July 26, 2019

3020 words 15 mins read

Paper Group ANR 755

Bayesian System Identification based on Hierarchical Sparse Bayesian Learning and Gibbs Sampling with Application to Structural Damage Assessment. Representation Learning for Scale-free Networks. OBJ2TEXT: Generating Visually Descriptive Language from Object Layouts. Foreign-language Reviews: Help or Hindrance?. Modeling Musical Context with Word2v …

Bayesian System Identification based on Hierarchical Sparse Bayesian Learning and Gibbs Sampling with Application to Structural Damage Assessment


Title	Bayesian System Identification based on Hierarchical Sparse Bayesian Learning and Gibbs Sampling with Application to Structural Damage Assessment
Authors	Yong Huang, James L. Beck, Hui Li
Abstract	The focus in this paper is Bayesian system identification based on noisy incomplete modal data where we can impose spatially-sparse stiffness changes when updating a structural model. To this end, based on a similar hierarchical sparse Bayesian learning model from our previous work, we propose two Gibbs sampling algorithms. The algorithms differ in their strategies to deal with the posterior uncertainty of the equation-error precision parameter, but both sample from the conditional posterior probability density functions (PDFs) for the structural stiffness parameters and system modal parameters. The effective dimension for the Gibbs sampling is low because iterative sampling is done from only three conditional posterior PDFs that correspond to three parameter groups, along with sampling of the equation-error precision parameter from another conditional posterior PDF in one of the algorithms where it is not integrated out as a “nuisance” parameter. A nice feature from a computational perspective is that it is not necessary to solve a nonlinear eigenvalue problem of a structural model. The effectiveness and robustness of the proposed algorithms are illustrated by applying them to the IASE-ASCE Phase II simulated and experimental benchmark studies. The goal is to use incomplete modal data identified before and after possible damage to detect and assess spatially-sparse stiffness reductions induced by any damage. Our past and current focus on meeting challenges arising from Bayesian inference of structural stiffness serve to strengthen the capability of vibration-based structural system identification but our methods also have much broader applicability for inverse problems in science and technology where system matrices are to be inferred from noisy partial information about their eigenquantities.
Tasks	Bayesian Inference
Published	2017-01-13
URL	http://arxiv.org/abs/1701.03550v1
PDF	http://arxiv.org/pdf/1701.03550v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-system-identification-based-on
Repo
Framework

Representation Learning for Scale-free Networks


Title	Representation Learning for Scale-free Networks
Authors	Rui Feng, Yang Yang, Wenjie Hu, Fei Wu, Yueting Zhuang
Abstract	Network embedding aims to learn the low-dimensional representations of vertexes in a network, while structure and inherent properties of the network is preserved. Existing network embedding works primarily focus on preserving the microscopic structure, such as the first- and second-order proximity of vertexes, while the macroscopic scale-free property is largely ignored. Scale-free property depicts the fact that vertex degrees follow a heavy-tailed distribution (i.e., only a few vertexes have high degrees) and is a critical property of real-world networks, such as social networks. In this paper, we study the problem of learning representations for scale-free networks. We first theoretically analyze the difficulty of embedding and reconstructing a scale-free network in the Euclidean space, by converting our problem to the sphere packing problem. Then, we propose the “degree penalty” principle for designing scale-free property preserving network embedding algorithm: punishing the proximity between high-degree vertexes. We introduce two implementations of our principle by utilizing the spectral techniques and a skip-gram model respectively. Extensive experiments on six datasets show that our algorithms are able to not only reconstruct heavy-tailed distributed degree distribution, but also outperform state-of-the-art embedding models in various network mining tasks, such as vertex classification and link prediction.
Tasks	Link Prediction, Network Embedding, Representation Learning
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10755v1
PDF	http://arxiv.org/pdf/1711.10755v1.pdf
PWC	https://paperswithcode.com/paper/representation-learning-for-scale-free
Repo
Framework

