July 28, 2019

2971 words 14 mins read

Paper Group ANR 220

Dialectical Multispectral Classification of Diffusion-Weighted Magnetic Resonance Images as an Alternative to Apparent Diffusion Coefficients Maps to Perform Anatomical Analysis. LogitBoost autoregressive networks. A Novel Stochastic Stratified Average Gradient Method: Convergence Rate and Its Complexity. Optimizing Quantum Models of Classical Chan …

Dialectical Multispectral Classification of Diffusion-Weighted Magnetic Resonance Images as an Alternative to Apparent Diffusion Coefficients Maps to Perform Anatomical Analysis


Title	Dialectical Multispectral Classification of Diffusion-Weighted Magnetic Resonance Images as an Alternative to Apparent Diffusion Coefficients Maps to Perform Anatomical Analysis
Authors	Wellington Pinheiro dos Santos, Francisco Marcos de Assis, Ricardo Emmanuel de Souza, Plínio Batista dos Santos Filho, Fernando Buarque de Lima Neto
Abstract	Multispectral image analysis is a relatively promising field of research with applications in several areas, such as medical imaging and satellite monitoring. A considerable number of current methods of analysis are based on parametric statistics. Alternatively, some methods in Computational Intelligence are inspired by biology and other sciences. Here we claim that Philosophy can be also considered as a source of inspiration. This work proposes the Objective Dialectical Method (ODM): a method for classification based on the Philosophy of Praxis. ODM is instrumental in assembling evolvable mathematical tools to analyze multispectral images. In the case study described in this paper, multispectral images are composed of diffusion-weighted (DW) magnetic resonance (MR) images. The results are compared to ground-truth images produced by polynomial networks using a morphological similarity index. The classification results are used to improve the usual analysis of the apparent diffusion coefficient map. Such results proved that gray and white matter can be distinguished in DW-MR multispectral analysis and, consequently, DW-MR images can also be used to furnish anatomical information.
Tasks
Published	2017-12-03
URL	http://arxiv.org/abs/1712.01697v1
PDF	http://arxiv.org/pdf/1712.01697v1.pdf
PWC	https://paperswithcode.com/paper/dialectical-multispectral-classification-of
Repo
Framework

LogitBoost autoregressive networks


Title	LogitBoost autoregressive networks
Authors	Marc Goessling
Abstract	Multivariate binary distributions can be decomposed into products of univariate conditional distributions. Recently popular approaches have modeled these conditionals through neural networks with sophisticated weight-sharing structures. It is shown that state-of-the-art performance on several standard benchmark datasets can actually be achieved by training separate probability estimators for each dimension. In that case, model training can be trivially parallelized over data dimensions. On the other hand, complexity control has to be performed for each learned conditional distribution. Three possible methods are considered and experimentally compared. The estimator that is employed for each conditional is LogitBoost. Similarities and differences between the proposed approach and autoregressive models based on neural networks are discussed in detail.
Tasks
Published	2017-03-22
URL	http://arxiv.org/abs/1703.07506v1
PDF	http://arxiv.org/pdf/1703.07506v1.pdf
PWC	https://paperswithcode.com/paper/logitboost-autoregressive-networks
Repo
Framework

A Novel Stochastic Stratified Average Gradient Method: Convergence Rate and Its Complexity


