October 19, 2019

3358 words 16 mins read

Paper Group ANR 303

Refining Manually-Designed Symbol Grounding and High-Level Planning by Policy Gradients. Big Data Analytics for Wireless and Wired Network Design: A Survey. Convolutional neural network based automatic plaque characterization from intracoronary optical coherence tomography images. What the Vec? Towards Probabilistically Grounded Embeddings. Native …

Refining Manually-Designed Symbol Grounding and High-Level Planning by Policy Gradients


Title	Refining Manually-Designed Symbol Grounding and High-Level Planning by Policy Gradients
Authors	Takuya Hiraoka, Takashi Onishi, Takahisa Imagawa, Yoshimasa Tsuruoka
Abstract	Hierarchical planners that produce interpretable and appropriate plans are desired, especially in its application to supporting human decision making. In the typical development of the hierarchical planners, higher-level planners and symbol grounding functions are manually created, and this manual creation requires much human effort. In this paper, we propose a framework that can automatically refine symbol grounding functions and a high-level planner to reduce human effort for designing these modules. In our framework, symbol grounding and high-level planning, which are based on manually-designed knowledge bases, are modeled with semi-Markov decision processes. A policy gradient method is then applied to refine the modules, in which two terms for updating the modules are considered. The first term, called a reinforcement term, contributes to updating the modules to improve the overall performance of a hierarchical planner to produce appropriate plans. The second term, called a penalty term, contributes to keeping refined modules consistent with the manually-designed original modules. Namely, it keeps the planner, which uses the refined modules, producing interpretable plans. We perform preliminary experiments to solve the Mountain car problem, and its results show that a manually-designed high-level planner and symbol grounding function were successfully refined by our framework.
Tasks	Decision Making
Published	2018-09-29
URL	http://arxiv.org/abs/1810.00177v1
PDF	http://arxiv.org/pdf/1810.00177v1.pdf
PWC	https://paperswithcode.com/paper/refining-manually-designed-symbol-grounding
Repo
Framework

Big Data Analytics for Wireless and Wired Network Design: A Survey


Title	Big Data Analytics for Wireless and Wired Network Design: A Survey
Authors	Mohammed S. Hadi, Ahmed Q. Lawey, Taisir E. H. El-Gorashi, Jaafar M. H. Elmirghani
Abstract	Currently, the world is witnessing a mounting avalanche of data due to the increasing number of mobile network subscribers, Internet websites, and online services. This trend is continuing to develop in a quick and diverse manner in the form of big data. Big data analytics can process large amounts of raw data and extract useful, smaller-sized information, which can be used by different parties to make reliable decisions. In this paper, we conduct a survey on the role that big data analytics can play in the design of data communication networks. Integrating the latest advances that employ big data analytics with the networks control/traffic layers might be the best way to build robust data communication networks with refined performance and intelligent features. First, the survey starts with the introduction of the big data basic concepts, framework, and characteristics. Second, we illustrate the main network design cycle employing big data analytics. This cycle represents the umbrella concept that unifies the surveyed topics. Third, there is a detailed review of the current academic and industrial efforts toward network design using big data analytics. Forth, we identify the challenges confronting the utilization of big data analytics in network design. Finally, we highlight several future research directions. To the best of our knowledge, this is the first survey that addresses the use of big data analytics techniques for the design of a broad range of networks.
Tasks
Published	2018-01-19
URL	http://arxiv.org/abs/1802.01415v1
PDF	http://arxiv.org/pdf/1802.01415v1.pdf
PWC	https://paperswithcode.com/paper/big-data-analytics-for-wireless-and-wired
Repo
Framework

Convolutional neural network based automatic plaque characterization from intracoronary optical coherence tomography images


