July 29, 2019

3362 words 16 mins read

Paper Group ANR 160

DeepConfig: Automating Data Center Network Topologies Management with Machine Learning. On Improving the Capacity of Solving Large-scale Wireless Network Design Problems by Genetic Algorithms. Deep Stacking Networks for Low-Resource Chinese Word Segmentation with Transfer Learning. Variable Annealing Length and Parallelism in Simulated Annealing. A …

DeepConfig: Automating Data Center Network Topologies Management with Machine Learning


Title	DeepConfig: Automating Data Center Network Topologies Management with Machine Learning
Authors	Christopher Streiffer, Huan Chen, Theophilus Benson, Asim Kadav
Abstract	In recent years, many techniques have been developed to improve the performance and efficiency of data center networks. While these techniques provide high accuracy, they are often designed using heuristics that leverage domain-specific properties of the workload or hardware. In this vision paper, we argue that many data center networking techniques, e.g., routing, topology augmentation, energy savings, with diverse goals actually share design and architectural similarity. We present a design for developing general intermediate representations of network topologies using deep learning that is amenable to solving classes of data center problems. We develop a framework, DeepConfig, that simplifies the processing of configuring and training deep learning agents that use the intermediate representation to learns different tasks. To illustrate the strength of our approach, we configured, implemented, and evaluated a DeepConfig-Agent that tackles the data center topology augmentation problem. Our initial results are promising — DeepConfig performs comparably to the optimal.
Tasks
Published	2017-12-11
URL	http://arxiv.org/abs/1712.03890v1
PDF	http://arxiv.org/pdf/1712.03890v1.pdf
PWC	https://paperswithcode.com/paper/deepconfig-automating-data-center-network
Repo
Framework

On Improving the Capacity of Solving Large-scale Wireless Network Design Problems by Genetic Algorithms


Title	On Improving the Capacity of Solving Large-scale Wireless Network Design Problems by Genetic Algorithms
Authors	Fabio D’Andreagiovanni
Abstract	Over the last decade, wireless networks have experienced an impressive growth and now play a main role in many telecommunications systems. As a consequence, scarce radio resources, such as frequencies, became congested and the need for effective and efficient assignment methods arose. In this work, we present a Genetic Algorithm for solving large instances of the Power, Frequency and Modulation Assignment Problem, arising in the design of wireless networks. To our best knowledge, this is the first Genetic Algorithm that is proposed for such problem. Compared to previous works, our approach allows a wider exploration of the set of power solutions, while eliminating sources of numerical problems. The performance of the algorithm is assessed by tests over a set of large realistic instances of a Fixed WiMAX Network.
Tasks
Published	2017-04-15
URL	http://arxiv.org/abs/1704.05367v1
PDF	http://arxiv.org/pdf/1704.05367v1.pdf
PWC	https://paperswithcode.com/paper/on-improving-the-capacity-of-solving-large
Repo
Framework

Deep Stacking Networks for Low-Resource Chinese Word Segmentation with Transfer Learning


Title	Deep Stacking Networks for Low-Resource Chinese Word Segmentation with Transfer Learning
Authors	Jingjing Xu, Xu Sun, Sujian Li, Xiaoyan Cai, Bingzhen Wei
Abstract	In recent years, neural networks have proven to be effective in Chinese word segmentation. However, this promising performance relies on large-scale training data. Neural networks with conventional architectures cannot achieve the desired results in low-resource datasets due to the lack of labelled training data. In this paper, we propose a deep stacking framework to improve the performance on word segmentation tasks with insufficient data by integrating datasets from diverse domains. Our framework consists of two parts, domain-based models and deep stacking networks. The domain-based models are used to learn knowledge from different datasets. The deep stacking networks are designed to integrate domain-based models. To reduce model conflicts, we innovatively add communication paths among models and design various structures of deep stacking networks, including Gaussian-based Stacking Networks, Concatenate-based Stacking Networks, Sequence-based Stacking Networks and Tree-based Stacking Networks. We conduct experiments on six low-resource datasets from various domains. Our proposed framework shows significant performance improvements on all datasets compared with several strong baselines.
Tasks	Chinese Word Segmentation, Transfer Learning
Published	2017-11-04
URL	http://arxiv.org/abs/1711.01427v1
PDF	http://arxiv.org/pdf/1711.01427v1.pdf
PWC	https://paperswithcode.com/paper/deep-stacking-networks-for-low-resource
Repo
Framework