Title	A Novel Stochastic Stratified Average Gradient Method: Convergence Rate and Its Complexity
Authors	Aixiang Chen, Bingchuan Chen, Xiaolong Chai, Rui Bian, Hengguang Li
Abstract	SGD (Stochastic Gradient Descent) is a popular algorithm for large scale optimization problems due to its low iterative cost. However, SGD can not achieve linear convergence rate as FGD (Full Gradient Descent) because of the inherent gradient variance. To attack the problem, mini-batch SGD was proposed to get a trade-off in terms of convergence rate and iteration cost. In this paper, a general CVI (Convergence-Variance Inequality) equation is presented to state formally the interaction of convergence rate and gradient variance. Then a novel algorithm named SSAG (Stochastic Stratified Average Gradient) is introduced to reduce gradient variance based on two techniques, stratified sampling and averaging over iterations that is a key idea in SAG (Stochastic Average Gradient). Furthermore, SSAG can achieve linear convergence rate of $\mathcal {O}((1-\frac{\mu}{8CL})^k)$ at smaller storage and iterative costs, where $C\geq 2$ is the category number of training data. This convergence rate depends mainly on the variance between classes, but not on the variance within the classes. In the case of $C\ll N$ ($N$ is the training data size), SSAG’s convergence rate is much better than SAG’s convergence rate of $\mathcal {O}((1-\frac{\mu}{8NL})^k)$. Our experimental results show SSAG outperforms SAG and many other algorithms.
Tasks
Published	2017-10-21
URL	http://arxiv.org/abs/1710.07783v3
PDF	http://arxiv.org/pdf/1710.07783v3.pdf
PWC	https://paperswithcode.com/paper/a-novel-stochastic-stratified-average
Repo
Framework

Optimizing Quantum Models of Classical Channels: The reverse Holevo problem


Title	Optimizing Quantum Models of Classical Channels: The reverse Holevo problem
Authors	S. Loomis, J. R. Mahoney, C. Aghamohammadi, J. P. Crutchfield
Abstract	Given a classical channel—a stochastic map from inputs to outputs—the input can often be transformed to an intermediate variable that is informationally smaller than the input. The new channel accurately simulates the original but at a smaller transmission rate. Here, we examine this procedure when the intermediate variable is a quantum state. We determine when and how well quantum simulations of classical channels may improve upon the minimal rates of classical simulation. This inverts Holevo’s original question of quantifying the capacity of quantum channels with classical resources. We also show that this problem is equivalent to another, involving the local generation of a distribution from common entanglement.
Tasks
Published	2017-09-23
URL	https://arxiv.org/abs/1709.08101v2
PDF	https://arxiv.org/pdf/1709.08101v2.pdf
PWC	https://paperswithcode.com/paper/classical-and-quantum-factors-of-channels
Repo
Framework

A Novel Way of Identifying Cyber Predators


Title	A Novel Way of Identifying Cyber Predators
Authors	Dan Liu, Ching Yee Suen, Olga Ormandjieva
Abstract	Recurrent Neural Networks with Long Short-Term Memory cell (LSTM-RNN) have impressive ability in sequence data processing, particularly for language model building and text classification. This research proposes the combination of sentiment analysis, new approach of sentence vectors and LSTM-RNN as a novel way for Sexual Predator Identification (SPI). LSTM-RNN language model is applied to generate sentence vectors which are the last hidden states in the language model. Sentence vectors are fed into another LSTM-RNN classifier, so as to capture suspicious conversations. Hidden state enables to generate vectors for sentences never seen before. Fasttext is used to filter the contents of conversations and generate a sentiment score so as to identify potential predators. The experiment achieves a record-breaking accuracy and precision of 100% with recall of 81.10%, exceeding the top-ranked result in the SPI competition.
Tasks	Language Modelling, Sentiment Analysis, Text Classification
Published	2017-12-11
URL	http://arxiv.org/abs/1712.03903v1
PDF	http://arxiv.org/pdf/1712.03903v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-way-of-identifying-cyber-predators
Repo
Framework

A Continuous Opinion Dynamic Model in Co-evolving Networks–A Novel Group Decision Approach


Title	A Continuous Opinion Dynamic Model in Co-evolving Networks–A Novel Group Decision Approach
Authors	Qingxing Dong, Xin Zhou
Abstract	Opinion polarization is a ubiquitous phenomenon in opinion dynamics. In contrast to the traditional consensus oriented group decision making (GDM) framework, this paper proposes a framework with the co-evolution of both opinions and relationship networks to improve the potential consensus level of a group and help the group reach a stable state. Taking the bound of confidence and the degree of individual’s persistence into consideration, the evolution of the opinion is driven by the relationship among the group. Meanwhile, the antagonism or cooperation of individuals presented by the network topology also evolve according to the dynamic opinion distances. Opinions are convergent and the stable state will be reached in this co-evolution mechanism. We further explored this framework through simulation experiments. The simulation results verify the influence of the level of persistence on the time cost and indicate the influence of group size, the initial topology of networks and the bound of confidence on the number of opinion clusters.
Tasks	Decision Making
Published	2017-05-17
URL	http://arxiv.org/abs/1705.05981v1
PDF	http://arxiv.org/pdf/1705.05981v1.pdf
PWC	https://paperswithcode.com/paper/a-continuous-opinion-dynamic-model-in-co
Repo
Framework

