October 18, 2019

3152 words 15 mins read

Paper Group ANR 540

Construction of neural networks for realization of localized deep learning. Equivalent Constraints for Two-View Geometry: Pose Solution/Pure Rotation Identification and 3D Reconstruction. Unbalanced Multi-Phase Distribution Grid Topology Estimation and Bus Phase Identification. Weighted Global Normalization for Multiple Choice ReadingComprehension …

Construction of neural networks for realization of localized deep learning


Title	Construction of neural networks for realization of localized deep learning
Authors	Charles K. Chui, Shao-Bo Lin, Ding-Xuan Zhou
Abstract	The subject of deep learning has recently attracted users of machine learning from various disciplines, including: medical diagnosis and bioinformatics, financial market analysis and online advertisement, speech and handwriting recognition, computer vision and natural language processing, time series forecasting, and search engines. However, theoretical development of deep learning is still at its infancy. The objective of this paper is to introduce a deep neural network (also called deep-net) approach to localized manifold learning, with each hidden layer endowed with a specific learning task. For the purpose of illustrations, we only focus on deep-nets with three hidden layers, with the first layer for dimensionality reduction, the second layer for bias reduction, and the third layer for variance reduction. A feedback component also designed to eliminate outliers. The main theoretical result in this paper is the order $\mathcal O\left(m^{-2s/(2s+d)}\right)$ of approximation of the regression function with regularity $s$, in terms of the number $m$ of sample points, where the (unknown) manifold dimension $d$ replaces the dimension $D$ of the sampling (Euclidean) space for shallow nets.
Tasks	Dimensionality Reduction, Medical Diagnosis, Time Series, Time Series Forecasting
Published	2018-03-09
URL	http://arxiv.org/abs/1803.03503v1
PDF	http://arxiv.org/pdf/1803.03503v1.pdf
PWC	https://paperswithcode.com/paper/construction-of-neural-networks-for
Repo
Framework

Equivalent Constraints for Two-View Geometry: Pose Solution/Pure Rotation Identification and 3D Reconstruction


Title	Equivalent Constraints for Two-View Geometry: Pose Solution/Pure Rotation Identification and 3D Reconstruction
Authors	Qi Cai, Yuanxin Wu, Lilian Zhang, Peike Zhang
Abstract	Two-view relative pose estimation and structure reconstruction is a classical problem in computer vision. The typical methods usually employ the singular value decomposition of the essential matrix to get multiple solutions of the relative pose, from which the right solution is picked out by reconstructing the three-dimension (3D) feature points and imposing the constraint of positive depth. This paper revisits the two-view geometry problem and discovers that the two-view imaging geometry is equivalently governed by a Pair of new Pose-Only (PPO) constraints: the same-side constraint and the intersection constraint. From the perspective of solving equation, the complete pose solutions of the essential matrix are explicitly derived and we rigorously prove that the orientation part of the pose can still be recovered in the case of pure rotation. The PPO constraints are simplified and formulated in the form of inequalities to directly identify the right pose solution with no need of 3D reconstruction and the 3D reconstruction can be analytically achieved from the identified right pose. Furthermore, the intersection inequality also enables a robust criterion for pure rotation identification. Experiment results validate the correctness of analyses and the robustness of the derived pose solution/pure rotation identification and analytical 3D reconstruction.
Tasks	3D Reconstruction, Pose Estimation
Published	2018-10-13
URL	http://arxiv.org/abs/1810.05863v1
PDF	http://arxiv.org/pdf/1810.05863v1.pdf
PWC	https://paperswithcode.com/paper/equivalent-constraints-for-two-view-geometry
Repo
Framework

Unbalanced Multi-Phase Distribution Grid Topology Estimation and Bus Phase Identification


