May 5, 2019

2727 words 13 mins read

Paper Group ANR 458

Global Minimum for a Finsler Elastica Minimal Path Approach. Möbius Invariants of Shapes and Images. MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction. Variational Inference for Sparse and Undirected Models. Towards Turkish ASR: Anatomy of a rule-based Turkish g2p. On Approximate …

Global Minimum for a Finsler Elastica Minimal Path Approach


Title	Global Minimum for a Finsler Elastica Minimal Path Approach
Authors	Da Chen, Jean-Marie Mirebeau, Laurent D. Cohen
Abstract	In this paper, we propose a novel curvature-penalized minimal path model via an orientation-lifted Finsler metric and the Euler elastica curve. The original minimal path model computes the globally minimal geodesic by solving an Eikonal partial differential equation (PDE). Essentially, this first-order model is unable to penalize curvature which is related to the path rigidity property in the classical active contour models. To solve this problem, we present an Eikonal PDE-based Finsler elastica minimal path approach to address the curvature-penalized geodesic energy minimization problem. We were successful at adding the curvature penalization to the classical geodesic energy. The basic idea of this work is to interpret the Euler elastica bending energy via a novel Finsler elastica metric that embeds a curvature penalty. This metric is non-Riemannian, anisotropic and asymmetric, and is defined over an orientation-lifted space by adding to the image domain the orientation as an extra space dimension. Based on this orientation lifting, the proposed minimal path model can benefit from both the curvature and orientation of the paths. Thanks to the fast marching method, the global minimum of the curvature-penalized geodesic energy can be computed efficiently. We introduce two anisotropic image data-driven speed functions that are computed by steerable filters. Based on these orientation-dependent speed functions, we can apply the proposed Finsler elastica minimal path model to the applications of closed contour detection, perceptual grouping and tubular structure extraction. Numerical experiments on both synthetic and real images show that these applications of the proposed model indeed obtain promising results.
Tasks	Contour Detection
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00343v3
PDF	http://arxiv.org/pdf/1612.00343v3.pdf
PWC	https://paperswithcode.com/paper/global-minimum-for-a-finsler-elastica-minimal
Repo
Framework

Möbius Invariants of Shapes and Images


Title	Möbius Invariants of Shapes and Images
Authors	Stephen Marsland, Robert McLachlan
Abstract	Identifying when different images are of the same object despite changes caused by imaging technologies, or processes such as growth, has many applications in fields such as computer vision and biological image analysis. One approach to this problem is to identify the group of possible transformations of the object and to find invariants to the action of that group, meaning that the object has the same values of the invariants despite the action of the group. In this paper we study the invariants of planar shapes and images under the M"obius group $\mathrm{PSL}(2,\mathbb{C})$, which arises in the conformal camera model of vision and may also correspond to neurological aspects of vision, such as grouping of lines and circles. We survey properties of invariants that are important in applications, and the known M"obius invariants, and then develop an algorithm by which shapes can be recognised that is M"obius- and reparametrization-invariant, numerically stable, and robust to noise. We demonstrate the efficacy of this new invariant approach on sets of curves, and then develop a M"obius-invariant signature of grey-scale images.
Tasks
Published	2016-03-30
URL	http://arxiv.org/abs/1603.09335v2
PDF	http://arxiv.org/pdf/1603.09335v2.pdf
PWC	https://paperswithcode.com/paper/mobius-invariants-of-shapes-and-images
Repo
Framework

MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction


Title	MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction
Authors	Zeming Lin, Jack Lanchantin, Yanjun Qi
Abstract	Predicting protein properties such as solvent accessibility and secondary structure from its primary amino acid sequence is an important task in bioinformatics. Recently, a few deep learning models have surpassed the traditional window based multilayer perceptron. Taking inspiration from the image classification domain we propose a deep convolutional neural network architecture, MUST-CNN, to predict protein properties. This architecture uses a novel multilayer shift-and-stitch (MUST) technique to generate fully dense per-position predictions on protein sequences. Our model is significantly simpler than the state-of-the-art, yet achieves better results. By combining MUST and the efficient convolution operation, we can consider far more parameters while retaining very fast prediction speeds. We beat the state-of-the-art performance on two large protein property prediction datasets.
Tasks	Image Classification
Published	2016-05-10
URL	http://arxiv.org/abs/1605.03004v1
PDF	http://arxiv.org/pdf/1605.03004v1.pdf
PWC	https://paperswithcode.com/paper/must-cnn-a-multilayer-shift-and-stitch-deep
Repo
Framework