Dynamic Discovery of Type Classes and Relations in Semantic Web Data


Title	Dynamic Discovery of Type Classes and Relations in Semantic Web Data
Authors	Serkan Ayvaz, Mehmet Aydar
Abstract	The continuing development of Semantic Web technologies and the increasing user adoption in the recent years have accelerated the progress incorporating explicit semantics with data on the Web. With the rapidly growing RDF (Resource Description Framework) data on the Semantic Web, processing large semantic graph data have become more challenging. Constructing a summary graph structure from the raw RDF can help obtain semantic type relations and reduce the computational complexity for graph processing purposes. In this paper, we addressed the problem of graph summarization in RDF graphs, and we proposed an approach for building summary graph structures automatically from RDF graph data. Moreover, we introduced a measure to help discover optimum class dissimilarity thresholds and an effective method to discover the type classes automatically. In future work, we plan to investigate further improvement options on the scalability of the proposed method.
Tasks
Published	2017-05-31
URL	http://arxiv.org/abs/1706.02591v1
PDF	http://arxiv.org/pdf/1706.02591v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-discovery-of-type-classes-and
Repo
Framework

When 3D-Aided 2D Face Recognition Meets Deep Learning: An extended UR2D for Pose-Invariant Face Recognition


Title	When 3D-Aided 2D Face Recognition Meets Deep Learning: An extended UR2D for Pose-Invariant Face Recognition
Authors	Xiang Xu, Pengfei Dou, Ha A. Le, Ioannis A. Kakadiaris
Abstract	Most of the face recognition works focus on specific modules or demonstrate a research idea. This paper presents a pose-invariant 3D-aided 2D face recognition system (UR2D) that is robust to pose variations as large as 90? by leveraging deep learning technology. The architecture and the interface of UR2D are described, and each module is introduced in detail. Extensive experiments are conducted on the UHDB31 and IJB-A, demonstrating that UR2D outperforms existing 2D face recognition systems such as VGG-Face, FaceNet, and a commercial off-the-shelf software (COTS) by at least 9% on the UHDB31 dataset and 3% on the IJB-A dataset on average in face identification tasks. UR2D also achieves state-of-the-art performance of 85% on the IJB-A dataset by comparing the Rank-1 accuracy score from template matching. It fills a gap by providing a 3D-aided 2D face recognition system that has compatible results with 2D face recognition systems using deep learning techniques.
Tasks	Face Identification, Face Recognition, Robust Face Recognition
Published	2017-09-19
URL	http://arxiv.org/abs/1709.06532v1
PDF	http://arxiv.org/pdf/1709.06532v1.pdf
PWC	https://paperswithcode.com/paper/when-3d-aided-2d-face-recognition-meets-deep
Repo
Framework

Nonconvex Sparse Logistic Regression with Weakly Convex Regularization


Title	Nonconvex Sparse Logistic Regression with Weakly Convex Regularization
Authors	Xinyue Shen, Yuantao Gu
Abstract	In this work we propose to fit a sparse logistic regression model by a weakly convex regularized nonconvex optimization problem. The idea is based on the finding that a weakly convex function as an approximation of the $\ell_0$ pseudo norm is able to better induce sparsity than the commonly used $\ell_1$ norm. For a class of weakly convex sparsity inducing functions, we prove the nonconvexity of the corresponding sparse logistic regression problem, and study its local optimality conditions and the choice of the regularization parameter to exclude trivial solutions. Despite the nonconvexity, a method based on proximal gradient descent is used to solve the general weakly convex sparse logistic regression, and its convergence behavior is studied theoretically. Then the general framework is applied to a specific weakly convex function, and a necessary and sufficient local optimality condition is provided. The solution method is instantiated in this case as an iterative firm-shrinkage algorithm, and its effectiveness is demonstrated in numerical experiments by both randomly generated and real datasets.
Tasks
Published	2017-08-07
URL	http://arxiv.org/abs/1708.02059v1
PDF	http://arxiv.org/pdf/1708.02059v1.pdf
PWC	https://paperswithcode.com/paper/nonconvex-sparse-logistic-regression-with
Repo
Framework