Title	Unbalanced Multi-Phase Distribution Grid Topology Estimation and Bus Phase Identification
Authors	Yizheng Liao, Yang Weng, Guangyi Liu, Zhongyang Zhao, Chin-woo Tan, Ram Rajagopal
Abstract	There is an increasing need for monitoring and controlling uncertainties brought by distributed energy resources in distribution grids. For such goal, accurate multi-phase topology is the basis for correlating measurements in unbalanced distribution networks. Unfortunately, such topology knowledge is often unavailable due to limited investment, especially for \revv{low-voltage} distribution grids. Also, the bus phase labeling information is inaccurate due to human errors or outdated records. For this challenge, this paper utilizes smart meter data for an information-theoretic approach to learn the topology of distribution grids. Specifically, multi-phase unbalanced systems are converted into symmetrical components, namely positive, negative, and zero sequences. Then, this paper proves that the Chow-Liu algorithm finds the topology by utilizing power flow equations and the conditional independence relationships implied by the radial multi-phase structure of distribution grids with the presence of incorrect bus phase labels. At last, by utilizing Carson’s equation, this paper proves that the bus phase connection can be correctly identified using voltage measurements. For validation, IEEE systems are simulated using three real data sets. The simulation results demonstrate that the algorithm is highly accurate for finding multi-phase topology even with strong load unbalancing condition and DERs. This ensures close monitoring and controlling DERs in distribution grids.
Tasks
Published	2018-09-18
URL	https://arxiv.org/abs/1809.07192v3
PDF	https://arxiv.org/pdf/1809.07192v3.pdf
PWC	https://paperswithcode.com/paper/unbalanced-three-phase-distribution-grid
Repo
Framework

Weighted Global Normalization for Multiple Choice ReadingComprehension over Long Documents


Title	Weighted Global Normalization for Multiple Choice ReadingComprehension over Long Documents
Authors	Aditi Chaudhary, Bhargavi Paranjape, Michiel de Jong
Abstract	Motivated by recent evidence pointing out the fragility of high-performing span prediction models, we direct our attention to multiple choice reading comprehension. In particular, this work introduces a novel method for improving answer selection on long documents through weighted global normalization of predictions over portions of the documents. We show that applying our method to a span prediction model adapted for answer selection helps model performance on long summaries from NarrativeQA, a challenging reading comprehension dataset with an answer selection task, and we strongly improve on the task baseline performance by +36.2 Mean Reciprocal Rank.
Tasks	Answer Selection, Reading Comprehension
Published	2018-12-05
URL	http://arxiv.org/abs/1812.02253v1
PDF	http://arxiv.org/pdf/1812.02253v1.pdf
PWC	https://paperswithcode.com/paper/weighted-global-normalization-for-multiple
Repo
Framework

Testing SensoGraph, a geometric approach for fast sensory evaluation


Title	Testing SensoGraph, a geometric approach for fast sensory evaluation
Authors	David Orden, Encarnación Fernández-Fernández, José M. Rodríguez-Nogales, Josefina Vila-Crespo
Abstract	This paper introduces SensoGraph, a novel approach for fast sensory evaluation using two-dimensional geometric techniques. In the tasting sessions, the assessors follow their own criteria to place samples on a tablecloth, according to the similarity between samples. In order to analyse the data collected, first a geometric clustering is performed to each tablecloth, extracting connections between the samples. Then, these connections are used to construct a global similarity matrix. Finally, a graph drawing algorithm is used to obtain a 2D consensus graphic, which reflects the global opinion of the panel by (1) positioning closer those samples that have been globally perceived as similar and (2) showing the strength of the connections between samples. The proposal is validated by performing four tasting sessions, with three types of panels tasting different wines, and by developing a new software to implement the proposed techniques. The results obtained show that the graphics provide similar positionings of the samples as the consensus maps obtained by multiple factor analysis (MFA), further providing extra information about connections between samples, not present in any previous method. The main conclusion is that the use of geometric techniques provides information complementary to MFA, and of a different type. Finally, the method proposed is computationally able to manage a significantly larger number of assessors than MFA, which can be useful for the comparison of pictures by a huge number of consumers, via the Internet.
Tasks
Published	2018-09-16
URL	http://arxiv.org/abs/1809.06911v1
PDF	http://arxiv.org/pdf/1809.06911v1.pdf
PWC	https://paperswithcode.com/paper/testing-sensograph-a-geometric-approach-for
Repo
Framework