Variable Annealing Length and Parallelism in Simulated Annealing


Title	Variable Annealing Length and Parallelism in Simulated Annealing
Authors	Vincent A. Cicirello
Abstract	In this paper, we propose: (a) a restart schedule for an adaptive simulated annealer, and (b) parallel simulated annealing, with an adaptive and parameter-free annealing schedule. The foundation of our approach is the Modified Lam annealing schedule, which adaptively controls the temperature parameter to track a theoretically ideal rate of acceptance of neighboring states. A sequential implementation of Modified Lam simulated annealing is almost parameter-free. However, it requires prior knowledge of the annealing length. We eliminate this parameter using restarts, with an exponentially increasing schedule of annealing lengths. We then extend this restart schedule to parallel implementation, executing several Modified Lam simulated annealers in parallel, with varying initial annealing lengths, and our proposed parallel annealing length schedule. To validate our approach, we conduct experiments on an NP-Hard scheduling problem with sequence-dependent setup constraints. We compare our approach to fixed length restarts, both sequentially and in parallel. Our results show that our approach can achieve substantial performance gains, throughout the course of the run, demonstrating our approach to be an effective anytime algorithm.
Tasks
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02877v1
PDF	http://arxiv.org/pdf/1709.02877v1.pdf
PWC	https://paperswithcode.com/paper/variable-annealing-length-and-parallelism-in
Repo
Framework

Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization


Title	Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization
Authors	Humam Alwassel, Fabian Caba Heilbron, Bernard Ghanem
Abstract	State-of-the-art temporal action detectors inefficiently search the entire video for specific actions. Despite the encouraging progress these methods achieve, it is crucial to design automated approaches that only explore parts of the video which are the most relevant to the actions being searched for. To address this need, we propose the new problem of action spotting in video, which we define as finding a specific action in a video while observing a small portion of that video. Inspired by the observation that humans are extremely efficient and accurate in spotting and finding action instances in video, we propose Action Search, a novel Recurrent Neural Network approach that mimics the way humans spot actions. Moreover, to address the absence of data recording the behavior of human annotators, we put forward the Human Searches dataset, which compiles the search sequences employed by human annotators spotting actions in the AVA and THUMOS14 datasets. We consider temporal action localization as an application of the action spotting problem. Experiments on the THUMOS14 dataset reveal that our model is not only able to explore the video efficiently (observing on average 17.3% of the video) but it also accurately finds human activities with 30.8% mAP.
Tasks	Action Localization, Action Spotting, Temporal Action Localization
Published	2017-06-13
URL	http://arxiv.org/abs/1706.04269v2
PDF	http://arxiv.org/pdf/1706.04269v2.pdf
PWC	https://paperswithcode.com/paper/action-search-spotting-actions-in-videos-and
Repo
Framework

Fairness-aware machine learning: a perspective


Title	Fairness-aware machine learning: a perspective
Authors	Indre Zliobaite
Abstract	Algorithms learned from data are increasingly used for deciding many aspects in our life: from movies we see, to prices we pay, or medicine we get. Yet there is growing evidence that decision making by inappropriately trained algorithms may unintentionally discriminate people. For example, in automated matching of candidate CVs with job descriptions, algorithms may capture and propagate ethnicity related biases. Several repairs for selected algorithms have already been proposed, but the underlying mechanisms how such discrimination happens from the computational perspective are not yet scientifically understood. We need to develop theoretical understanding how algorithms may become discriminatory, and establish fundamental machine learning principles for prevention. We need to analyze machine learning process as a whole to systematically explain the roots of discrimination occurrence, which will allow to devise global machine learning optimization criteria for guaranteed prevention, as opposed to pushing empirical constraints into existing algorithms case-by-case. As a result, the state-of-the-art will advance from heuristic repairing, to proactive and theoretically supported prevention. This is needed not only because law requires to protect vulnerable people. Penetration of big data initiatives will only increase, and computer science needs to provide solid explanations and accountability to the public, before public concerns lead to unnecessarily restrictive regulations against machine learning.
Tasks	Decision Making
Published	2017-08-02
URL	http://arxiv.org/abs/1708.00754v1
PDF	http://arxiv.org/pdf/1708.00754v1.pdf
PWC	https://paperswithcode.com/paper/fairness-aware-machine-learning-a-perspective
Repo
Framework

Applying Deep Bidirectional LSTM and Mixture Density Network for Basketball Trajectory Prediction