OBJ2TEXT: Generating Visually Descriptive Language from Object Layouts


Title	OBJ2TEXT: Generating Visually Descriptive Language from Object Layouts
Authors	Xuwang Yin, Vicente Ordonez
Abstract	Generating captions for images is a task that has recently received considerable attention. In this work we focus on caption generation for abstract scenes, or object layouts where the only information provided is a set of objects and their locations. We propose OBJ2TEXT, a sequence-to-sequence model that encodes a set of objects and their locations as an input sequence using an LSTM network, and decodes this representation using an LSTM language model. We show that our model, despite encoding object layouts as a sequence, can represent spatial relationships between objects, and generate descriptions that are globally coherent and semantically relevant. We test our approach in a task of object-layout captioning by using only object annotations as inputs. We additionally show that our model, combined with a state-of-the-art object detector, improves an image captioning model from 0.863 to 0.950 (CIDEr score) in the test benchmark of the standard MS-COCO Captioning task.
Tasks	Image Captioning, Language Modelling
Published	2017-07-22
URL	http://arxiv.org/abs/1707.07102v1
PDF	http://arxiv.org/pdf/1707.07102v1.pdf
PWC	https://paperswithcode.com/paper/obj2text-generating-visually-descriptive
Repo
Framework

Foreign-language Reviews: Help or Hindrance?


Title	Foreign-language Reviews: Help or Hindrance?
Authors	Scott A. Hale, Irene Eleta
Abstract	The number and quality of user reviews greatly affects consumer purchasing decisions. While reviews in all languages are increasing, it is still often the case (especially for non-English speakers) that there are only a few reviews in a person’s first language. Using an online experiment, we examine the value that potential purchasers receive from interfaces showing additional reviews in a second language. The results paint a complicated picture with both positive and negative reactions to the inclusion of foreign-language reviews. Roughly 26-28% of subjects clicked to see translations of the foreign-language content when given the opportunity, and those who did so were more likely to select the product with foreign-language reviews than those who did not.
Tasks
Published	2017-02-01
URL	http://arxiv.org/abs/1702.00210v1
PDF	http://arxiv.org/pdf/1702.00210v1.pdf
PWC	https://paperswithcode.com/paper/foreign-language-reviews-help-or-hindrance
Repo
Framework

Modeling Musical Context with Word2vec


Title	Modeling Musical Context with Word2vec
Authors	Dorien Herremans, Ching-Hua Chuan
Abstract	We present a semantic vector space model for capturing complex polyphonic musical context. A word2vec model based on a skip-gram representation with negative sampling was used to model slices of music from a dataset of Beethoven’s piano sonatas. A visualization of the reduced vector space using t-distributed stochastic neighbor embedding shows that the resulting embedded vector space captures tonal relationships, even without any explicit information about the musical contents of the slices. Secondly, an excerpt of the Moonlight Sonata from Beethoven was altered by replacing slices based on context similarity. The resulting music shows that the selected slice based on similar word2vec context also has a relatively short tonal distance from the original slice.
Tasks
Published	2017-06-28
URL	http://arxiv.org/abs/1706.09088v2
PDF	http://arxiv.org/pdf/1706.09088v2.pdf
PWC	https://paperswithcode.com/paper/modeling-musical-context-with-word2vec
Repo
Framework

Direct Mapping Hidden Excited State Interaction Patterns from ab initio Dynamics and Its Implications on Force Field Development


Title	Direct Mapping Hidden Excited State Interaction Patterns from ab initio Dynamics and Its Implications on Force Field Development
Authors	Fang Liu, Likai Du, Dongju Zhang, Jun Gao
Abstract	The excited states of polyatomic systems are rather complex, and often exhibit meta-stable dynamical behaviors. Static analysis of reaction pathway often fails to sufficiently characterize excited state motions due to their highly non-equilibrium nature. Here, we proposed a time series guided clustering algorithm to generate most relevant meta-stable patterns directly from ab initio dynamic trajectories. Based on the knowledge of these meta-stable patterns, we suggested an interpolation scheme with only a concrete and finite set of known patterns to accurately predict the ground and excited state properties of the entire dynamics trajectories. As illustrated with the example of sinapic acids, the estimation error for both ground and excited state is very close, which indicates one could predict the ground and excited state molecular properties with similar accuracy. These results may provide us some insights to construct an excited state force field with compatible energy terms as traditional ones.
Tasks	Time Series
Published	2017-05-28
URL	http://arxiv.org/abs/1705.09919v1
PDF	http://arxiv.org/pdf/1705.09919v1.pdf
PWC	https://paperswithcode.com/paper/direct-mapping-hidden-excited-state
Repo
Framework