Variational Inference for Sparse and Undirected Models


Title	Variational Inference for Sparse and Undirected Models
Authors	John Ingraham, Debora Marks
Abstract	Undirected graphical models are applied in genomics, protein structure prediction, and neuroscience to identify sparse interactions that underlie discrete data. Although Bayesian methods for inference would be favorable in these contexts, they are rarely used because they require doubly intractable Monte Carlo sampling. Here, we develop a framework for scalable Bayesian inference of discrete undirected models based on two new methods. The first is Persistent VI, an algorithm for variational inference of discrete undirected models that avoids doubly intractable MCMC and approximations of the partition function. The second is Fadeout, a reparameterization approach for variational inference under sparsity-inducing priors that captures a posteriori correlations between parameters and hyperparameters with noncentered parameterizations. We find that, together, these methods for variational inference substantially improve learning of sparse undirected graphical models in simulated and real problems from physics and biology.
Tasks	Bayesian Inference
Published	2016-02-11
URL	http://arxiv.org/abs/1602.03807v2
PDF	http://arxiv.org/pdf/1602.03807v2.pdf
PWC	https://paperswithcode.com/paper/variational-inference-for-sparse-and
Repo
Framework

Towards Turkish ASR: Anatomy of a rule-based Turkish g2p


Title	Towards Turkish ASR: Anatomy of a rule-based Turkish g2p
Authors	Duygu Altinok
Abstract	This paper describes the architecture and implementation of a rule-based grapheme to phoneme converter for Turkish. The system accepts surface form as input, outputs SAMPA mapping of the all parallel pronounciations according to the morphological analysis together with stress positions. The system has been implemented in Python
Tasks	Morphological Analysis
Published	2016-01-15
URL	http://arxiv.org/abs/1601.03783v1
PDF	http://arxiv.org/pdf/1601.03783v1.pdf
PWC	https://paperswithcode.com/paper/towards-turkish-asr-anatomy-of-a-rule-based
Repo
Framework

On Approximate Dynamic Programming with Multivariate Splines for Adaptive Control


Title	On Approximate Dynamic Programming with Multivariate Splines for Adaptive Control
Authors	Willem Eerland, Coen de Visser, Erik-Jan van Kampen
Abstract	We define a SDP framework based on the RLSTD algorithm and multivariate simplex B-splines. We introduce a local forget factor capable of preserving the continuity of the simplex splines. This local forget factor is integrated with the RLSTD algorithm, resulting in a modified RLSTD algorithm that is capable of tracking time-varying systems. We present the results of two numerical experiments, one validating SDP and comparing it with NDP and another to show the advantages of the modified RLSTD algorithm over the original. While SDP requires more computations per time-step, the experiment shows that for the same amount of function approximator parameters, there is an increase in performance in terms of stability and learning rate compared to NDP. The second experiment shows that SDP in combination with the modified RLSTD algorithm allows for faster recovery compared to the original RLSTD algorithm when system parameters are altered, paving the way for an adaptive high-performance non-linear control method.
Tasks
Published	2016-06-30
URL	http://arxiv.org/abs/1606.09383v1
PDF	http://arxiv.org/pdf/1606.09383v1.pdf
PWC	https://paperswithcode.com/paper/on-approximate-dynamic-programming-with
Repo
Framework

Genetic cellular neural networks for generating three-dimensional geometry


Title	Genetic cellular neural networks for generating three-dimensional geometry
Authors	Hugo Martay
Abstract	There are a number of ways to procedurally generate interesting three-dimensional shapes, and a method where a cellular neural network is combined with a mesh growth algorithm is presented here. The aim is to create a shape from a genetic code in such a way that a crude search can find interesting shapes. Identical neural networks are placed at each vertex of a mesh which can communicate with neural networks on neighboring vertices. The output of the neural networks determine how the mesh grows, allowing interesting shapes to be produced emergently, mimicking some of the complexity of biological organism development. Since the neural networks’ parameters can be freely mutated, the approach is amenable for use in a genetic algorithm.
Tasks
Published	2016-03-28
URL	http://arxiv.org/abs/1603.08551v1
PDF	http://arxiv.org/pdf/1603.08551v1.pdf
PWC	https://paperswithcode.com/paper/genetic-cellular-neural-networks-for
Repo
Framework

An automatic method for segmentation of fission tracks in epidote crystal photomicrographs


