May 5, 2019

3016 words 15 mins read

Paper Group ANR 455

Generic and Efficient Solution Solves the Shortest Paths Problem in Square Runtime. Ontohub: A semantic repository for heterogeneous ontologies. Collective Decision Dynamics in Group Evacuation: Behavioral Experiment and Machine Learning Models. Fast, Dense Feature SDM on an iPhone. Database of handwritten Arabic mathematical formulas images. Combi …

Generic and Efficient Solution Solves the Shortest Paths Problem in Square Runtime


Title	Generic and Efficient Solution Solves the Shortest Paths Problem in Square Runtime
Authors	Yong Tan
Abstract	We study a group of new methods to solve an open problem that is the shortest paths problem on a given fix-weighted instance. It is the real significance at a considerable altitude to reach our aim to meet these qualities of generic, efficiency, precision which we generally require to a methodology. Besides our proof to guarantee our measures might work normally, we pay more interest to root out the vital theory about calculation and logic in favor of our extension to range over a wide field about decision, operator, economy, management, robot, AI and etc.
Tasks
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09666v1
PDF	http://arxiv.org/pdf/1611.09666v1.pdf
PWC	https://paperswithcode.com/paper/generic-and-efficient-solution-solves-the
Repo
Framework

Ontohub: A semantic repository for heterogeneous ontologies


Title	Ontohub: A semantic repository for heterogeneous ontologies
Authors	Mihai Codescu, Eugen Kuksa, Oliver Kutz, Till Mossakowski, Fabian Neuhaus
Abstract	Ontohub is a repository engine for managing distributed heterogeneous ontologies. The distributed nature enables communities to share and exchange their contributions easily. The heterogeneous nature makes it possible to integrate ontologies written in various ontology languages. Ontohub supports a wide range of formal logical and ontology languages, as well as various structuring and modularity constructs and inter-theory (concept) mappings, building on the OMG-standardized DOL language. Ontohub repositories are organised as Git repositories, thus inheriting all features of this popular version control system. Moreover, Ontohub is the first repository engine meeting a substantial amount of the requirements formulated in the context of the Open Ontology Repository (OOR) initiative, including an API for federation as well as support for logical inference and axiom selection.
Tasks
Published	2016-12-15
URL	http://arxiv.org/abs/1612.05028v1
PDF	http://arxiv.org/pdf/1612.05028v1.pdf
PWC	https://paperswithcode.com/paper/ontohub-a-semantic-repository-for
Repo
Framework

Collective Decision Dynamics in Group Evacuation: Behavioral Experiment and Machine Learning Models


Title	Collective Decision Dynamics in Group Evacuation: Behavioral Experiment and Machine Learning Models
Authors	Chantal Nguyen, Fangqiu Han, Kimberly J. Schlesinger, Izzeddin Gür, Jean M. Carlson
Abstract	Identifying factors that affect human decision making and quantifying their influence remain essential and challenging tasks for the design and implementation of social and technological communication systems. We report results of a behavioral experiment involving decision making in the face of an impending natural disaster. In a controlled laboratory setting, we characterize individual and group evacuation decision making influenced by several key factors, including the likelihood of the disaster, available shelter capacity, group size, and group decision protocol. Our results show that success in individual decision making is not a strong predictor of group performance. We use an artificial neural network trained on the collective behavior of subjects to predict individual and group outcomes. Overall model accuracy increases with the inclusion of a subject-specific performance parameter based on laboratory trials that captures individual differences. In parallel, we demonstrate that the social media activity of individual subjects, specifically their Facebook use, can be used to generate an alternative individual personality profile that leads to comparable model accuracy. Quantitative characterization and prediction of collective decision making is crucial for the development of effective policies to guide the action of populations in the face of threat or uncertainty.
Tasks	Decision Making
Published	2016-06-17
URL	http://arxiv.org/abs/1606.05647v3
PDF	http://arxiv.org/pdf/1606.05647v3.pdf
PWC	https://paperswithcode.com/paper/collective-decision-dynamics-in-group
Repo
Framework

