July 26, 2019

3164 words 15 mins read

Paper Group ANR 769

A Vision System for Multi-View Face Recognition. HPX Smart Executors. Transfer Deep Learning for Low-Resource Chinese Word Segmentation with a Novel Neural Network. Union of Intersections (UoI) for Interpretable Data Driven Discovery and Prediction. AirDraw: Leveraging Smart Watch Motion Sensors for Mobile Human Computer Interactions. Human-in-the- …

A Vision System for Multi-View Face Recognition


Title	A Vision System for Multi-View Face Recognition
Authors	M. Y. Shams, A. S. Tolba, S. H. Sarhan
Abstract	Multimodal biometric identification has been grown a great attention in the most interests in the security fields. In the real world there exist modern system devices that are able to detect, recognize, and classify the human identities with reliable and fast recognition rates. Unfortunately most of these systems rely on one modality, and the reliability for two or more modalities are further decreased. The variations of face images with respect to different poses are considered as one of the important challenges in face recognition systems. In this paper, we propose a multimodal biometric system that able to detect the human face images that are not only one view face image, but also multi-view face images. Each subject entered to the system adjusted their face at front of the three cameras, and then the features of the face images are extracted based on Speeded Up Robust Features (SURF) algorithm. We utilize Multi-Layer Perceptron (MLP) and combined classifiers based on both Learning Vector Quantization (LVQ), and Radial Basis Function (RBF) for classification purposes. The proposed system has been tested using SDUMLA-HMT, and CASIA datasets. Furthermore, we collected a database of multi-view face images by which we take the additive white Gaussian noise into considerations. The results indicated the reliability, robustness of the proposed system with different poses and variations including noise images.
Tasks	Face Recognition, Quantization
Published	2017-06-01
URL	http://arxiv.org/abs/1706.00510v1
PDF	http://arxiv.org/pdf/1706.00510v1.pdf
PWC	https://paperswithcode.com/paper/a-vision-system-for-multi-view-face
Repo
Framework

HPX Smart Executors


Title	HPX Smart Executors
Authors	Zahra Khatami, Lukas Troska, Hartmut Kaiser, J. Ramanujam, Adrian Serio
Abstract	The performance of many parallel applications depends on loop-level parallelism. However, manually parallelizing all loops may result in degrading parallel performance, as some of them cannot scale desirably to a large number of threads. In addition, the overheads of manually tuning loop parameters might prevent an application from reaching its maximum parallel performance. We illustrate how machine learning techniques can be applied to address these challenges. In this research, we develop a framework that is able to automatically capture the static and dynamic information of a loop. Moreover, we advocate a novel method by introducing HPX smart executors for determining the execution policy, chunk size, and prefetching distance of an HPX loop to achieve higher possible performance by feeding static information captured during compilation and runtime-based dynamic information to our learning model. Our evaluated execution results show that using these smart executors can speed up the HPX execution process by around 12%-35% for the Matrix Multiplication, Stream and $2D$ Stencil benchmarks compared to setting their HPX loop’s execution policy/parameters manually or using HPX auto-parallelization techniques.
Tasks
Published	2017-11-05
URL	http://arxiv.org/abs/1711.01519v1
PDF	http://arxiv.org/pdf/1711.01519v1.pdf
PWC	https://paperswithcode.com/paper/hpx-smart-executors
Repo
Framework

Transfer Deep Learning for Low-Resource Chinese Word Segmentation with a Novel Neural Network


Title	Transfer Deep Learning for Low-Resource Chinese Word Segmentation with a Novel Neural Network
Authors	Jingjing Xu, Xu Sun
Abstract	Recent studies have shown effectiveness in using neural networks for Chinese word segmentation. However, these models rely on large-scale data and are less effective for low-resource datasets because of insufficient training data. We propose a transfer learning method to improve low-resource word segmentation by leveraging high-resource corpora. First, we train a teacher model on high-resource corpora and then use the learned knowledge to initialize a student model. Second, a weighted data similarity method is proposed to train the student model on low-resource data. Experiment results show that our work significantly improves the performance on low-resource datasets: 2.3% and 1.5% F-score on PKU and CTB datasets. Furthermore, this paper achieves state-of-the-art results: 96.1%, and 96.2% F-score on PKU and CTB datasets.
Tasks	Chinese Word Segmentation, Transfer Learning
Published	2017-02-15
URL	http://arxiv.org/abs/1702.04488v5
PDF	http://arxiv.org/pdf/1702.04488v5.pdf
PWC	https://paperswithcode.com/paper/transfer-deep-learning-for-low-resource
Repo
Framework