Title	An automatic method for segmentation of fission tracks in epidote crystal photomicrographs
Authors	Alexandre Fioravante de Siqueira, Wagner Massayuki Nakasuga, Aylton Pagamisse, Carlos Alberto Tello Saenz, Aldo Eloizo Job
Abstract	Manual identification of fission tracks has practical problems, such as variation due to observer-observation efficiency. An automatic processing method that could identify fission tracks in a photomicrograph could solve this problem and improve the speed of track counting. However, separation of non-trivial images is one of the most difficult tasks in image processing. Several commercial and free softwares are available, but these softwares are meant to be used in specific images. In this paper, an automatic method based on starlet wavelets is presented in order to separate fission tracks in mineral photomicrographs. Automatization is obtained by Matthews correlation coefficient, and results are evaluated by precision, recall and accuracy. This technique is an improvement of a method aimed at segmentation of scanning electron microscopy images. This method is applied in photomicrographs of epidote phenocrystals, in which accuracy higher than 89% was obtained in fission track segmentation, even for difficult images. Algorithms corresponding to the proposed method are available for download. Using the method presented here, an user could easily determine fission tracks in photomicrographs of mineral samples.
Tasks
Published	2016-02-12
URL	http://arxiv.org/abs/1602.03995v1
PDF	http://arxiv.org/pdf/1602.03995v1.pdf
PWC	https://paperswithcode.com/paper/an-automatic-method-for-segmentation-of
Repo
Framework

Generating Politically-Relevant Event Data


Title	Generating Politically-Relevant Event Data
Authors	John Beieler
Abstract	Automatically generated political event data is an important part of the social science data ecosystem. The approaches for generating this data, though, have remained largely the same for two decades. During this time, the field of computational linguistics has progressed tremendously. This paper presents an overview of political event data, including methods and ontologies, and a set of experiments to determine the applicability of deep neural networks to the extraction of political events from news text.
Tasks
Published	2016-09-20
URL	http://arxiv.org/abs/1609.06239v1
PDF	http://arxiv.org/pdf/1609.06239v1.pdf
PWC	https://paperswithcode.com/paper/generating-politically-relevant-event-data
Repo
Framework

The Recycling Gibbs Sampler for Efficient Learning


Title	The Recycling Gibbs Sampler for Efficient Learning
Authors	Luca Martino, Victor Elvira, Gustau Camps-Valls
Abstract	Monte Carlo methods are essential tools for Bayesian inference. Gibbs sampling is a well-known Markov chain Monte Carlo (MCMC) algorithm, extensively used in signal processing, machine learning, and statistics, employed to draw samples from complicated high-dimensional posterior distributions. The key point for the successful application of the Gibbs sampler is the ability to draw efficiently samples from the full-conditional probability density functions. Since in the general case this is not possible, in order to speed up the convergence of the chain, it is required to generate auxiliary samples whose information is eventually disregarded. In this work, we show that these auxiliary samples can be recycled within the Gibbs estimators, improving their efficiency with no extra cost. This novel scheme arises naturally after pointing out the relationship between the standard Gibbs sampler and the chain rule used for sampling purposes. Numerical simulations involving simple and real inference problems confirm the excellent performance of the proposed scheme in terms of accuracy and computational efficiency. In particular we give empirical evidence of performance in a toy example, inference of Gaussian processes hyperparameters, and learning dependence graphs through regression.
Tasks	Bayesian Inference, Gaussian Processes
Published	2016-11-21
URL	http://arxiv.org/abs/1611.07056v2
PDF	http://arxiv.org/pdf/1611.07056v2.pdf
PWC	https://paperswithcode.com/paper/the-recycling-gibbs-sampler-for-efficient
Repo
Framework

Distributable Consistent Multi-Object Matching


Title	Distributable Consistent Multi-Object Matching
Authors	Nan Hu, Qixing Huang, Boris Thibert, Leonidas Guibas
Abstract	In this paper we propose an optimization-based framework to multiple object matching. The framework takes maps computed between pairs of objects as input, and outputs maps that are consistent among all pairs of objects. The central idea of our approach is to divide the input object collection into overlapping sub-collections and enforce map consistency among each sub-collection. This leads to a distributed formulation, which is scalable to large-scale datasets. We also present an equivalence condition between this decoupled scheme and the original scheme. Experiments on both synthetic and real-world datasets show that our framework is competitive against state-of-the-art multi-object matching techniques.
Tasks
Published	2016-11-22
URL	http://arxiv.org/abs/1611.07191v3
PDF	http://arxiv.org/pdf/1611.07191v3.pdf
PWC	https://paperswithcode.com/paper/distributable-consistent-multi-object
Repo
Framework

Lipschitz Continuity of Mahalanobis Distances and Bilinear Forms


Title	Lipschitz Continuity of Mahalanobis Distances and Bilinear Forms
Authors	Valentina Zantedeschi, Rémi Emonet, Marc Sebban
Abstract	Many theoretical results in the machine learning domain stand only for functions that are Lipschitz continuous. Lipschitz continuity is a strong form of continuity that linearly bounds the variations of a function. In this paper, we derive tight Lipschitz constants for two families of metrics: Mahalanobis distances and bounded-space bilinear forms. To our knowledge, this is the first time the Mahalanobis distance is formally proved to be Lipschitz continuous and that such tight Lipschitz constants are derived.
Tasks
Published	2016-04-04
URL	http://arxiv.org/abs/1604.01376v1
PDF	http://arxiv.org/pdf/1604.01376v1.pdf
PWC	https://paperswithcode.com/paper/lipschitz-continuity-of-mahalanobis-distances
Repo
Framework