Fast, Dense Feature SDM on an iPhone


Title	Fast, Dense Feature SDM on an iPhone
Authors	Ashton Fagg, Simon Lucey, Sridha Sridharan
Abstract	In this paper, we present our method for enabling dense SDM to run at over 90 FPS on a mobile device. Our contributions are two-fold. Drawing inspiration from the FFT, we propose a Sparse Compositional Regression (SCR) framework, which enables a significant speed up over classical dense regressors. Second, we propose a binary approximation to SIFT features. Binary Approximated SIFT (BASIFT) features, which are a computationally efficient approximation to SIFT, a commonly used feature with SDM. We demonstrate the performance of our algorithm on an iPhone 7, and show that we achieve similar accuracy to SDM.
Tasks
Published	2016-12-16
URL	http://arxiv.org/abs/1612.05332v1
PDF	http://arxiv.org/pdf/1612.05332v1.pdf
PWC	https://paperswithcode.com/paper/fast-dense-feature-sdm-on-an-iphone
Repo
Framework

Database of handwritten Arabic mathematical formulas images


Title	Database of handwritten Arabic mathematical formulas images
Authors	Ibtissem Hadj Ali, Mohammed Ali Mahjoub
Abstract	Although publicly available, ground-truthed database have proven useful for training, evaluating, and comparing recognition systems in many domains, the availability of such database for handwritten Arabic mathematical formula recognition in particular, is currently quite poor. In this paper, we present a new public database that contains mathematical expressions available in their off-line handwritten form. Here, we describe the different steps that allowed us to acquire this database, from the creation of the mathematical expression corpora to the transcription of the collected data. Currently, the dataset contains 4 238 off-line handwritten mathematical expressions written by 66 writers and 20 300 handwritten isolated symbol images. The ground truth is also provided for the handwritten expressions as XML files with the number of symbols, and the MATHML structure.
Tasks
Published	2016-08-08
URL	http://arxiv.org/abs/1608.02388v1
PDF	http://arxiv.org/pdf/1608.02388v1.pdf
PWC	https://paperswithcode.com/paper/database-of-handwritten-arabic-mathematical
Repo
Framework

Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning


Title	Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning
Authors	Wouter M. Koolen, Peter Grünwald, Tim van Erven
Abstract	We consider online learning algorithms that guarantee worst-case regret rates in adversarial environments (so they can be deployed safely and will perform robustly), yet adapt optimally to favorable stochastic environments (so they will perform well in a variety of settings of practical importance). We quantify the friendliness of stochastic environments by means of the well-known Bernstein (a.k.a. generalized Tsybakov margin) condition. For two recent algorithms (Squint for the Hedge setting and MetaGrad for online convex optimization) we show that the particular form of their data-dependent individual-sequence regret guarantees implies that they adapt automatically to the Bernstein parameters of the stochastic environment. We prove that these algorithms attain fast rates in their respective settings both in expectation and with high probability.
Tasks
Published	2016-05-20
URL	http://arxiv.org/abs/1605.06439v1
PDF	http://arxiv.org/pdf/1605.06439v1.pdf
PWC	https://paperswithcode.com/paper/combining-adversarial-guarantees-and
Repo
Framework

Analysis of Massive Heterogeneous Temporal-Spatial Data with 3D Self-Organizing Map and Time Vector


Title	Analysis of Massive Heterogeneous Temporal-Spatial Data with 3D Self-Organizing Map and Time Vector
Authors	Yu Ding
Abstract	Self-organizing map(SOM) have been widely applied in clustering, this paper focused on centroids of clusters and what they reveal. When the input vectors consists of time, latitude and longitude, the map can be strongly linked to physical world, providing valuable information. Beyond basic clustering, a novel approach to address the temporal element is developed, enabling 3D SOM to track behaviors in multiple periods concurrently. Combined with adaptations targeting to process heterogeneous data relating to distribution in time and space, the paper offers a fresh scope for business and services based on temporal-spatial pattern.
Tasks
Published	2016-09-27
URL	http://arxiv.org/abs/1609.09116v1
PDF	http://arxiv.org/pdf/1609.09116v1.pdf
PWC	https://paperswithcode.com/paper/analysis-of-massive-heterogeneous-temporal
Repo
Framework