Cakewalk Sampling


Title	Cakewalk Sampling
Authors	Uri Patish, Shimon Ullman
Abstract	We study the task of finding good local optima in combinatorial optimization problems. Although combinatorial optimization is NP-hard in general, locally optimal solutions are frequently used in practice. Local search methods however typically converge to a limited set of optima that depend on their initialization. Sampling methods on the other hand can access any valid solution, and thus can be used either directly or alongside methods of the former type as a way for finding good local optima. Since the effectiveness of this strategy depends on the sampling distribution, we derive a robust learning algorithm that adapts sampling distributions towards good local optima of arbitrary objective functions. As a first use case, we empirically study the efficiency in which sampling methods can recover locally maximal cliques in undirected graphs. Not only do we show how our adaptive sampler outperforms related methods, we also show how it can even approach the performance of established clique algorithms. As a second use case, we consider how greedy algorithms can be combined with our adaptive sampler, and we demonstrate how this leads to superior performance in k-medoid clustering. Together, these findings suggest that our adaptive sampler can provide an effective strategy to combinatorial optimization problems that arise in practice.
Tasks	Combinatorial Optimization
Published	2018-02-25
URL	https://arxiv.org/abs/1802.09030v2
PDF	https://arxiv.org/pdf/1802.09030v2.pdf
PWC	https://paperswithcode.com/paper/cakewalk-sampling
Repo
Framework

A Swift Heuristic Method for Work Order Scheduling under the Skilled-Workforce Constraint


Title	A Swift Heuristic Method for Work Order Scheduling under the Skilled-Workforce Constraint
Authors	Nima Safaei, Corey Kiassat
Abstract	The considered problem is how to optimally allocate a set of jobs to technicians of different skills such that the number of technicians of each skill does not exceed the number of persons with that skill designation. The key motivation is the quick sensitivity analysis in terms of the workforce size which is quite necessary in many industries in the presence of unexpected work orders. A time-indexed mathematical model is proposed to minimize the total weighted completion time of the jobs. The proposed model is decomposed into a number of single-skill sub-problems so that each one is a combination of a series of nested binary Knapsack problems. A heuristic procedure is proposed to solve the problem. Our experimental results, based on a real-world case study, reveal that the proposed method quickly produces a schedule statistically close to the optimal one while the classical optimal procedure is very time-consuming.
Tasks
Published	2018-03-03
URL	http://arxiv.org/abs/1803.01252v1
PDF	http://arxiv.org/pdf/1803.01252v1.pdf
PWC	https://paperswithcode.com/paper/a-swift-heuristic-method-for-work-order
Repo
Framework

Limitations of Source-Filter Coupling In Phonation


Title	Limitations of Source-Filter Coupling In Phonation
Authors	Debasish Ray Mohapatra, Sidney Fels
Abstract	The coupling of vocal fold (source) and vocal tract (filter) is one of the most critical factors in source-filter articulation theory. The traditional linear source-filter theory has been challenged by current research which clearly shows the impact of acoustic loading on the dynamic behavior of the vocal fold vibration as well as the variations in the glottal flow pulses shape. This paper outlines the underlying mechanism of source-filter interactions; demonstrates the design and working principles of coupling for the various existing vocal cord and vocal tract biomechanical models. For our study, we have considered self-oscillating lumped-element models of the acoustic source and computational models of the vocal tract as articulators. To understand the limitations of source-filter interactions which are associated with each of those models, we compare them concerning their mechanical design, acoustic and physiological characteristics and aerodynamic simulation.
Tasks
Published	2018-11-19
URL	http://arxiv.org/abs/1811.07435v1
PDF	http://arxiv.org/pdf/1811.07435v1.pdf
PWC	https://paperswithcode.com/paper/limitations-of-source-filter-coupling-in
Repo
Framework

A Model Parallel Proximal Stochastic Gradient Algorithm for Partially Asynchronous Systems