Title	Applying Deep Bidirectional LSTM and Mixture Density Network for Basketball Trajectory Prediction
Authors	Yu Zhao, Rennong Yang, Guillaume Chevalier, Rajiv Shah, Rob Romijnders
Abstract	Data analytics helps basketball teams to create tactics. However, manual data collection and analytics are costly and ineffective. Therefore, we applied a deep bidirectional long short-term memory (BLSTM) and mixture density network (MDN) approach. This model is not only capable of predicting a basketball trajectory based on real data, but it also can generate new trajectory samples. It is an excellent application to help coaches and players decide when and where to shoot. Its structure is particularly suitable for dealing with time series problems. BLSTM receives forward and backward information at the same time, while stacking multiple BLSTMs further increases the learning ability of the model. Combined with BLSTMs, MDN is used to generate a multi-modal distribution of outputs. Thus, the proposed model can, in principle, represent arbitrary conditional probability distributions of output variables. We tested our model with two experiments on three-pointer datasets from NBA SportVu data. In the hit-or-miss classification experiment, the proposed model outperformed other models in terms of the convergence speed and accuracy. In the trajectory generation experiment, eight model-generated trajectories at a given time closely matched real trajectories.
Tasks	Time Series, Trajectory Prediction
Published	2017-08-19
URL	http://arxiv.org/abs/1708.05824v1
PDF	http://arxiv.org/pdf/1708.05824v1.pdf
PWC	https://paperswithcode.com/paper/applying-deep-bidirectional-lstm-and-mixture
Repo
Framework

Automatic sleep monitoring using ear-EEG


Title	Automatic sleep monitoring using ear-EEG
Authors	Takashi Nakamura, Valentin Goverdovsky, Mary J. Morrell, Danilo P. Mandic
Abstract	The monitoring of sleep patterns without patient’s inconvenience or involvement of a medical specialist is a clinical question of significant importance. To this end, we propose an automatic sleep stage monitoring system based on an affordable, unobtrusive, discreet, and long-term wearable in-ear sensor for recording the Electroencephalogram (ear-EEG). The selected features for sleep pattern classification from a single ear-EEG channel include the spectral edge frequency (SEF) and multi- scale fuzzy entropy (MSFE), a structural complexity feature. In this preliminary study, the manually scored hypnograms from simultaneous scalp-EEG and ear-EEG recordings of four subjects are used as labels for two analysis scenarios: 1) classification of ear-EEG hypnogram labels from ear-EEG recordings and 2) prediction of scalp-EEG hypnogram labels from ear-EEG recordings. We consider both 2-class and 4-class sleep scoring, with the achieved accuracies ranging from 78.5 % to 95.2 % for ear-EEG labels predicted from ear-EEG, and 76.8 % to 91.8 % for scalp-EEG labels predicted from ear-EEG. The corresponding kappa coefficients, which range from 0.64 to 0.83 for Scenario 1 and from 0.65 to 0.80 for Scenario 2, indicate a Substantial to Almost Perfect agreement, thus proving the feasibility of in-ear sensing for sleep monitoring in the community.
Tasks	EEG
Published	2017-01-03
URL	http://arxiv.org/abs/1701.04398v1
PDF	http://arxiv.org/pdf/1701.04398v1.pdf
PWC	https://paperswithcode.com/paper/automatic-sleep-monitoring-using-ear-eeg
Repo
Framework

Word Searching in Scene Image and Video Frame in Multi-Script Scenario using Dynamic Shape Coding


Title	Word Searching in Scene Image and Video Frame in Multi-Script Scenario using Dynamic Shape Coding
Authors	Partha Pratim Roy, Ayan Kumar Bhunia, Avirup Bhattacharyya, Umapada Pal
Abstract	Retrieval of text information from natural scene images and video frames is a challenging task due to its inherent problems like complex character shapes, low resolution, background noise, etc. Available OCR systems often fail to retrieve such information in scene/video frames. Keyword spotting, an alternative way to retrieve information, performs efficient text searching in such scenarios. However, current word spotting techniques in scene/video images are script-specific and they are mainly developed for Latin script. This paper presents a novel word spotting framework using dynamic shape coding for text retrieval in natural scene image and video frames. The framework is designed to search query keyword from multiple scripts with the help of on-the-fly script-wise keyword generation for the corresponding script. We have used a two-stage word spotting approach using Hidden Markov Model (HMM) to detect the translated keyword in a given text line by identifying the script of the line. A novel unsupervised dynamic shape coding based scheme has been used to group similar shape characters to avoid confusion and to improve text alignment. Next, the hypotheses locations are verified to improve retrieval performance. To evaluate the proposed system for searching keyword from natural scene image and video frames, we have considered two popular Indic scripts such as Bangla (Bengali) and Devanagari along with English. Inspired by the zone-wise recognition approach in Indic scripts[1], zone-wise text information has been used to improve the traditional word spotting performance in Indic scripts. For our experiment, a dataset consisting of images of different scenes and video frames of English, Bangla and Devanagari scripts were considered. The results obtained showed the effectiveness of our proposed word spotting approach.
Tasks	Keyword Spotting, Optical Character Recognition
Published	2017-08-18
URL	http://arxiv.org/abs/1708.05529v6
PDF	http://arxiv.org/pdf/1708.05529v6.pdf
PWC	https://paperswithcode.com/paper/word-searching-in-scene-image-and-video-frame
Repo
Framework