Title	Convolutional neural network based automatic plaque characterization from intracoronary optical coherence tomography images
Authors	Shenghua He, Jie Zheng, Akiko Maehara, Gary Mintz, Dalin Tang, Mark Anastasio, Hua Li
Abstract	Optical coherence tomography (OCT) can provide high-resolution cross-sectional images for analyzing superficial plaques in coronary arteries. Commonly, plaque characterization using intra-coronary OCT images is performed manually by expert observers. This manual analysis is time consuming and its accuracy heavily relies on the experience of human observers. Traditional machine learning based methods, such as the least squares support vector machine and random forest methods, have been recently employed to automatically characterize plaque regions in OCT images. Several processing steps, including feature extraction, informative feature selection, and final pixel classification, are commonly used in these traditional methods. Therefore, the final classification accuracy can be jeopardized by error or inaccuracy within each of these steps. In this study, we proposed a convolutional neural network (CNN) based method to automatically characterize plaques in OCT images. Unlike traditional methods, our method uses the image as a direct input and performs classification as a single-step process. The experiments on 269 OCT images showed that the average prediction accuracy of CNN-based method was 0.866, which indicated a great promise for clinical translation.
Tasks	Feature Selection
Published	2018-07-10
URL	http://arxiv.org/abs/1807.03613v1
PDF	http://arxiv.org/pdf/1807.03613v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-network-based-automatic
Repo
Framework

What the Vec? Towards Probabilistically Grounded Embeddings


Title	What the Vec? Towards Probabilistically Grounded Embeddings
Authors	Carl Allen, Ivana Balažević, Timothy Hospedales
Abstract	Word2Vec (W2V) and GloVe are popular, fast and efficient word embedding algorithms. Their embeddings are widely used and perform well on a variety of natural language processing tasks. Moreover, W2V has recently been adopted in the field of graph embedding, where it underpins several leading algorithms. However, despite their ubiquity and relatively simple model architecture, a theoretical understanding of what the embedding parameters of W2V and GloVe learn and why that is useful in downstream tasks has been lacking. We show that different interactions between PMI vectors reflect semantic word relationships, such as similarity and paraphrasing, that are encoded in low dimensional word embeddings under a suitable projection, theoretically explaining why embeddings of W2V and GloVe work. As a consequence, we also reveal an interesting mathematical interconnection between the considered semantic relationships themselves.
Tasks	Graph Embedding, Word Embeddings
Published	2018-05-30
URL	https://arxiv.org/abs/1805.12164v3
PDF	https://arxiv.org/pdf/1805.12164v3.pdf
PWC	https://paperswithcode.com/paper/what-the-vec-towards-probabilistically
Repo
Framework

Native Language Cognate Effects on Second Language Lexical Choice


Title	Native Language Cognate Effects on Second Language Lexical Choice
Authors	Ella Rabinovich, Yulia Tsvetkov, Shuly Wintner
Abstract	We present a computational analysis of cognate effects on the spontaneous linguistic productions of advanced non-native speakers. Introducing a large corpus of highly competent non-native English speakers, and using a set of carefully selected lexical items, we show that the lexical choices of non-natives are affected by cognates in their native language. This effect is so powerful that we are able to reconstruct the phylogenetic language tree of the Indo-European language family solely from the frequencies of specific lexical items in the English of authors with various native languages. We quantitatively analyze non-native lexical choice, highlighting cognate facilitation as one of the important phenomena shaping the language of non-native speakers.
Tasks
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09590v1
PDF	http://arxiv.org/pdf/1805.09590v1.pdf
PWC	https://paperswithcode.com/paper/native-language-cognate-effects-on-second
Repo
Framework

Deep Reinforcement Learning for Optimal Control of Space Heating


Title	Deep Reinforcement Learning for Optimal Control of Space Heating
Authors	Adam Nagy, Hussain Kazmi, Farah Cheaib, Johan Driesen
Abstract	Classical methods to control heating systems are often marred by suboptimal performance, inability to adapt to dynamic conditions and unreasonable assumptions e.g. existence of building models. This paper presents a novel deep reinforcement learning algorithm which can control space heating in buildings in a computationally efficient manner, and benchmarks it against other known techniques. The proposed algorithm outperforms rule based control by between 5-10% in a simulation environment for a number of price signals. We conclude that, while not optimal, the proposed algorithm offers additional practical advantages such as faster computation times and increased robustness to non-stationarities in building dynamics.
Tasks
Published	2018-05-10
URL	http://arxiv.org/abs/1805.03777v1
PDF	http://arxiv.org/pdf/1805.03777v1.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-for-optimal
Repo
Framework