An Evolutionary Algorithm to Learn SPARQL Queries for Source-Target-Pairs: Finding Patterns for Human Associations in DBpedia


Title	An Evolutionary Algorithm to Learn SPARQL Queries for Source-Target-Pairs: Finding Patterns for Human Associations in DBpedia
Authors	Jörn Hees, Rouven Bauer, Joachim Folz, Damian Borth, Andreas Dengel
Abstract	Efficient usage of the knowledge provided by the Linked Data community is often hindered by the need for domain experts to formulate the right SPARQL queries to answer questions. For new questions they have to decide which datasets are suitable and in which terminology and modelling style to phrase the SPARQL query. In this work we present an evolutionary algorithm to help with this challenging task. Given a training list of source-target node-pair examples our algorithm can learn patterns (SPARQL queries) from a SPARQL endpoint. The learned patterns can be visualised to form the basis for further investigation, or they can be used to predict target nodes for new source nodes. Amongst others, we apply our algorithm to a dataset of several hundred human associations (such as “circle - square”) to find patterns for them in DBpedia. We show the scalability of the algorithm by running it against a SPARQL endpoint loaded with > 7.9 billion triples. Further, we use the resulting SPARQL queries to mimic human associations with a Mean Average Precision (MAP) of 39.9 % and a Recall@10 of 63.9 %.
Tasks
Published	2016-07-25
URL	http://arxiv.org/abs/1607.07249v3
PDF	http://arxiv.org/pdf/1607.07249v3.pdf
PWC	https://paperswithcode.com/paper/an-evolutionary-algorithm-to-learn-sparql
Repo
Framework

Multiphase Segmentation For Simultaneously Homogeneous and Textural Images


Title	Multiphase Segmentation For Simultaneously Homogeneous and Textural Images
Authors	Duy Hoang Thai, Lucas Mentch
Abstract	Segmentation remains an important problem in image processing. For homogeneous (piecewise smooth) images, a number of important models have been developed and refined over the past several decades. However, these models often fail when applied to the substantially larger class of natural images that simultaneously contain regions of both texture and homogeneity. This work introduces a bi-level constrained minimization model for simultaneous multiphase segmentation of images containing both homogeneous and textural regions. We develop novel norms defined in different functional Banach spaces for the segmentation which results in a non-convex minimization. Finally, we develop a generalized notion of segmentation delving into approximation theory and demonstrating that a more refined decomposition of these images results in multiple meaningful components. Both theoretical results and demonstrations on natural images are provided.
Tasks
Published	2016-06-29
URL	http://arxiv.org/abs/1606.09281v1
PDF	http://arxiv.org/pdf/1606.09281v1.pdf
PWC	https://paperswithcode.com/paper/multiphase-segmentation-for-simultaneously
Repo
Framework

EvoGrader: an online formative assessment tool for automatically evaluating written evolutionary explanations


Title	EvoGrader: an online formative assessment tool for automatically evaluating written evolutionary explanations
Authors	Kayhan Moharreri, Minsu Ha, Ross H Nehm
Abstract	EvoGrader is a free, online, on-demand formative assessment service designed for use in undergraduate biology classrooms. EvoGrader’s web portal is powered by Amazon’s Elastic Cloud and run with LightSIDE Lab’s open-source machine-learning tools. The EvoGrader web portal allows biology instructors to upload a response file (.csv) containing unlimited numbers of evolutionary explanations written in response to 86 different ACORNS (Assessing COntextual Reasoning about Natural Selection) instrument items. The system automatically analyzes the responses and provides detailed information about the scientific and naive concepts contained within each student’s response, as well as overall student (and sample) reasoning model types. Graphs and visual models provided by EvoGrader summarize class-level responses; downloadable files of raw scores (in .csv format) are also provided for more detailed analyses. Although the computational machinery that EvoGrader employs is complex, using the system is easy. Users only need to know how to use spreadsheets to organize student responses, upload files to the web, and use a web browser. A series of experiments using new samples of 2,200 written evolutionary explanations demonstrate that EvoGrader scores are comparable to those of trained human raters, although EvoGrader scoring takes 99% less time and is free. EvoGrader will be of interest to biology instructors teaching large classes who seek to emphasize scientific practices such as generating scientific explanations, and to teach crosscutting ideas such as evolution and natural selection. The software architecture of EvoGrader is described as it may serve as a template for developing machine-learning portals for other core concepts within biology and across other disciplines.
Tasks
Published	2016-01-13
URL	http://arxiv.org/abs/1601.03348v1
PDF	http://arxiv.org/pdf/1601.03348v1.pdf
PWC	https://paperswithcode.com/paper/evograder-an-online-formative-assessment-tool
Repo
Framework