Learning Sparse Polymatrix Games in Polynomial Time and Sample Complexity


Title	Learning Sparse Polymatrix Games in Polynomial Time and Sample Complexity
Authors	Asish Ghoshal, Jean Honorio
Abstract	We consider the problem of learning sparse polymatrix games from observations of strategic interactions. We show that a polynomial time method based on $\ell_{1,2}$-group regularized logistic regression recovers a game, whose Nash equilibria are the $\epsilon$-Nash equilibria of the game from which the data was generated (true game), in $\mathcal{O}(m^4 d^4 \log (pd))$ samples of strategy profiles — where $m$ is the maximum number of pure strategies of a player, $p$ is the number of players, and $d$ is the maximum degree of the game graph. Under slightly more stringent separability conditions on the payoff matrices of the true game, we show that our method learns a game with the exact same Nash equilibria as the true game. We also show that $\Omega(d \log (pm))$ samples are necessary for any method to consistently recover a game, with the same Nash-equilibria as the true game, from observations of strategic interactions. We verify our theoretical results through simulation experiments.
Tasks
Published	2017-06-18
URL	http://arxiv.org/abs/1706.05648v2
PDF	http://arxiv.org/pdf/1706.05648v2.pdf
PWC	https://paperswithcode.com/paper/learning-sparse-polymatrix-games-in
Repo
Framework

Intriguing Properties of Adversarial Examples


Title	Intriguing Properties of Adversarial Examples
Authors	Ekin D. Cubuk, Barret Zoph, Samuel S. Schoenholz, Quoc V. Le
Abstract	It is becoming increasingly clear that many machine learning classifiers are vulnerable to adversarial examples. In attempting to explain the origin of adversarial examples, previous studies have typically focused on the fact that neural networks operate on high dimensional data, they overfit, or they are too linear. Here we argue that the origin of adversarial examples is primarily due to an inherent uncertainty that neural networks have about their predictions. We show that the functional form of this uncertainty is independent of architecture, dataset, and training protocol; and depends only on the statistics of the logit differences of the network, which do not change significantly during training. This leads to adversarial error having a universal scaling, as a power-law, with respect to the size of the adversarial perturbation. We show that this universality holds for a broad range of datasets (MNIST, CIFAR10, ImageNet, and random data), models (including state-of-the-art deep networks, linear models, adversarially trained networks, and networks trained on randomly shuffled labels), and attacks (FGSM, step l.l., PGD). Motivated by these results, we study the effects of reducing prediction entropy on adversarial robustness. Finally, we study the effect of network architectures on adversarial sensitivity. To do this, we use neural architecture search with reinforcement learning to find adversarially robust architectures on CIFAR10. Our resulting architecture is more robust to white \emph{and} black box attacks compared to previous attempts.
Tasks	Neural Architecture Search
Published	2017-11-08
URL	http://arxiv.org/abs/1711.02846v1
PDF	http://arxiv.org/pdf/1711.02846v1.pdf
PWC	https://paperswithcode.com/paper/intriguing-properties-of-adversarial-examples
Repo
Framework

Evaluating gender portrayal in Bangladeshi TV


Title	Evaluating gender portrayal in Bangladeshi TV
Authors	Md. Naimul Hoque, Rawshan E Fatima, Manash Kumar Mandal, Nazmus Saquib
Abstract	Computer Vision and machine learning methods were previously used to reveal screen presence of genders in TV and movies. In this work, using head pose, gender detection, and skin color estimation techniques, we demonstrate that the gender disparity in TV in a South Asian country such as Bangladesh exhibits unique characteristics and is sometimes counter-intuitive to popular perception. We demonstrate a noticeable discrepancy in female screen presence in Bangladeshi TV advertisements and political talk shows. Further, contrary to popular hypotheses, we demonstrate that lighter-toned skin colors are less prevalent than darker complexions, and additionally, quantifiable body language markers do not provide conclusive insights about gender dynamics. Overall, these gender portrayal parameters reveal the different layers of onscreen gender politics and can help direct incentives to address existing disparities in a nuanced and targeted manner.
Tasks
Published	2017-11-14
URL	http://arxiv.org/abs/1711.09728v1
PDF	http://arxiv.org/pdf/1711.09728v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-gender-portrayal-in-bangladeshi-tv
Repo
Framework