Influencing Flock Formation in Low-Density Settings


Title	Influencing Flock Formation in Low-Density Settings
Authors	Daniel Y. Fu, Emily S. Wang, Peter M. Krafft, Barbara J. Grosz
Abstract	Flocking is a coordinated collective behavior that results from local sensing between individual agents that have a tendency to orient towards each other. Flocking is common among animal groups and might also be useful in robotic swarms. In the interest of learning how to control flocking behavior, recent work in the multiagent systems literature has explored the use of influencing agents for guiding flocking agents to face a target direction. The existing work in this domain has focused on simulation settings of small areas with toroidal shapes. In such settings, agent density is high, so interactions are common, and flock formation occurs easily. In our work, we study new environments with lower agent density, wherein interactions are more rare. We study the efficacy of placement strategies and influencing agent behaviors drawn from the literature, and find that the behaviors that have been shown to work well in high-density conditions tend to be much less effective in lower density environments. The source of this ineffectiveness is that the influencing agents explored in prior work tended to face directions optimized for maximal influence, but which actually separate the influencing agents from the flock. We find that in low-density conditions maintaining a connection to the flock is more important than rushing to orient towards the desired direction. We use these insights to propose new influencing agent behaviors, which we dub “follow-then-influence”; agents act like normal members of the flock to achieve positions that allow for control and then exert their influence. This strategy overcomes the difficulties posed by low density environments.
Tasks
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08667v1
PDF	http://arxiv.org/pdf/1804.08667v1.pdf
PWC	https://paperswithcode.com/paper/influencing-flock-formation-in-low-density
Repo
Framework

Triangle Lasso for Simultaneous Clustering and Optimization in Graph Datasets


Title	Triangle Lasso for Simultaneous Clustering and Optimization in Graph Datasets
Authors	Yawei Zhao, Kai Xu, Xinwang Liu, En Zhu, Xinzhong Zhu, Jianping Yin
Abstract	Recently, network lasso has drawn many attentions due to its remarkable performance on simultaneous clustering and optimization. However, it usually suffers from the imperfect data (noise, missing values etc), and yields sub-optimal solutions. The reason is that it finds the similar instances according to their features directly, which is usually impacted by the imperfect data, and thus returns sub-optimal results. In this paper, we propose triangle lasso to avoid its disadvantage. Triangle lasso finds the similar instances according to their neighbours. If two instances have many common neighbours, they tend to become similar. Although some instances are profiled by the imperfect data, it is still able to find the similar counterparts. Furthermore, we develop an efficient algorithm based on Alternating Direction Method of Multipliers (ADMM) to obtain a moderately accurate solution. In addition, we present a dual method to obtain the accurate solution with the low additional time consumption. We demonstrate through extensive numerical experiments that triangle lasso is robust to the imperfect data. It usually yields a better performance than the state-of-the-art method when performing data analysis tasks in practical scenarios.
Tasks
Published	2018-08-20
URL	http://arxiv.org/abs/1808.06556v1
PDF	http://arxiv.org/pdf/1808.06556v1.pdf
PWC	https://paperswithcode.com/paper/triangle-lasso-for-simultaneous-clustering
Repo
Framework

A temporal neural network model for object recognition using a biologically plausible decision making layer


Title	A temporal neural network model for object recognition using a biologically plausible decision making layer
Authors	Hamed Heidari Gorji, Sajjad Zabbah, Reza Ebrahimpour
Abstract	Brain can recognize different objects as ones that it has experienced before. The recognition accuracy and its processing time depend on task properties such as viewing condition, level of noise and etc. Recognition accuracy can be well explained by different models. However, less attention has been paid to the processing time and the ones that do, are not biologically plausible. By extracting features temporally as well as utilizing an accumulation to bound decision making model, an object recognition model accounting for both recognition time and accuracy is proposed. To temporally extract informative features in support of possible classes of stimuli, a hierarchical spiking neural network, called spiking HMAX is modified. In the decision making part of the model the extracted information accumulates over time using accumulator units. The input category is determined as soon as any of the accumulators reaches a threshold, called decision bound. Results show that not only does the model follow human accuracy in a psychophysics task better than the classic spiking HMAX model, but also it predicts human response time in each choice. Results provide enough evidence that temporal representation of features are informative since they can improve the accuracy of a biological plausible decision maker over time. This is also in line with the well-known idea of speed accuracy trade-off in decision making studies.
Tasks	Decision Making, Object Recognition
Published	2018-06-25
URL	http://arxiv.org/abs/1806.09334v2
PDF	http://arxiv.org/pdf/1806.09334v2.pdf
PWC	https://paperswithcode.com/paper/a-temporal-neural-network-model-for-object
Repo
Framework