Online Categorical Subspace Learning for Sketching Big Data with Misses


Title	Online Categorical Subspace Learning for Sketching Big Data with Misses
Authors	Yanning Shen, Morteza Mardani, Georgios B. Giannakis
Abstract	With the scale of data growing every day, reducing the dimensionality (a.k.a. sketching) of high-dimensional data has emerged as a task of paramount importance. Relevant issues to address in this context include the sheer volume of data that may consist of categorical samples, the typically streaming format of acquisition, and the possibly missing entries. To cope with these challenges, the present paper develops a novel categorical subspace learning approach to unravel the latent structure for three prominent categorical (bilinear) models, namely, Probit, Tobit, and Logit. The deterministic Probit and Tobit models treat data as quantized values of an analog-valued process lying in a low-dimensional subspace, while the probabilistic Logit model relies on low dimensionality of the data log-likelihood ratios. Leveraging the low intrinsic dimensionality of the sought models, a rank regularized maximum-likelihood estimator is devised, which is then solved recursively via alternating majorization-minimization to sketch high-dimensional categorical data `on the fly.’ The resultant procedure alternates between sketching the new incomplete datum and refining the latent subspace, leading to lightweight first-order algorithms with highly parallelizable tasks per iteration. As an extra degree of freedom, the quantization thresholds are also learned jointly along with the subspace to enhance the predictive power of the sought models. Performance of the subspace iterates is analyzed for both infinite and finite data streams, where for the former asymptotic convergence to the stationary point set of the batch estimator is established, while for the latter sublinear regret bounds are derived for the empirical cost. Simulated tests with both synthetic and real-world datasets corroborate the merits of the novel schemes for real-time movie recommendation and chess-game classification. \|
Tasks	Quantization
Published	2016-09-27
URL	http://arxiv.org/abs/1609.08235v1
PDF	http://arxiv.org/pdf/1609.08235v1.pdf
PWC	https://paperswithcode.com/paper/online-categorical-subspace-learning-for
Repo
Framework

BioLeaf: a professional mobile application to measure foliar damage caused by insect herbivory


Title	BioLeaf: a professional mobile application to measure foliar damage caused by insect herbivory
Authors	Bruno Machado, Jonatan Orue, Mauro Arruda, Cleidimar Santos, Diogo Sarath, Wesley Goncalves, Gercina Silva, Hemerson Pistori, Antonia Roel, Jose Rodrigues-Jr
Abstract	Soybean is one of the ten greatest crops in the world, answering for billion-dollar businesses every year. This crop suffers from insect herbivory that costs millions from producers. Hence, constant monitoring of the crop foliar damage is necessary to guide the application of insecticides. However, current methods to measure foliar damage are expensive and dependent on laboratory facilities, in some cases, depending on complex devices. To cope with these shortcomings, we introduce an image processing methodology to measure the foliar damage in soybean leaves. We developed a non-destructive imaging method based on two techniques, Otsu segmentation and Bezier curves, to estimate the foliar loss in leaves with or without border damage. We instantiate our methodology in a mobile application named BioLeaf, which is freely distributed for smartphone users. We experimented with real-world leaves collected from a soybean crop in Brazil. Our results demonstrated that BioLeaf achieves foliar damage quantification with precision comparable to that of human specialists. With these results, our proposal might assist soybean producers, reducing the time to measure foliar damage, reducing analytical costs, and defining a commodity application that is applicable not only to soy, but also to different crops such as cotton, bean, potato, coffee, and vegetables.
Tasks
Published	2016-09-26
URL	http://arxiv.org/abs/1609.08004v2
PDF	http://arxiv.org/pdf/1609.08004v2.pdf
PWC	https://paperswithcode.com/paper/bioleaf-a-professional-mobile-application-to
Repo
Framework