Union of Intersections (UoI) for Interpretable Data Driven Discovery and Prediction


Title	Union of Intersections (UoI) for Interpretable Data Driven Discovery and Prediction
Authors	Kristofer E. Bouchard, Alejandro F. Bujan, Farbod Roosta-Khorasani, Shashanka Ubaru, Prabhat, Antoine M. Snijders, Jian-Hua Mao, Edward F. Chang, Michael W. Mahoney, Sharmodeep Bhattacharyya
Abstract	The increasing size and complexity of scientific data could dramatically enhance discovery and prediction for basic scientific applications. Realizing this potential, however, requires novel statistical analysis methods that are both interpretable and predictive. We introduce Union of Intersections (UoI), a flexible, modular, and scalable framework for enhanced model selection and estimation. Methods based on UoI perform model selection and model estimation through intersection and union operations, respectively. We show that UoI-based methods achieve low-variance and nearly unbiased estimation of a small number of interpretable features, while maintaining high-quality prediction accuracy. We perform extensive numerical investigation to evaluate a UoI algorithm ($UoI_{Lasso}$) on synthetic and real data. In doing so, we demonstrate the extraction of interpretable functional networks from human electrophysiology recordings as well as accurate prediction of phenotypes from genotype-phenotype data with reduced features. We also show (with the $UoI_{L1Logistic}$ and $UoI_{CUR}$ variants of the basic framework) improved prediction parsimony for classification and matrix factorization on several benchmark biomedical data sets. These results suggest that methods based on the UoI framework could improve interpretation and prediction in data-driven discovery across scientific fields.
Tasks	Model Selection
Published	2017-05-22
URL	http://arxiv.org/abs/1705.07585v2
PDF	http://arxiv.org/pdf/1705.07585v2.pdf
PWC	https://paperswithcode.com/paper/union-of-intersections-uoi-for-interpretable
Repo
Framework

AirDraw: Leveraging Smart Watch Motion Sensors for Mobile Human Computer Interactions


Title	AirDraw: Leveraging Smart Watch Motion Sensors for Mobile Human Computer Interactions
Authors	Seyed A Sajjadi, Danial Moazen, Ani Nahapetian
Abstract	Wearable computing is one of the fastest growing technologies today. Smart watches are poised to take over at least of half the wearable devices market in the near future. Smart watch screen size, however, is a limiting factor for growth, as it restricts practical text input. On the other hand, wearable devices have some features, such as consistent user interaction and hands-free, heads-up operations, which pave the way for gesture recognition methods of text entry. This paper proposes a new text input method for smart watches, which utilizes motion sensor data and machine learning approaches to detect letters written in the air by a user. This method is less computationally intensive and less expensive when compared to computer vision approaches. It is also not affected by lighting factors, which limit computer vision solutions. The AirDraw system prototype developed to test this approach is presented. Additionally, experimental results close to 71% accuracy are presented.
Tasks	Gesture Recognition
Published	2017-05-07
URL	http://arxiv.org/abs/1705.02689v1
PDF	http://arxiv.org/pdf/1705.02689v1.pdf
PWC	https://paperswithcode.com/paper/airdraw-leveraging-smart-watch-motion-sensors
Repo
Framework