AnyThreat: An Opportunistic Knowledge Discovery Approach to Insider Threat Detection


Title	AnyThreat: An Opportunistic Knowledge Discovery Approach to Insider Threat Detection
Authors	Diana Haidar, Mohamed Medhat Gaber, Yevgeniya Kovalchuk
Abstract	Insider threat detection is getting an increased concern from academia, industry, and governments due to the growing number of malicious insider incidents. The existing approaches proposed for detecting insider threats still have a common shortcoming, which is the high number of false alarms (false positives). The challenge in these approaches is that it is essential to detect all anomalous behaviours which belong to a particular threat. To address this shortcoming, we propose an opportunistic knowledge discovery system, namely AnyThreat, with the aim to detect any anomalous behaviour in all malicious insider threats. We design the AnyThreat system with four components. (1) A feature engineering component, which constructs community data sets from the activity logs of a group of users having the same role. (2) An oversampling component, where we propose a novel oversampling technique named Artificial Minority Oversampling and Trapper REmoval (AMOTRE). AMOTRE first removes the minority (anomalous) instances that have a high resemblance with normal (majority) instances to reduce the number of false alarms, then it synthetically oversamples the minority class by shielding the border of the majority class. (3) A class decomposition component, which is introduced to cluster the instances of the majority class into subclasses to weaken the effect of the majority class without information loss. (4) A classification component, which applies a classification method on the subclasses to achieve a better separation between the majority class(es) and the minority class(es). AnyThreat is evaluated on synthetic data sets generated by Carnegie Mellon University. It detects approximately 87.5% of malicious insider threats, and achieves the minimum of false positives=3.36%.
Tasks	Feature Engineering
Published	2018-12-01
URL	http://arxiv.org/abs/1812.00257v1
PDF	http://arxiv.org/pdf/1812.00257v1.pdf
PWC	https://paperswithcode.com/paper/anythreat-an-opportunistic-knowledge
Repo
Framework

Coupled Recurrent Network (CRN)


Title	Coupled Recurrent Network (CRN)
Authors	Lin Sun, Kui Jia, Yuejia Shen, Silvio Savarese, Dit Yan Yeung, Bertram E. Shi
Abstract	Many semantic video analysis tasks can benefit from multiple, heterogenous signals. For example, in addition to the original RGB input sequences, sequences of optical flow are usually used to boost the performance of human action recognition in videos. To learn from these heterogenous input sources, existing methods reply on two-stream architectural designs that contain independent, parallel streams of Recurrent Neural Networks (RNNs). However, two-stream RNNs do not fully exploit the reciprocal information contained in the multiple signals, let alone exploit it in a recurrent manner. To this end, we propose in this paper a novel recurrent architecture, termed Coupled Recurrent Network (CRN), to deal with multiple input sources. In CRN, the parallel streams of RNNs are coupled together. Key design of CRN is a Recurrent Interpretation Block (RIB) that supports learning of reciprocal feature representations from multiple signals in a recurrent manner. Different from RNNs which stack the training loss at each time step or the last time step, we propose an effective and efficient training strategy for CRN. Experiments show the efficacy of the proposed CRN. In particular, we achieve the new state of the art on the benchmark datasets of human action recognition and multi-person pose estimation.
Tasks	Action Recognition In Videos, Multi-Person Pose Estimation, Optical Flow Estimation, Pose Estimation, Temporal Action Localization
Published	2018-12-25
URL	http://arxiv.org/abs/1812.10071v2
PDF	http://arxiv.org/pdf/1812.10071v2.pdf
PWC	https://paperswithcode.com/paper/coupled-recurrent-network-crn
Repo
Framework