Transaction Fraud Detection Using GRU-centered Sandwich-structured Model


Title	Transaction Fraud Detection Using GRU-centered Sandwich-structured Model
Authors	Xurui Li, Wei Yu, Tianyu Luwang, Jianbin Zheng, Xuetao Qiu, Jintao Zhao, Lei Xia, Yujiao Li
Abstract	Rapid growth of modern technologies such as internet and mobile computing are bringing dramatically increased e-commerce payments, as well as the explosion in transaction fraud. Meanwhile, fraudsters are continually refining their tricks, making rule-based fraud detection systems difficult to handle the ever-changing fraud patterns. Many data mining and artificial intelligence methods have been proposed for identifying small anomalies in large transaction data sets, increasing detecting efficiency to some extent. Nevertheless, there is always a contradiction that most methods are irrelevant to transaction sequence, yet sequence-related methods usually cannot learn information at single-transaction level well. In this paper, a new “within->between->within” sandwich-structured sequence learning architecture has been proposed by stacking an ensemble method, a deep sequential learning method and another top-layer ensemble classifier in proper order. Moreover, attention mechanism has also been introduced in to further improve performance. Models in this structure have been manifested to be very efficient in scenarios like fraud detection, where the information sequence is made up of vectors with complex interconnected features.
Tasks	Fraud Detection
Published	2017-11-04
URL	http://arxiv.org/abs/1711.01434v3
PDF	http://arxiv.org/pdf/1711.01434v3.pdf
PWC	https://paperswithcode.com/paper/transaction-fraud-detection-using-gru
Repo
Framework

Sequence-to-Label Script Identification for Multilingual OCR


Title	Sequence-to-Label Script Identification for Multilingual OCR
Authors	Yasuhisa Fujii, Karel Driesen, Jonathan Baccash, Ash Hurst, Ashok C. Popat
Abstract	We describe a novel line-level script identification method. Previous work repurposed an OCR model generating per-character script codes, counted to obtain line-level script identification. This has two shortcomings. First, as a sequence-to-sequence model it is more complex than necessary for the sequence-to-label problem of line script identification. This makes it harder to train and inefficient to run. Second, the counting heuristic may be suboptimal compared to a learned model. Therefore we reframe line script identification as a sequence-to-label problem and solve it using two components, trained end-toend: Encoder and Summarizer. The encoder converts a line image into a feature sequence. The summarizer aggregates the sequence to classify the line. We test various summarizers with identical inception-style convolutional networks as encoders. Experiments on scanned books and photos containing 232 languages in 30 scripts show 16% reduction of script identification error rate compared to the baseline. This improved script identification reduces the character error rate attributable to script misidentification by 33%.
Tasks	Optical Character Recognition
Published	2017-08-15
URL	http://arxiv.org/abs/1708.04671v2
PDF	http://arxiv.org/pdf/1708.04671v2.pdf
PWC	https://paperswithcode.com/paper/sequence-to-label-script-identification-for
Repo
Framework

Convolutional Neural Networks for Font Classification


Title	Convolutional Neural Networks for Font Classification
Authors	Chris Tensmeyer, Daniel Saunders, Tony Martinez
Abstract	Classifying pages or text lines into font categories aids transcription because single font Optical Character Recognition (OCR) is generally more accurate than omni-font OCR. We present a simple framework based on Convolutional Neural Networks (CNNs), where a CNN is trained to classify small patches of text into predefined font classes. To classify page or line images, we average the CNN predictions over densely extracted patches. We show that this method achieves state-of-the-art performance on a challenging dataset of 40 Arabic computer fonts with 98.8% line level accuracy. This same method also achieves the highest reported accuracy of 86.6% in predicting paleographic scribal script classes at the page level on medieval Latin manuscripts. Finally, we analyze what features are learned by the CNN on Latin manuscripts and find evidence that the CNN is learning both the defining morphological differences between scribal script classes as well as overfitting to class-correlated nuisance factors. We propose a novel form of data augmentation that improves robustness to text darkness, further increasing classification performance.
Tasks	Data Augmentation, Optical Character Recognition
Published	2017-08-11
URL	http://arxiv.org/abs/1708.03669v1
PDF	http://arxiv.org/pdf/1708.03669v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-for-font
Repo
Framework