Human-in-the-loop Artificial Intelligence


Title	Human-in-the-loop Artificial Intelligence
Authors	Fabio Massimo Zanzotto
Abstract	Little by little, newspapers are revealing the bright future that Artificial Intelligence (AI) is building. Intelligent machines will help everywhere. However, this bright future has a dark side: a dramatic job market contraction before its unpredictable transformation. Hence, in a near future, large numbers of job seekers will need financial support while catching up with these novel unpredictable jobs. This possible job market crisis has an antidote inside. In fact, the rise of AI is sustained by the biggest knowledge theft of the recent years. Learning AI machines are extracting knowledge from unaware skilled or unskilled workers by analyzing their interactions. By passionately doing their jobs, these workers are digging their own graves. In this paper, we propose Human-in-the-loop Artificial Intelligence (HIT-AI) as a fairer paradigm for Artificial Intelligence systems. HIT-AI will reward aware and unaware knowledge producers with a different scheme: decisions of AI systems generating revenues will repay the legitimate owners of the knowledge used for taking those decisions. As modern Robin Hoods, HIT-AI researchers should fight for a fairer Artificial Intelligence that gives back what it steals.
Tasks
Published	2017-10-23
URL	http://arxiv.org/abs/1710.08191v1
PDF	http://arxiv.org/pdf/1710.08191v1.pdf
PWC	https://paperswithcode.com/paper/human-in-the-loop-artificial-intelligence
Repo
Framework

Effects of the optimisation of the margin distribution on generalisation in deep architectures


Title	Effects of the optimisation of the margin distribution on generalisation in deep architectures
Authors	Lech Szymanski, Brendan McCane, Wei Gao, Zhi-Hua Zhou
Abstract	Despite being so vital to success of Support Vector Machines, the principle of separating margin maximisation is not used in deep learning. We show that minimisation of margin variance and not maximisation of the margin is more suitable for improving generalisation in deep architectures. We propose the Halfway loss function that minimises the Normalised Margin Variance (NMV) at the output of a deep learning models and evaluate its performance against the Softmax Cross-Entropy loss on the MNIST, smallNORB and CIFAR-10 datasets.
Tasks
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05646v1
PDF	http://arxiv.org/pdf/1704.05646v1.pdf
PWC	https://paperswithcode.com/paper/effects-of-the-optimisation-of-the-margin
Repo
Framework

Fast and robust tensor decomposition with applications to dictionary learning


Title	Fast and robust tensor decomposition with applications to dictionary learning
Authors	Tselil Schramm, David Steurer
Abstract	We develop fast spectral algorithms for tensor decomposition that match the robustness guarantees of the best known polynomial-time algorithms for this problem based on the sum-of-squares (SOS) semidefinite programming hierarchy. Our algorithms can decompose a 4-tensor with $n$-dimensional orthonormal components in the presence of error with constant spectral norm (when viewed as an $n^2$-by-$n^2$ matrix). The running time is $n^5$ which is close to linear in the input size $n^4$. We also obtain algorithms with similar running time to learn sparsely-used orthogonal dictionaries even when feature representations have constant relative sparsity and non-independent coordinates. The only previous polynomial-time algorithms to solve these problem are based on solving large semidefinite programs. In contrast, our algorithms are easy to implement directly and are based on spectral projections and tensor-mode rearrangements. Or work is inspired by recent of Hopkins, Schramm, Shi, and Steurer (STOC’16) that shows how fast spectral algorithms can achieve the guarantees of SOS for average-case problems. In this work, we introduce general techniques to capture the guarantees of SOS for worst-case problems.
Tasks	Dictionary Learning
Published	2017-06-27
URL	http://arxiv.org/abs/1706.08672v1
PDF	http://arxiv.org/pdf/1706.08672v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-robust-tensor-decomposition-with
Repo
Framework

Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling


Title	Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling
Authors	Kazuya Kawakami, Chris Dyer, Phil Blunsom
Abstract	Fixed-vocabulary language models fail to account for one of the most characteristic statistical facts of natural language: the frequent creation and reuse of new word types. Although character-level language models offer a partial solution in that they can create word types not attested in the training corpus, they do not capture the “bursty” distribution of such words. In this paper, we augment a hierarchical LSTM language model that generates sequences of word tokens character by character with a caching mechanism that learns to reuse previously generated words. To validate our model we construct a new open-vocabulary language modeling corpus (the Multilingual Wikipedia Corpus, MWC) from comparable Wikipedia articles in 7 typologically diverse languages and demonstrate the effectiveness of our model across this range of languages.
Tasks	Language Modelling
Published	2017-04-23
URL	http://arxiv.org/abs/1704.06986v1
PDF	http://arxiv.org/pdf/1704.06986v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-create-and-reuse-words-in-open
Repo
Framework

A Probabilistic Model for the Cold-Start Problem in Rating Prediction using Click Data


