since these algorithms became popular. Starting in the nineties a systematic approach to analyse the performance of stochastic search heuristics has been put in place. This quickly increasing basis of results allows, nowadays, the analysis of sophisticated algorithms such as population-based evolutionary algorithms, ant colony optimisation and artificial immune systems. Results are available concerning problems from various domains including classical combinatorial and continuous optimisation, single and multi-objective optimisation, and noisy and dynamic optimisation. This chapter introduces the mathematical techniques that are most commonly used in the runtime analysis of stochastic search heuristics. Careful attention is given to the very popular artificial fitness levels and drift analyses techniques for which several variants are presented. To aid the reader’s comprehension of the presented mathematical methods, these are applied to the analysis of simple evolutionary algorithms for artificial example functions. The chapter is concluded by providing references to more complex applications and further extensions of the techniques for the obtainment of advanced results.
Tasks
Published	2017-09-04
URL	http://arxiv.org/abs/1709.00890v1
PDF	http://arxiv.org/pdf/1709.00890v1.pdf
PWC	https://paperswithcode.com/paper/theoretical-analysis-of-stochastic-search
Repo
Framework

Keynote: Small Neural Nets Are Beautiful: Enabling Embedded Systems with Small Deep-Neural-Network Architectures


Title	Keynote: Small Neural Nets Are Beautiful: Enabling Embedded Systems with Small Deep-Neural-Network Architectures
Authors	Forrest Iandola, Kurt Keutzer
Abstract	Over the last five years Deep Neural Nets have offered more accurate solutions to many problems in speech recognition, and computer vision, and these solutions have surpassed a threshold of acceptability for many applications. As a result, Deep Neural Networks have supplanted other approaches to solving problems in these areas, and enabled many new applications. While the design of Deep Neural Nets is still something of an art form, in our work we have found basic principles of design space exploration used to develop embedded microprocessor architectures to be highly applicable to the design of Deep Neural Net architectures. In particular, we have used these design principles to create a novel Deep Neural Net called SqueezeNet that requires as little as 480KB of storage for its model parameters. We have further integrated all these experiences to develop something of a playbook for creating small Deep Neural Nets for embedded systems.
Tasks	Speech Recognition
Published	2017-10-07
URL	http://arxiv.org/abs/1710.02759v1
PDF	http://arxiv.org/pdf/1710.02759v1.pdf
PWC	https://paperswithcode.com/paper/keynote-small-neural-nets-are-beautiful
Repo
Framework

“How May I Help You?": Modeling Twitter Customer Service Conversations Using Fine-Grained Dialogue Acts


Title	“How May I Help You?": Modeling Twitter Customer Service Conversations Using Fine-Grained Dialogue Acts
Authors	Shereen Oraby, Pritam Gundecha, Jalal Mahmud, Mansurul Bhuiyan, Rama Akkiraju
Abstract	Given the increasing popularity of customer service dialogue on Twitter, analysis of conversation data is essential to understand trends in customer and agent behavior for the purpose of automating customer service interactions. In this work, we develop a novel taxonomy of fine-grained “dialogue acts” frequently observed in customer service, showcasing acts that are more suited to the domain than the more generic existing taxonomies. Using a sequential SVM-HMM model, we model conversation flow, predicting the dialogue act of a given turn in real-time. We characterize differences between customer and agent behavior in Twitter customer service conversations, and investigate the effect of testing our system on different customer service industries. Finally, we use a data-driven approach to predict important conversation outcomes: customer satisfaction, customer frustration, and overall problem resolution. We show that the type and location of certain dialogue acts in a conversation have a significant effect on the probability of desirable and undesirable outcomes, and present actionable rules based on our findings. The patterns and rules we derive can be used as guidelines for outcome-driven automated customer service platforms.
Tasks
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05413v1
PDF	http://arxiv.org/pdf/1709.05413v1.pdf
PWC	https://paperswithcode.com/paper/how-may-i-help-you-modeling-twitter-customer
Repo
Framework

Mining User/Movie Preferred Features Based on Reviews for Video Recommendation System