Title	A Model Parallel Proximal Stochastic Gradient Algorithm for Partially Asynchronous Systems
Authors	Rui Zhu, Di Niu
Abstract	Large models are prevalent in modern machine learning scenarios, including deep learning, recommender systems, etc., which can have millions or even billions of parameters. Parallel algorithms have become an essential solution technique to many large-scale machine learning jobs. In this paper, we propose a model parallel proximal stochastic gradient algorithm, AsyB-ProxSGD, to deal with large models using model parallel blockwise updates while in the meantime handling a large amount of training data using proximal stochastic gradient descent (ProxSGD). In our algorithm, worker nodes communicate with the parameter servers asynchronously, and each worker performs proximal stochastic gradient for only one block of model parameters during each iteration. Our proposed algorithm generalizes ProxSGD to the asynchronous and model parallel setting. We prove that AsyB-ProxSGD achieves a convergence rate of $O(1/\sqrt{K})$ to stationary points for nonconvex problems under \emph{constant} minibatch sizes, where $K$ is the total number of block updates. This rate matches the best-known rates of convergence for a wide range of gradient-like algorithms. Furthermore, we show that when the number of workers is bounded by $O(K^{1/4})$, we can expect AsyB-ProxSGD to achieve linear speedup as the number of workers increases. We implement the proposed algorithm on MXNet and demonstrate its convergence behavior and near-linear speedup on a real-world dataset involving both a large model size and large amounts of data.
Tasks	Recommendation Systems
Published	2018-10-19
URL	http://arxiv.org/abs/1810.09270v1
PDF	http://arxiv.org/pdf/1810.09270v1.pdf
PWC	https://paperswithcode.com/paper/a-model-parallel-proximal-stochastic-gradient
Repo
Framework

A novel health risk model based on intraday physical activity time series collected by smartphones


Title	A novel health risk model based on intraday physical activity time series collected by smartphones
Authors	Evgeny Getmantsev, Boris Zhurov, Timothy V. Pyrkov, Peter O. Fedichev
Abstract	We compiled a demo application and collected a motion database of more than 10,000 smartphone users to produce a health risk model trained on physical activity streams. We turned to adversarial domain adaptation and employed the UK Biobank dataset of motion data, augmented by a rich set of clinical information as the source domain to train the model using a deep residual convolutional neuron network (ResNet). The model risk score is a biomarker of ageing, since it was predictive of lifespan and healthspan (as defined by the onset of specified diseases), and was elevated in groups associated with life-shortening lifestyles, such as smoking. We ascertained the target domain performance in a smaller cohort of the mobile application that included users who were willing to share answers to a short questionnaire related to their disease and smoking status. We thus conclude that the proposed pipeline combining deep convolutional and Domain Adversarial neuron networks (DANN) is a powerful tool for disease risk and lifestyle-associated hazard assessment from mobile motion sensors that are transferable across devices and populations.
Tasks	Domain Adaptation, Time Series
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02522v1
PDF	http://arxiv.org/pdf/1812.02522v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-health-risk-model-based-on-intraday
Repo
Framework

A Tamper-Free Semi-Universal Communication System for Deletion Channels


Title	A Tamper-Free Semi-Universal Communication System for Deletion Channels
Authors	Shahab Asoodeh, Yi Huang, Ishanu Chattopadhyay
Abstract	We investigate the problem of reliable communication between two legitimate parties over deletion channels under an active eavesdropping (aka jamming) adversarial model. To this goal, we develop a theoretical framework based on probabilistic finite-state automata to define novel encoding and decoding schemes that ensure small error probability in both message decoding as well as tamper detecting. We then experimentally verify the reliability and tamper-detection property of our scheme.
Tasks
Published	2018-04-09
URL	http://arxiv.org/abs/1804.03707v1
PDF	http://arxiv.org/pdf/1804.03707v1.pdf
PWC	https://paperswithcode.com/paper/a-tamper-free-semi-universal-communication
Repo
Framework

Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery


Title	Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery
Authors	Il Yong Chun, Jeffrey A. Fessler
Abstract	In “extreme” computational imaging that collects extremely undersampled or noisy measurements, obtaining an accurate image within a reasonable computing time is challenging. Incorporating image mapping convolutional neural networks (CNN) into iterative image recovery has great potential to resolve this issue. This paper 1) incorporates image mapping CNN using identical convolutional kernels in both encoders and decoders into a block coordinate descent (BCD) signal recovery method and 2) applies alternating direction method of multipliers to train the aforementioned image mapping CNN. We refer to the proposed recurrent network as BCD-Net using identical encoding-decoding CNN structures. Numerical experiments show that, for a) denoising low signal-to-noise-ratio images and b) extremely undersampled magnetic resonance imaging, the proposed BCD-Net achieves significantly more accurate image recovery, compared to BCD-Net using distinct encoding-decoding structures and/or the conventional image recovery model using both wavelets and total variation.
Tasks	Denoising
Published	2018-02-20
URL	http://arxiv.org/abs/1802.07129v2
PDF	http://arxiv.org/pdf/1802.07129v2.pdf
PWC	https://paperswithcode.com/paper/deep-bcd-net-using-identical-encoding
Repo
Framework