Title	A Probabilistic Model for the Cold-Start Problem in Rating Prediction using Click Data
Authors	ThaiBinh Nguyen, Atsuhiro Takasu
Abstract	One of the most efficient methods in collaborative filtering is matrix factorization, which finds the latent vector representations of users and items based on the ratings of users to items. However, a matrix factorization based algorithm suffers from the cold-start problem: it cannot find latent vectors for items to which previous ratings are not available. This paper utilizes click data, which can be collected in abundance, to address the cold-start problem. We propose a probabilistic item embedding model that learns item representations from click data, and a model named EMB-MF, that connects it with a probabilistic matrix factorization for rating prediction. The experiments on three real-world datasets demonstrate that the proposed model is not only effective in recommending items with no previous ratings, but also outperforms competing methods, especially when the data is very sparse.
Tasks
Published	2017-05-05
URL	https://arxiv.org/abs/1705.02085v2
PDF	https://arxiv.org/pdf/1705.02085v2.pdf
PWC	https://paperswithcode.com/paper/a-probabilistic-model-for-the-cold-start
Repo
Framework

The Problem of Coincidence in A Theory of Temporal Multiple Recurrence


Title	The Problem of Coincidence in A Theory of Temporal Multiple Recurrence
Authors	B. O. Akinkunmi
Abstract	Logical theories have been developed which have allowed temporal reasoning about eventualities (a la Galton) such as states, processes, actions, events, processes and complex eventualities such as sequences and recurrences of other eventualities. This paper presents the problem of coincidence within the framework of a first order logical theory formalising temporal multiple recurrence of two sequences of fixed duration eventualities and presents a solution to it The coincidence problem is described as: if two complex eventualities (or eventuality sequences) consisting respectively of component eventualities x0, x1,….,xr and y0, y1, ..,ys both recur over an interval k and all eventualities are of fixed durations, is there a sub-interval of k over which the incidence xt and yu for t between 0..r and s between 0..s coincide. The solution presented here formalises the intuition that a solution can be found by temporal projection over a cycle of the multiple recurrence of both sequences.
Tasks
Published	2017-04-29
URL	http://arxiv.org/abs/1705.00969v1
PDF	http://arxiv.org/pdf/1705.00969v1.pdf
PWC	https://paperswithcode.com/paper/the-problem-of-coincidence-in-a-theory-of
Repo
Framework

Feature learning in feature-sample networks using multi-objective optimization


Title	Feature learning in feature-sample networks using multi-objective optimization
Authors	Filipe Alves Neto Verri, Renato Tinós, Liang Zhao
Abstract	Data and knowledge representation are fundamental concepts in machine learning. The quality of the representation impacts the performance of the learning model directly. Feature learning transforms or enhances raw data to structures that are effectively exploited by those models. In recent years, several works have been using complex networks for data representation and analysis. However, no feature learning method has been proposed for such category of techniques. Here, we present an unsupervised feature learning mechanism that works on datasets with binary features. First, the dataset is mapped into a feature–sample network. Then, a multi-objective optimization process selects a set of new vertices to produce an enhanced version of the network. The new features depend on a nonlinear function of a combination of preexisting features. Effectively, the process projects the input data into a higher-dimensional space. To solve the optimization problem, we design two metaheuristics based on the lexicographic genetic algorithm and the improved strength Pareto evolutionary algorithm (SPEA2). We show that the enhanced network contains more information and can be exploited to improve the performance of machine learning methods. The advantages and disadvantages of each optimization strategy are discussed.
Tasks
Published	2017-10-25
URL	http://arxiv.org/abs/1710.09300v1
PDF	http://arxiv.org/pdf/1710.09300v1.pdf
PWC	https://paperswithcode.com/paper/feature-learning-in-feature-sample-networks
Repo
Framework

Improving Scalability of Inductive Logic Programming via Pruning and Best-Effort Optimisation