Incorporating Global Visual Features into Attention-Based Neural Machine Translation


Title	Incorporating Global Visual Features into Attention-Based Neural Machine Translation
Authors	Iacer Calixto, Qun Liu, Nick Campbell
Abstract	We introduce multi-modal, attention-based neural machine translation (NMT) models which incorporate visual features into different parts of both the encoder and the decoder. We utilise global image features extracted using a pre-trained convolutional neural network and incorporate them (i) as words in the source sentence, (ii) to initialise the encoder hidden state, and (iii) as additional data to initialise the decoder hidden state. In our experiments, we evaluate how these different strategies to incorporate global image features compare and which ones perform best. We also study the impact that adding synthetic multi-modal, multilingual data brings and find that the additional data have a positive impact on multi-modal models. We report new state-of-the-art results and our best models also significantly improve on a comparable phrase-based Statistical MT (PBSMT) model trained on the Multi30k data set according to all metrics evaluated. To the best of our knowledge, it is the first time a purely neural model significantly improves over a PBSMT model on all metrics evaluated on this data set.
Tasks	Machine Translation
Published	2017-01-23
URL	http://arxiv.org/abs/1701.06521v1
PDF	http://arxiv.org/pdf/1701.06521v1.pdf
PWC	https://paperswithcode.com/paper/incorporating-global-visual-features-into
Repo
Framework

Concurrent Activity Recognition with Multimodal CNN-LSTM Structure


Title	Concurrent Activity Recognition with Multimodal CNN-LSTM Structure
Authors	Xinyu Li, Yanyi Zhang, Jianyu Zhang, Shuhong Chen, Ivan Marsic, Richard A. Farneth, Randall S. Burd
Abstract	We introduce a system that recognizes concurrent activities from real-world data captured by multiple sensors of different types. The recognition is achieved in two steps. First, we extract spatial and temporal features from the multimodal data. We feed each datatype into a convolutional neural network that extracts spatial features, followed by a long-short term memory network that extracts temporal information in the sensory data. The extracted features are then fused for decision making in the second step. Second, we achieve concurrent activity recognition with a single classifier that encodes a binary output vector in which elements indicate whether the corresponding activity types are currently in progress. We tested our system with three datasets from different domains recorded using different sensors and achieved performance comparable to existing systems designed specifically for those domains. Our system is the first to address the concurrent activity recognition with multisensory data using a single model, which is scalable, simple to train and easy to deploy.
Tasks	Activity Recognition, Concurrent Activity Recognition, Decision Making
Published	2017-02-06
URL	http://arxiv.org/abs/1702.01638v1
PDF	http://arxiv.org/pdf/1702.01638v1.pdf
PWC	https://paperswithcode.com/paper/concurrent-activity-recognition-with
Repo
Framework

Towards prediction of rapid intensification in tropical cyclones with recurrent neural networks


Title	Towards prediction of rapid intensification in tropical cyclones with recurrent neural networks
Authors	Rohitash Chandra
Abstract	The problem where a tropical cyclone intensifies dramatically within a short period of time is known as rapid intensification. This has been one of the major challenges for tropical weather forecasting. Recurrent neural networks have been promising for time series problems which makes them appropriate for rapid intensification. In this paper, recurrent neural networks are used to predict rapid intensification cases of tropical cyclones from the South Pacific and South Indian Ocean regions. A class imbalanced problem is encountered which makes it very challenging to achieve promising performance. A simple strategy was proposed to include more positive cases for detection where the false positive rate was slightly improved. The limitations of building an efficient system remains due to the challenges of addressing the class imbalance problem encountered for rapid intensification prediction. This motivates further research in using innovative machine learning methods.
Tasks	Time Series, Weather Forecasting
Published	2017-01-17
URL	http://arxiv.org/abs/1701.04518v1
PDF	http://arxiv.org/pdf/1701.04518v1.pdf
PWC	https://paperswithcode.com/paper/towards-prediction-of-rapid-intensification
Repo
Framework