Automatic Node Selection for Deep Neural Networks using Group Lasso Regularization


Title	Automatic Node Selection for Deep Neural Networks using Group Lasso Regularization
Authors	Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri
Abstract	We examine the effect of the Group Lasso (gLasso) regularizer in selecting the salient nodes of Deep Neural Network (DNN) hidden layers by applying a DNN-HMM hybrid speech recognizer to TED Talks speech data. We test two types of gLasso regularization, one for outgoing weight vectors and another for incoming weight vectors, as well as two sizes of DNNs: 2048 hidden layer nodes and 4096 nodes. Furthermore, we compare gLasso and L2 regularizers. Our experiment results demonstrate that our DNN training, in which the gLasso regularizer was embedded, successfully selected the hidden layer nodes that are necessary and sufficient for achieving high classification power.
Tasks
Published	2016-11-17
URL	http://arxiv.org/abs/1611.05527v1
PDF	http://arxiv.org/pdf/1611.05527v1.pdf
PWC	https://paperswithcode.com/paper/automatic-node-selection-for-deep-neural
Repo
Framework

Semi-Markov Switching Vector Autoregressive Model-based Anomaly Detection in Aviation Systems


Title	Semi-Markov Switching Vector Autoregressive Model-based Anomaly Detection in Aviation Systems
Authors	Igor Melnyk, Arindam Banerjee, Bryan Matthews, Nikunj Oza
Abstract	In this work we consider the problem of anomaly detection in heterogeneous, multivariate, variable-length time series datasets. Our focus is on the aviation safety domain, where data objects are flights and time series are sensor readings and pilot switches. In this context the goal is to detect anomalous flight segments, due to mechanical, environmental, or human factors in order to identifying operationally significant events and provide insights into the flight operations and highlight otherwise unavailable potential safety risks and precursors to accidents. For this purpose, we propose a framework which represents each flight using a semi-Markov switching vector autoregressive (SMS-VAR) model. Detection of anomalies is then based on measuring dissimilarities between the model’s prediction and data observation. The framework is scalable, due to the inherent parallel nature of most computations, and can be used to perform online anomaly detection. Extensive experimental results on simulated and real datasets illustrate that the framework can detect various types of anomalies along with the key parameters involved.
Tasks	Anomaly Detection, Time Series
Published	2016-02-21
URL	http://arxiv.org/abs/1602.06550v2
PDF	http://arxiv.org/pdf/1602.06550v2.pdf
PWC	https://paperswithcode.com/paper/semi-markov-switching-vector-autoregressive
Repo
Framework

Body movement to sound interface with vector autoregressive hierarchical hidden Markov models


Title	Body movement to sound interface with vector autoregressive hierarchical hidden Markov models
Authors	Dimitrije Marković, Borjana Valčić, Nebojša Malešević
Abstract	Interfacing a kinetic action of a person to an action of a machine system is an important research topic in many application areas. One of the key factors for intimate human-machine interaction is the ability of the control algorithm to detect and classify different user commands with shortest possible latency, thus making a highly correlated link between cause and effect. In our research, we focused on the task of mapping user kinematic actions into sound samples. The presented methodology relies on the wireless sensor nodes equipped with inertial measurement units and the real-time algorithm dedicated for early detection and classification of a variety of movements/gestures performed by a user. The core algorithm is based on the approximate Bayesian inference of Vector Autoregressive Hierarchical Hidden Markov Models (VAR-HHMM), where models database is derived from the set of motion gestures. The performance of the algorithm was compared with an online version of the K-nearest neighbours (KNN) algorithm, where we used offline expert based classification as the benchmark. In almost all of the evaluation metrics (e.g. confusion matrix, recall and precision scores) the VAR-HHMM algorithm outperformed KNN. Furthermore, the VAR-HHMM algorithm, in some cases, achieved faster movement onset detection compared with the offline standard. The proposed concept, although envisioned for movement-to-sound application, could be implemented in other human-machine interfaces.
Tasks	Bayesian Inference
Published	2016-10-26
URL	http://arxiv.org/abs/1610.08450v1
PDF	http://arxiv.org/pdf/1610.08450v1.pdf
PWC	https://paperswithcode.com/paper/body-movement-to-sound-interface-with-vector
Repo
Framework