DASNet: Reducing Pixel-level Annotations for Instance and Semantic Segmentation


Title	DASNet: Reducing Pixel-level Annotations for Instance and Semantic Segmentation
Authors	Chuang Niu, Shenghan Ren, Jimin Liang
Abstract	Pixel-level annotation demands expensive human efforts and limits the performance of deep networks that usually benefits from more such training data. In this work we aim to achieve high quality instance and semantic segmentation results over a small set of pixel-level mask annotations and a large set of box annotations. The basic idea is exploring detection models to simplify the pixel-level supervised learning task and thus reduce the required amount of mask annotations. Our architecture, named DASNet, consists of three modules: detection, attention, and segmentation. The detection module detects all classes of objects, the attention module generates multi-scale class-specific features, and the segmentation module recovers the binary masks. Our method demonstrates substantially improved performance compared to existing semi-supervised approaches on PASCAL VOC 2012 dataset.
Tasks	Semantic Segmentation
Published	2018-09-17
URL	https://arxiv.org/abs/1809.06013v2
PDF	https://arxiv.org/pdf/1809.06013v2.pdf
PWC	https://paperswithcode.com/paper/dasnet-reducing-pixel-level-annotations-for
Repo
Framework

Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking


Title	Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking
Authors	Han Shen, Lichao Huang, Chang Huang, Wei Xu
Abstract	Traditional multiple object tracking methods divide the task into two parts: affinity learning and data association. The separation of the task requires to define a hand-crafted training goal in affinity learning stage and a hand-crafted cost function of data association stage, which prevents the tracking goals from learning directly from the feature. In this paper, we present a new multiple object tracking (MOT) framework with data-driven association method, named as Tracklet Association Tracker (TAT). The framework aims at gluing feature learning and data association into a unity by a bi-level optimization formulation so that the association results can be directly learned from features. To boost the performance, we also adopt the popular hierarchical association and perform the necessary alignment and selection of raw detection responses. Our model trains over 20X faster than a similar approach, and achieves the state-of-the-art performance on both MOT2016 and MOT2017 benchmarks.
Tasks	Multi-Object Tracking, Multiple Object Tracking, Object Tracking
Published	2018-08-05
URL	http://arxiv.org/abs/1808.01562v1
PDF	http://arxiv.org/pdf/1808.01562v1.pdf
PWC	https://paperswithcode.com/paper/tracklet-association-tracker-an-end-to-end
Repo
Framework

Adversarially-Trained Normalized Noisy-Feature Auto-Encoder for Text Generation


Title	Adversarially-Trained Normalized Noisy-Feature Auto-Encoder for Text Generation
Authors	Xiang Zhang, Yann LeCun
Abstract	This article proposes Adversarially-Trained Normalized Noisy-Feature Auto-Encoder (ATNNFAE) for byte-level text generation. An ATNNFAE consists of an auto-encoder where the internal code is normalized on the unit sphere and corrupted by additive noise. Simultaneously, a replica of the decoder (sharing the same parameters as the AE decoder) is used as the generator and fed with random latent vectors. An adversarial discriminator is trained to distinguish training samples reconstructed from the AE from samples produced through the random-input generator, making the entire generator-discriminator path differentiable for discrete data like text. The combined effect of noise injection in the code and shared weights between the decoder and the generator can prevent the mode collapsing phenomenon commonly observed in GANs. Since perplexity cannot be applied to non-sequential text generation, we propose a new evaluation method using the total variance distance between frequencies of hash-coded byte-level n-grams (NGTVD). NGTVD is a single benchmark that can characterize both the quality and the diversity of the generated texts. Experiments are offered in 6 large-scale datasets in Arabic, Chinese and English, with comparisons against n-gram baselines and recurrent neural networks (RNNs). Ablation study on both the noise level and the discriminator is performed. We find that RNNs have trouble competing with the n-gram baselines, and the ATNNFAE results are generally competitive.
Tasks	Text Generation
Published	2018-11-10
URL	http://arxiv.org/abs/1811.04201v1
PDF	http://arxiv.org/pdf/1811.04201v1.pdf
PWC	https://paperswithcode.com/paper/adversarially-trained-normalized-noisy
Repo
Framework