Composition Properties of Inferential Privacy for Time-Series Data


Title	Composition Properties of Inferential Privacy for Time-Series Data
Authors	Shuang Song, Kamalika Chaudhuri
Abstract	With the proliferation of mobile devices and the internet of things, developing principled solutions for privacy in time series applications has become increasingly important. While differential privacy is the gold standard for database privacy, many time series applications require a different kind of guarantee, and a number of recent works have used some form of inferential privacy to address these situations. However, a major barrier to using inferential privacy in practice is its lack of graceful composition – even if the same or related sensitive data is used in multiple releases that are safe individually, the combined release may have poor privacy properties. In this paper, we study composition properties of a form of inferential privacy called Pufferfish when applied to time-series data. We show that while general Pufferfish mechanisms may not compose gracefully, a specific Pufferfish mechanism, called the Markov Quilt Mechanism, which was recently introduced, has strong composition properties comparable to that of pure differential privacy when applied to time series data.
Tasks	Time Series
Published	2017-07-10
URL	http://arxiv.org/abs/1707.02702v1
PDF	http://arxiv.org/pdf/1707.02702v1.pdf
PWC	https://paperswithcode.com/paper/composition-properties-of-inferential-privacy
Repo
Framework

Generalisation in Named Entity Recognition: A Quantitative Analysis


Title	Generalisation in Named Entity Recognition: A Quantitative Analysis
Authors	Isabelle Augenstein, Leon Derczynski, Kalina Bontcheva
Abstract	Named Entity Recognition (NER) is a key NLP task, which is all the more challenging on Web and user-generated content with their diverse and continuously changing language. This paper aims to quantify how this diversity impacts state-of-the-art NER methods, by measuring named entity (NE) and context variability, feature sparsity, and their effects on precision and recall. In particular, our findings indicate that NER approaches struggle to generalise in diverse genres with limited training data. Unseen NEs, in particular, play an important role, which have a higher incidence in diverse genres such as social media than in more regular genres such as newswire. Coupled with a higher incidence of unseen features more generally and the lack of large training corpora, this leads to significantly lower F1 scores for diverse genres as compared to more regular ones. We also find that leading systems rely heavily on surface forms found in training data, having problems generalising beyond these, and offer explanations for this observation.
Tasks	Named Entity Recognition
Published	2017-01-11
URL	http://arxiv.org/abs/1701.02877v2
PDF	http://arxiv.org/pdf/1701.02877v2.pdf
PWC	https://paperswithcode.com/paper/generalisation-in-named-entity-recognition-a
Repo
Framework

Fusing Deep Learned and Hand-Crafted Features of Appearance, Shape, and Dynamics for Automatic Pain Estimation


Title	Fusing Deep Learned and Hand-Crafted Features of Appearance, Shape, and Dynamics for Automatic Pain Estimation
Authors	Joy Egede, Michel Valstar, Brais Martinez
Abstract	Automatic continuous time, continuous value assessment of a patient’s pain from face video is highly sought after by the medical profession. Despite the recent advances in deep learning that attain impressive results in many domains, pain estimation risks not being able to benefit from this due to the difficulty in obtaining data sets of considerable size. In this work we propose a combination of hand-crafted and deep-learned features that makes the most of deep learning techniques in small sample settings. Encoding shape, appearance, and dynamics, our method significantly outperforms the current state of the art, attaining a RMSE error of less than 1 point on a 16-level pain scale, whilst simultaneously scoring a 67.3% Pearson correlation coefficient between our predicted pain level time series and the ground truth.
Tasks	Time Series
Published	2017-01-17
URL	http://arxiv.org/abs/1701.04540v1
PDF	http://arxiv.org/pdf/1701.04540v1.pdf
PWC	https://paperswithcode.com/paper/fusing-deep-learned-and-hand-crafted-features
Repo
Framework