Title	Mining User/Movie Preferred Features Based on Reviews for Video Recommendation System
Authors	Xuan-Son Vu, Seong-Bae Park
Abstract	In this work, we present an approach for mining user preferences and recommendation based on reviews. There have been various studies worked on recommendation problem. However, most of the studies beyond one aspect user generated- content such as user ratings, user feedback and so on to state user preferences. There is a prob- lem in one aspect mining is lacking for stating user preferences. As a demonstration, in collaborative filter recommendation, we try to figure out the preference trend of crowded users, then use that trend to predict current user preference. Therefore, there is a gap between real user preferences and the trend of the crowded people. Additionally, user preferences can be addressed from mining user reviews since user often comment about various aspects of products. To solve this problem, we mainly focus on mining product aspects and user aspects inside user reviews to directly state user preferences. We also take into account Social Network Analysis for cold-start item problem. With cold-start user problem, collaborative filter algorithm is employed in our work. The framework is general enough to be applied to different recommendation domains. Theoretically, our method would achieve a significant enhancement.
Tasks
Published	2017-02-09
URL	http://arxiv.org/abs/1702.02737v1
PDF	http://arxiv.org/pdf/1702.02737v1.pdf
PWC	https://paperswithcode.com/paper/mining-usermovie-preferred-features-based-on
Repo
Framework

Global optimality conditions for deep neural networks


Title	Global optimality conditions for deep neural networks
Authors	Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Abstract	We study the error landscape of deep linear and nonlinear neural networks with the squared error loss. Minimizing the loss of a deep linear neural network is a nonconvex problem, and despite recent progress, our understanding of this loss surface is still incomplete. For deep linear networks, we present necessary and sufficient conditions for a critical point of the risk function to be a global minimum. Surprisingly, our conditions provide an efficiently checkable test for global optimality, while such tests are typically intractable in nonconvex optimization. We further extend these results to deep nonlinear neural networks and prove similar sufficient conditions for global optimality, albeit in a more limited function space setting.
Tasks
Published	2017-07-08
URL	http://arxiv.org/abs/1707.02444v3
PDF	http://arxiv.org/pdf/1707.02444v3.pdf
PWC	https://paperswithcode.com/paper/global-optimality-conditions-for-deep-neural
Repo
Framework

Scalable multimodal convolutional networks for brain tumour segmentation


Title	Scalable multimodal convolutional networks for brain tumour segmentation
Authors	Lucas Fidon, Wenqi Li, Luis C. Garcia-Peraza-Herrera, Jinendra Ekanayake, Neil Kitchen, Sebastien Ourselin, Tom Vercauteren
Abstract	Brain tumour segmentation plays a key role in computer-assisted surgery. Deep neural networks have increased the accuracy of automatic segmentation significantly, however these models tend to generalise poorly to different imaging modalities than those for which they have been designed, thereby limiting their applications. For example, a network architecture initially designed for brain parcellation of monomodal T1 MRI can not be easily translated into an efficient tumour segmentation network that jointly utilises T1, T1c, Flair and T2 MRI. To tackle this, we propose a novel scalable multimodal deep learning architecture using new nested structures that explicitly leverage deep features within or across modalities. This aims at making the early layers of the architecture structured and sparse so that the final architecture becomes scalable to the number of modalities. We evaluate the scalable architecture for brain tumour segmentation and give evidence of its regularisation effect compared to the conventional concatenation approach.
Tasks
Published	2017-06-25
URL	http://arxiv.org/abs/1706.08124v1
PDF	http://arxiv.org/pdf/1706.08124v1.pdf
PWC	https://paperswithcode.com/paper/scalable-multimodal-convolutional-networks
Repo
Framework

Analyzing Neural MT Search and Model Performance


Title	Analyzing Neural MT Search and Model Performance
Authors	Jan Niehues, Eunah Cho, Thanh-Le Ha, Alex Waibel
Abstract	In this paper, we offer an in-depth analysis about the modeling and search performance. We address the question if a more complex search algorithm is necessary. Furthermore, we investigate the question if more complex models which might only be applicable during rescoring are promising. By separating the search space and the modeling using $n$-best list reranking, we analyze the influence of both parts of an NMT system independently. By comparing differently performing NMT systems, we show that the better translation is already in the search space of the translation systems with less performance. This results indicate that the current search algorithms are sufficient for the NMT systems. Furthermore, we could show that even a relatively small $n$-best list of $50$ hypotheses already contain notably better translations.
Tasks
Published	2017-08-02
URL	http://arxiv.org/abs/1708.00563v1
PDF	http://arxiv.org/pdf/1708.00563v1.pdf
PWC	https://paperswithcode.com/paper/analyzing-neural-mt-search-and-model
Repo
Framework

Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks


Title	Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks
Authors	Simon Kallweit, Thomas Müller, Brian McWilliams, Markus Gross, Jan Novák
Abstract	We present a technique for efficiently synthesizing images of atmospheric clouds using a combination of Monte Carlo integration and neural networks. The intricacies of Lorenz-Mie scattering and the high albedo of cloud-forming aerosols make rendering of clouds—e.g. the characteristic silverlining and the “whiteness” of the inner body—challenging for methods based solely on Monte Carlo integration or diffusion theory. We approach the problem differently. Instead of simulating all light transport during rendering, we pre-learn the spatial and directional distribution of radiant flux from tens of cloud exemplars. To render a new scene, we sample visible points of the cloud and, for each, extract a hierarchical 3D descriptor of the cloud geometry with respect to the shading location and the light source. The descriptor is input to a deep neural network that predicts the radiance function for each shading configuration. We make the key observation that progressively feeding the hierarchical descriptor into the network enhances the network’s ability to learn faster and predict with high accuracy while using few coefficients. We also employ a block design with residual connections to further improve performance. A GPU implementation of our method synthesizes images of clouds that are nearly indistinguishable from the reference solution within seconds interactively. Our method thus represents a viable solution for applications such as cloud design and, thanks to its temporal stability, also for high-quality production of animated content.
Tasks
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05418v1
PDF	http://arxiv.org/pdf/1709.05418v1.pdf
PWC	https://paperswithcode.com/paper/deep-scattering-rendering-atmospheric-clouds
Repo
Framework

Potential Conditional Mutual Information: Estimators, Properties and Applications


Title	Potential Conditional Mutual Information: Estimators, Properties and Applications
Authors	Arman Rahimzamani, Sreeram Kannan
Abstract	The conditional mutual information I(X;YZ) measures the average information that X and Y contain about each other given Z. This is an important primitive in many learning problems including conditional independence testing, graphical model inference, causal strength estimation and time-series problems. In several applications, it is desirable to have a functional purely of the conditional distribution p_{YX,Z} rather than of the joint distribution p_{X,Y,Z}. We define the potential conditional mutual information as the conditional mutual information calculated with a modified joint distribution p_{YX,Z} q_{X,Z}, where q_{X,Z} is a potential distribution, fixed airport. We develop K nearest neighbor based estimators for this functional, employing importance sampling, and a coupling trick, and prove the finite k consistency of such an estimator. We demonstrate that the estimator has excellent practical performance and show an application in dynamical system inference.
Tasks	Time Series
Published	2017-10-13
URL	http://arxiv.org/abs/1710.05012v1
PDF	http://arxiv.org/pdf/1710.05012v1.pdf
PWC	https://paperswithcode.com/paper/potential-conditional-mutual-information
Repo
Framework

Dimension Reduction of High-Dimensional Datasets Based on Stepwise SVM


Title	Dimension Reduction of High-Dimensional Datasets Based on Stepwise SVM
Authors	Elizabeth P. Chou, Tzu-Wei Ko
Abstract	The current study proposes a dimension reduction method, stepwise support vector machine (SVM), to reduce the dimensions of large p small n datasets. The proposed method is compared with other dimension reduction methods, namely, the Pearson product difference correlation coefficient (PCCs), recursive feature elimination based on random forest (RF-RFE), and principal component analysis (PCA), by using five gene expression datasets. Additionally, the prediction performance of the variables selected by our method is evaluated. The study found that stepwise SVM can effectively select the important variables and achieve good prediction performance. Moreover, the predictions of stepwise SVM for reduced datasets was better than those for the unreduced datasets. The performance of stepwise SVM was more stable than that of PCA and RF-RFE, but the performance difference with respect to PCCs was minimal. It is necessary to reduce the dimensions of large p small n datasets. We believe that stepwise SVM can effectively eliminate noise in data and improve the prediction accuracy in any large p small n dataset.
Tasks	Dimensionality Reduction
Published	2017-11-09
URL	http://arxiv.org/abs/1711.03346v1
PDF	http://arxiv.org/pdf/1711.03346v1.pdf
PWC	https://paperswithcode.com/paper/dimension-reduction-of-high-dimensional
Repo
Framework