Joint Calibration of Panoramic Camera and Lidar Based on Supervised Learning


Title	Joint Calibration of Panoramic Camera and Lidar Based on Supervised Learning
Authors	Mingwei Cao, Ming Yang, Chunxiang Wang, Yeqiang Qian, Bing Wang
Abstract	In view of contemporary panoramic camera-laser scanner system, the traditional calibration method is not suitable for panoramic cameras whose imaging model is extremely nonlinear. The method based on statistical optimization has the disadvantage that the requirement of the number of laser scanner’s channels is relatively high. Calibration equipments with extreme accuracy for panoramic camera-laser scanner system are costly. Facing all these in the calibration of panoramic camera-laser scanner system, a method based on supervised learning is proposed. Firstly, corresponding feature points of panoramic images and point clouds are gained to generate the training dataset by designing a round calibration object. Furthermore, the traditional calibration problem is transformed into a multiple nonlinear regression optimization problem by designing a supervised learning network with preprocessing of the panoramic imaging model. Back propagation algorithm is utilized to regress the rotation and translation matrix with high accuracy. Experimental results show that this method can quickly regress the calibration parameters and the accuracy is better than the traditional calibration method and the method based on statistical optimization. The calibration accuracy of this method is really high, and it is more highly-automated.
Tasks	Calibration
Published	2017-09-09
URL	http://arxiv.org/abs/1709.02926v2
PDF	http://arxiv.org/pdf/1709.02926v2.pdf
PWC	https://paperswithcode.com/paper/joint-calibration-of-panoramic-camera-and
Repo
Framework

Faster Spatially Regularized Correlation Filters for Visual Tracking


Title	Faster Spatially Regularized Correlation Filters for Visual Tracking
Authors	Xiaoxiang Hu, Yujiu Yang
Abstract	Discriminatively learned correlation filters (DCF) have been widely used in online visual tracking filed due to its simplicity and efficiency. These methods utilize a periodic assumption of the training samples to construct a circulant data matrix, which implicitly increases the training samples and reduces both storage and computational complexity.The periodic assumption also introduces unwanted boundary effects. Recently, Spatially Regularized Correlation Filters (SRDCF) solved this issue by introducing penalization on correlation filter coefficients depending on their spatial location. However, SRDCF’s efficiency dramatically decreased due to the breaking of circulant structure. We propose Faster Spatially Regularized Discriminative Correlation Filters (FSRDCF) for tracking. The FSRDCF is constructed from Ridge Regression, the circulant structure of training samples in the spatial domain is fully used, more importantly, we further exploit the circulant structure of regularization function in the Fourier domain, which allows our problem to be solved more directly and efficiently. Experiments are conducted on three benchmark datasets: OTB-2013, OTB-2015 and VOT2016. Our approach achieves equivalent performance to the baseline tracker SRDCF on all three datasets. On OTB-2013 and OTB-2015 datasets, our approach obtains a more than twice faster running speed and a more than third times shorter start-up time than the SRDCF. For state-of-the-art comparison, our approach demonstrates superior performance compared to other non-spatial-regularization trackers.
Tasks	Visual Tracking
Published	2017-06-01
URL	http://arxiv.org/abs/1706.00140v1
PDF	http://arxiv.org/pdf/1706.00140v1.pdf
PWC	https://paperswithcode.com/paper/faster-spatially-regularized-correlation
Repo
Framework