Highway and Residual Networks learn Unrolled Iterative Estimation


Title	Highway and Residual Networks learn Unrolled Iterative Estimation
Authors	Klaus Greff, Rupesh K. Srivastava, Jürgen Schmidhuber
Abstract	The past year saw the introduction of new architectures such as Highway networks and Residual networks which, for the first time, enabled the training of feedforward networks with dozens to hundreds of layers using simple gradient descent. While depth of representation has been posited as a primary reason for their success, there are indications that these architectures defy a popular view of deep learning as a hierarchical computation of increasingly abstract features at each layer. In this report, we argue that this view is incomplete and does not adequately explain several recent findings. We propose an alternative viewpoint based on unrolled iterative estimation – a group of successive layers iteratively refine their estimates of the same features instead of computing an entirely new representation. We demonstrate that this viewpoint directly leads to the construction of Highway and Residual networks. Finally we provide preliminary experiments to discuss the similarities and differences between the two architectures.
Tasks
Published	2016-12-22
URL	http://arxiv.org/abs/1612.07771v3
PDF	http://arxiv.org/pdf/1612.07771v3.pdf
PWC	https://paperswithcode.com/paper/highway-and-residual-networks-learn-unrolled
Repo
Framework

Label-Free Supervision of Neural Networks with Physics and Domain Knowledge


Title	Label-Free Supervision of Neural Networks with Physics and Domain Knowledge
Authors	Russell Stewart, Stefano Ermon
Abstract	In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than direct examples of input-output pairs. These constraints are derived from prior domain knowledge, e.g., from known laws of physics. We demonstrate the effectiveness of this approach on real world and simulated computer vision tasks. We are able to train a convolutional neural network to detect and track objects without any labeled examples. Our approach can significantly reduce the need for labeled training data, but introduces new challenges for encoding prior knowledge into appropriate loss functions.
Tasks
Published	2016-09-18
URL	http://arxiv.org/abs/1609.05566v1
PDF	http://arxiv.org/pdf/1609.05566v1.pdf
PWC	https://paperswithcode.com/paper/label-free-supervision-of-neural-networks
Repo
Framework

Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches


Title	Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches
Authors	Shane Settle, Karen Livescu
Abstract	Acoustic word embeddings — fixed-dimensional vector representations of variable-length spoken word segments — have begun to be considered for tasks such as speech recognition and query-by-example search. Such embeddings can be learned discriminatively so that they are similar for speech segments corresponding to the same word, while being dissimilar for segments corresponding to different words. Recent work has found that acoustic word embeddings can outperform dynamic time warping on query-by-example search and related word discrimination tasks. However, the space of embedding models and training approaches is still relatively unexplored. In this paper we present new discriminative embedding models based on recurrent neural networks (RNNs). We consider training losses that have been successful in prior work, in particular a cross entropy loss for word classification and a contrastive loss that explicitly aims to separate same-word and different-word pairs in a “Siamese network” training setting. We find that both classifier-based and Siamese RNN embeddings improve over previously reported results on a word discrimination task, with Siamese RNNs outperforming classification models. In addition, we present analyses of the learned embeddings and the effects of variables such as dimensionality and network structure.
Tasks	Speech Recognition, Word Embeddings
Published	2016-11-08
URL	http://arxiv.org/abs/1611.02550v1
PDF	http://arxiv.org/pdf/1611.02550v1.pdf
PWC	https://paperswithcode.com/paper/discriminative-acoustic-word-embeddings
Repo
Framework