Title	Improving Scalability of Inductive Logic Programming via Pruning and Best-Effort Optimisation
Authors	Mishal Kazmi, Peter Schüller, Yücel Saygın
Abstract	Inductive Logic Programming (ILP) combines rule-based and statistical artificial intelligence methods, by learning a hypothesis comprising a set of rules given background knowledge and constraints for the search space. We focus on extending the XHAIL algorithm for ILP which is based on Answer Set Programming and we evaluate our extensions using the Natural Language Processing application of sentence chunking. With respect to processing natural language, ILP can cater for the constant change in how we use language on a daily basis. At the same time, ILP does not require huge amounts of training examples such as other statistical methods and produces interpretable results, that means a set of rules, which can be analysed and tweaked if necessary. As contributions we extend XHAIL with (i) a pruning mechanism within the hypothesis generalisation algorithm which enables learning from larger datasets, (ii) a better usage of modern solver technology using recently developed optimisation methods, and (iii) a time budget that permits the usage of suboptimal results. We evaluate these improvements on the task of sentence chunking using three datasets from a recent SemEval competition. Results show that our improvements allow for learning on bigger datasets with results that are of similar quality to state-of-the-art systems on the same task. Moreover, we compare the hypotheses obtained on datasets to gain insights on the structure of each dataset.
Tasks	Chunking
Published	2017-06-16
URL	http://arxiv.org/abs/1706.05171v1
PDF	http://arxiv.org/pdf/1706.05171v1.pdf
PWC	https://paperswithcode.com/paper/improving-scalability-of-inductive-logic
Repo
Framework

On Identification of Distribution Grids


Title	On Identification of Distribution Grids
Authors	Omid Ardakanian, Vincent W. S. Wong, Roel Dobbe, Steven H. Low, Alexandra von Meier, Claire Tomlin, Ye Yuan
Abstract	Large-scale integration of distributed energy resources into residential distribution feeders necessitates careful control of their operation through power flow analysis. While the knowledge of the distribution system model is crucial for this type of analysis, it is often unavailable or outdated. The recent introduction of synchrophasor technology in low-voltage distribution grids has created an unprecedented opportunity to learn this model from high-precision, time-synchronized measurements of voltage and current phasors at various locations. This paper focuses on joint estimation of model parameters (admittance values) and operational structure of a poly-phase distribution network from the available telemetry data via the lasso, a method for regression shrinkage and selection. We propose tractable convex programs capable of tackling the low rank structure of the distribution system and develop an online algorithm for early detection and localization of critical events that induce a change in the admittance matrix. The efficacy of these techniques is corroborated through power flow studies on four three-phase radial distribution systems serving real household demands.
Tasks
Published	2017-11-05
URL	http://arxiv.org/abs/1711.01526v1
PDF	http://arxiv.org/pdf/1711.01526v1.pdf
PWC	https://paperswithcode.com/paper/on-identification-of-distribution-grids
Repo
Framework

Tumor Classification and Segmentation of MR Brain Images


Title	Tumor Classification and Segmentation of MR Brain Images
Authors	Tanvi Gupta, Pranay Manocha, Tapan K. Gandhi, RK Gupta, BK Panigrahi
Abstract	The diagnosis and segmentation of tumors using any medical diagnostic tool can be challenging due to the varying nature of this pathology. Magnetic Reso- nance Imaging (MRI) is an established diagnostic tool for various diseases and disorders and plays a major role in clinical neuro-diagnosis. Supplementing this technique with automated classification and segmentation tools is gaining importance, to reduce errors and time needed to make a conclusive diagnosis. In this paper a simple three-step algorithm is proposed; (1) identification of patients that present with tumors, (2) automatic selection of abnormal slices of the patients, and (3) segmentation and detection of the tumor. Features were extracted by using discrete wavelet transform on the normalized images and classified by support vector machine (for step (1)) and random forest (for step (2)). The 400 subjects were divided in a 3:1 ratio between training and test with no overlap. This study is novel in terms of use of data, as it employed the entire T2 weighted slices as a single image for classification and a unique combination of contralateral approach with patch thresholding for segmentation, which does not require a training set or a template as is used by most segmentation studies. Using the proposed method, the tumors were segmented accurately with a classification accuracy of 95% with 100% specificity and 90% sensitivity.
Tasks
Published	2017-10-31
URL	http://arxiv.org/abs/1710.11309v1
PDF	http://arxiv.org/pdf/1710.11309v1.pdf
PWC	https://paperswithcode.com/paper/tumor-classification-and-segmentation-of-mr
Repo
Framework