Deep Self-taught Learning for Remote Sensing Image Classification


Title	Deep Self-taught Learning for Remote Sensing Image Classification
Authors	Anika Bettge, Ribana Roscher, Susanne Wenzel
Abstract	This paper addresses the land cover classification task for remote sensing images by deep self-taught learning. Our self-taught learning approach learns suitable feature representations of the input data using sparse representation and undercomplete dictionary learning. We propose a deep learning framework which extracts representations in multiple layers and use the output of the deepest layer as input to a classification algorithm. We evaluate our approach using a multispectral Landsat 5 TM image of a study area in the North of Novo Progresso (South America) and the Zurich Summer Data Set provided by the University of Zurich. Experiments indicate that features learned by a deep self-taught learning framework can be used for classification and improve the results compared to classification results using the original feature representation.
Tasks	Dictionary Learning, Image Classification, Remote Sensing Image Classification
Published	2017-10-19
URL	http://arxiv.org/abs/1710.07096v2
PDF	http://arxiv.org/pdf/1710.07096v2.pdf
PWC	https://paperswithcode.com/paper/deep-self-taught-learning-for-remote-sensing
Repo
Framework

Learning the PE Header, Malware Detection with Minimal Domain Knowledge


Title	Learning the PE Header, Malware Detection with Minimal Domain Knowledge
Authors	Edward Raff, Jared Sylvester, Charles Nicholas
Abstract	Many efforts have been made to use various forms of domain knowledge in malware detection. Currently there exist two common approaches to malware detection without domain knowledge, namely byte n-grams and strings. In this work we explore the feasibility of applying neural networks to malware detection and feature learning. We do this by restricting ourselves to a minimal amount of domain knowledge in order to extract a portion of the Portable Executable (PE) header. By doing this we show that neural networks can learn from raw bytes without explicit feature construction, and perform even better than a domain knowledge approach that parses the PE header into explicit features.
Tasks	Malware Detection
Published	2017-09-05
URL	http://arxiv.org/abs/1709.01471v2
PDF	http://arxiv.org/pdf/1709.01471v2.pdf
PWC	https://paperswithcode.com/paper/learning-the-pe-header-malware-detection-with
Repo
Framework

Understanding Deep Learning Generalization by Maximum Entropy


Title	Understanding Deep Learning Generalization by Maximum Entropy
Authors	Guanhua Zheng, Jitao Sang, Changsheng Xu
Abstract	Deep learning achieves remarkable generalization capability with overwhelming number of model parameters. Theoretical understanding of deep learning generalization receives recent attention yet remains not fully explored. This paper attempts to provide an alternative understanding from the perspective of maximum entropy. We first derive two feature conditions that softmax regression strictly apply maximum entropy principle. DNN is then regarded as approximating the feature conditions with multilayer feature learning, and proved to be a recursive solution towards maximum entropy principle. The connection between DNN and maximum entropy well explains why typical designs such as shortcut and regularization improves model generalization, and provides instructions for future model development.
Tasks
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07758v1
PDF	http://arxiv.org/pdf/1711.07758v1.pdf
PWC	https://paperswithcode.com/paper/understanding-deep-learning-generalization-by
Repo
Framework

Temporal Overdrive Recurrent Neural Network


Title	Temporal Overdrive Recurrent Neural Network
Authors	Filippo Maria Bianchi, Michael Kampffmeyer, Enrico Maiorino, Robert Jenssen
Abstract	In this work we present a novel recurrent neural network architecture designed to model systems characterized by multiple characteristic timescales in their dynamics. The proposed network is composed by several recurrent groups of neurons that are trained to separately adapt to each timescale, in order to improve the system identification process. We test our framework on time series prediction tasks and we show some promising, preliminary results achieved on synthetic data. To evaluate the capabilities of our network, we compare the performance with several state-of-the-art recurrent architectures.
Tasks	Time Series, Time Series Prediction
Published	2017-01-18
URL	http://arxiv.org/abs/1701.05159v1
PDF	http://arxiv.org/pdf/1701.05159v1.pdf
PWC	https://paperswithcode.com/paper/temporal-overdrive-recurrent-neural-network
Repo
Framework

Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking


Title	Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
Authors	Aleksandar Bojchevski, Stephan Günnemann
Abstract	Methods that learn representations of nodes in a graph play a critical role in network analysis since they enable many downstream learning tasks. We propose Graph2Gauss - an approach that can efficiently learn versatile node embeddings on large scale (attributed) graphs that show strong performance on tasks such as link prediction and node classification. Unlike most approaches that represent nodes as point vectors in a low-dimensional continuous space, we embed each node as a Gaussian distribution, allowing us to capture uncertainty about the representation. Furthermore, we propose an unsupervised method that handles inductive learning scenarios and is applicable to different types of graphs: plain/attributed, directed/undirected. By leveraging both the network structure and the associated node attributes, we are able to generalize to unseen nodes without additional training. To learn the embeddings we adopt a personalized ranking formulation w.r.t. the node distances that exploits the natural ordering of the nodes imposed by the network structure. Experiments on real world networks demonstrate the high performance of our approach, outperforming state-of-the-art network embedding methods on several different tasks. Additionally, we demonstrate the benefits of modeling uncertainty - by analyzing it we can estimate neighborhood diversity and detect the intrinsic latent dimensionality of a graph.
Tasks	Link Prediction, Network Embedding, Node Classification
Published	2017-07-12
URL	http://arxiv.org/abs/1707.03815v4
PDF	http://arxiv.org/pdf/1707.03815v4.pdf
PWC	https://paperswithcode.com/paper/deep-gaussian-embedding-of-graphs
Repo
Framework

Adaptive Sampled Softmax with Kernel Based Sampling


Title	Adaptive Sampled Softmax with Kernel Based Sampling
Authors	Guy Blanc, Steffen Rendle
Abstract	Softmax is the most commonly used output function for multiclass problems and is widely used in areas such as vision, natural language processing, and recommendation. A softmax model has linear costs in the number of classes which makes it too expensive for many real-world problems. A common approach to speed up training involves sampling only some of the classes at each training step. It is known that this method is biased and that the bias increases the more the sampling distribution deviates from the output distribution. Nevertheless, almost any recent work uses simple sampling distributions that require a large sample size to mitigate the bias. In this work, we propose a new class of kernel based sampling methods and develop an efficient sampling algorithm. Kernel based sampling adapts to the model as it is trained, thus resulting in low bias. Kernel based sampling can be easily applied to many models because it relies only on the model’s last hidden layer. We empirically study the trade-off of bias, sampling distribution and sample size and show that kernel based sampling results in low bias with few samples.
Tasks
Published	2017-12-02
URL	http://arxiv.org/abs/1712.00527v2
PDF	http://arxiv.org/pdf/1712.00527v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-sampled-softmax-with-kernel-based
Repo
Framework

Unsupervised Induction of Contingent Event Pairs from Film Scenes


Title	Unsupervised Induction of Contingent Event Pairs from Film Scenes
Authors	Zhichao Hu, Elahe Rahimtoroghi, Larissa Munishkina, Reid Swanson, Marilyn A. Walker
Abstract	Human engagement in narrative is partially driven by reasoning about discourse relations between narrative events, and the expectations about what is likely to happen next that results from such reasoning. Researchers in NLP have tackled modeling such expectations from a range of perspectives, including treating it as the inference of the contingent discourse relation, or as a type of common-sense causal reasoning. Our approach is to model likelihood between events by drawing on several of these lines of previous work. We implement and evaluate different unsupervised methods for learning event pairs that are likely to be contingent on one another. We refine event pairs that we learn from a corpus of film scene descriptions utilizing web search counts, and evaluate our results by collecting human judgments of contingency. Our results indicate that the use of web search counts increases the average accuracy of our best method to 85.64% over a baseline of 50%, as compared to an average accuracy of 75.15% without web search.
Tasks	Common Sense Reasoning
Published	2017-08-30
URL	http://arxiv.org/abs/1708.09497v1
PDF	http://arxiv.org/pdf/1708.09497v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-induction-of-contingent-event
Repo
Framework