End-to-end Learning for Graph Decomposition


Title	End-to-end Learning for Graph Decomposition
Authors	Jie Song, Bjoern Andres, Michael Black, Otmar Hilliges, Siyu Tang
Abstract	We propose a novel end-to-end trainable framework for the graph decomposition problem. The minimum cost multicut problem is first converted to an unconstrained binary cubic formulation where cycle consistency constraints are incorporated into the objective function. The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels of the initial graph and the hard constraints are introduced in the CRF as high-order potentials. The parameters of a standard Neural Network and the fully differentiable CRF are optimized in an end-to-end manner. Furthermore, our method utilizes the cycle constraints as meta-supervisory signals during the learning of the deep feature representations by taking the dependencies between the output random variables into account. We present analyses of the end-to-end learned representations, showing the impact of the joint training, on the task of clustering images of MNIST. We also validate the effectiveness of our approach both for the feature learning and the final clustering on the challenging task of real-world multi-person pose estimation.
Tasks	Multi-Person Pose Estimation, Pose Estimation
Published	2018-12-23
URL	http://arxiv.org/abs/1812.09737v1
PDF	http://arxiv.org/pdf/1812.09737v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-learning-for-graph-decomposition
Repo
Framework

Saliency Detection via Bidirectional Absorbing Markov Chain


Title	Saliency Detection via Bidirectional Absorbing Markov Chain
Authors	Fengling Jiang, Bin Kong, Ahsan Adeel, Yun Xiao, Amir Hussain
Abstract	Traditional saliency detection via Markov chain only considers boundaries nodes. However, in addition to boundaries cues, background prior and foreground prior cues play a complementary role to enhance saliency detection. In this paper, we propose an absorbing Markov chain based saliency detection method considering both boundary information and foreground prior cues. The proposed approach combines both boundaries and foreground prior cues through bidirectional Markov chain. Specifically, the image is first segmented into superpixels and four boundaries nodes (duplicated as virtual nodes) are selected. Subsequently, the absorption time upon transition node’s random walk to the absorbing state is calculated to obtain foreground possibility. Simultaneously, foreground prior as the virtual absorbing nodes is used to calculate the absorption time and obtain the background possibility. Finally, two obtained results are fused to obtain the combined saliency map using cost function for further optimization at multi-scale. Experimental results demonstrate the outperformance of our proposed model on 4 benchmark datasets as compared to 17 state-of-the-art methods.
Tasks	Saliency Detection
Published	2018-08-25
URL	http://arxiv.org/abs/1808.08393v1
PDF	http://arxiv.org/pdf/1808.08393v1.pdf
PWC	https://paperswithcode.com/paper/saliency-detection-via-bidirectional
Repo
Framework

Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint


Title	Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint
Authors	Miaopeng Li, Zimeng Zhou, Jie Li, Xinguo Liu
Abstract	In this work, we propose a new method for multi-person pose estimation which combines the traditional bottom-up and the top-down methods. Specifically, we perform the network feed-forwarding in a bottom-up manner, and then parse the poses with bounding box constraints in a top-down manner. In contrast to the previous top-down methods, our method is robust to bounding box shift and tightness. We extract features from an original image by a residual network and train the network to learn both the confidence maps of joints and the connection relationships between joints. During testing, the predicted confidence maps, the connection relationships and the bounding boxes are used to parse the poses of all persons. The experimental results showed that our method learns more accurate human poses especially in challenging situations and gains better time performance, compared with the bottom-up and the top-down methods.
Tasks	Multi-Person Pose Estimation, Pose Estimation
Published	2018-07-26
URL	http://arxiv.org/abs/1807.09972v1
PDF	http://arxiv.org/pdf/1807.09972v1.pdf
PWC	https://paperswithcode.com/paper/bottom-up-pose-estimation-of-multiple-person
Repo
Framework

Approximate inference with Wasserstein gradient flows


Title	Approximate inference with Wasserstein gradient flows
Authors	Charlie Frogner, Tomaso Poggio
Abstract	We present a novel approximate inference method for diffusion processes, based on the Wasserstein gradient flow formulation of the diffusion. In this formulation, the time-dependent density of the diffusion is derived as the limit of implicit Euler steps that follow the gradients of a particular free energy functional. Existing methods for computing Wasserstein gradient flows rely on discretization of the domain of the diffusion, prohibiting their application to domains in more than several dimensions. We propose instead a discretization-free inference method that computes the Wasserstein gradient flow directly in a space of continuous functions. We characterize approximation properties of the proposed method and evaluate it on a nonlinear filtering task, finding performance comparable to the state-of-the-art for filtering diffusions.
Tasks
Published	2018-06-12
URL	http://arxiv.org/abs/1806.04542v1
PDF	http://arxiv.org/pdf/1806.04542v1.pdf
PWC	https://paperswithcode.com/paper/approximate-inference-with-wasserstein
Repo
Framework