Skip to main content

149,746
UPLOADS


More right-solid

Show sorted alphabetically

More right-solid

Show sorted alphabetically

More right-solid

SHOW DETAILS
eye
Title
Date Archived
Creator
Arxiv.org
by Edward Choi; Mohammad Taha Bahadori; Elizabeth Searles; Catherine Coffey; Jimeng Sun
texts

eye 3

favorite 0

comment 0

Learning efficient representations for concepts has been proven to be an important basis for many applications such as machine translation or document classification. Proper representations of medical concepts such as diagnosis, medication, procedure codes and visits will have broad applications in healthcare analytics. However, in Electronic Health Records (EHR) the visit sequences of patients include multiple concepts (diagnosis, procedure, and medication codes) per visit. This structure...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1602.05568
Arxiv.org
by Bowen Baker; Otkrist Gupta; Nikhil Naik; Ramesh Raskar
texts

eye 5

favorite 0

comment 0

At present, designing convolutional neural network (CNN) architectures requires both human expertise and labor. New architectures are handcrafted by careful experimentation or modified from a handful of existing networks. We introduce MetaQNN, a meta-modeling algorithm based on reinforcement learning to automatically generate high-performing CNN architectures for a given learning task. The learning agent is trained to sequentially choose CNN layers using $Q$-learning with an $\epsilon$-greedy...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1611.02167
Arxiv.org
by Carl S. Adorf; Paul M. Dodd; Sharon C. Glotzer
texts

eye 5

favorite 0

comment 0

Researchers in the field of computational physics, chemistry, and materials science are regularly posed with the challenge of managing large and heterogeneous data spaces. The amount of data increases in lockstep with computational efficiency multiplied by the amount of available computational resources, which shifts the bottleneck within the scientific process from data acquisition to data post-processing and analysis. We present a framework designed to aid in the integration of various...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1611.03543
Arxiv.org
by Han-Zhou Wu; Hong-Xia Wang; Yun-Qing Shi
texts

eye 4

favorite 0

comment 0

This paper presents a novel reversible data hiding (RDH) algorithm for gray-scaled images, in which the prediction-error of prediction error (PPE) of a pixel is used to carry the secret data. In the proposed method, the pixels to be embedded are firstly predicted with their neighboring pixels to obtain the corresponding prediction errors (PEs). Then, by exploiting the PEs of the neighboring pixels, the prediction of the PEs of the pixels can be determined. And, a sorting technique based on the...
Topics: Multimedia, Computing Research Repository
Source: http://arxiv.org/abs/1604.04984
Arxiv.org
by Fereidoon Sadri; Gayatri Tallur
texts

eye 5

favorite 0

comment 0

We study the problem of data integration from sources that contain probabilistic uncertain information. Data is modeled by possible-worlds with probability distribution, compactly represented in the probabilistic relation model. Integration is achieved efficiently using the extended probabilistic relation model. We study the problem of determining the probability distribution of the integration result. It has been shown that, in general, only probability ranges can be determined for the result...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1607.05702
Arxiv.org
by Gokhan Kul; Duc Luong; Ting Xie; Patrick Coonan; Varun Chandola; Oliver Kennedy; Shambhu Upadhyaya
texts

eye 3

favorite 0

comment 0

Database access logs are large, unwieldy, and hard for humans to inspect and summarize. In spite of this, they remain the canonical go-to resource for tasks ranging from performance tuning to security auditing. In this paper, we address the challenge of compactly encoding large sequences of SQL queries for presentation to a human user. Our approach is based on the Weisfeiler-Lehman (WL) approximate graph isomorphism algorithm, which identifies salient features of a graph or in our case of an...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1608.01013
Arxiv.org
texts

eye 3

favorite 0

comment 0

This paper reports a partially decentralized implementation of an Extended Kalman filter for the cooperative localization of a team of mobile robots with limited onboard resources. Unlike a fully centralized scheme that requires, at each timestep, information from the entire team to be gathered together and be processed by a single device, our algorithm only requires that the robots communicate with a central command unit at the time of a measurement update. Every robot only needs to propagate...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1608.00609
In this paper, a two-stage dual tree complex wavelet packet transform (DTCWPT) based speech enhancement algorithm has been proposed, in which a speech presence probability (SPP) estimator and a generalized minimum mean squared error (MMSE) estimator are developed. To overcome the drawback of signal distortions caused by down sampling of WPT, a two-stage analytic decomposition concatenating undecimated WPT (UWPT) and decimated WPT is employed. An SPP estimator in the DTCWPT domain is derived...
Topics: Sound, Computing Research Repository
Source: http://arxiv.org/abs/1610.00644
Arxiv.org
by Weiran Wang; Xinchen Yan; Honglak Lee; Karen Livescu
texts

eye 3

favorite 0

comment 0

We present deep variational canonical correlation analysis (VCCA), a deep multi-view learning model that extends the latent variable model interpretation of linear CCA to nonlinear observation models parameterized by deep neural networks. We derive variational lower bounds of the data likelihood by parameterizing the posterior probability of the latent variables from the view that is available at test time. We also propose a variant of VCCA called VCCA-private that can, in addition to the...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1610.03454
Arxiv.org
texts

eye 5

favorite 0

comment 0

One key aspect of the CELP algorithm is that it shapes the coding noise using a simple, yet effective, weighting filter. In this paper, we improve the noise shaping of CELP using a more modern psychoacoustic model. This has the significant advantage of improving the quality of an existing codec without the need to change the bit-stream. More specifically, we improve the Speex CELP codec by using the psychoacoustic model used in the Vorbis audio codec. The results show a significant increase in...
Topics: Sound, Computing Research Repository
Source: http://arxiv.org/abs/1603.01863
Arxiv.org
by Srikanth Cherla; Son N Tran; Tillman Weyde; Artur d'Avila Garcez
texts

eye 3

favorite 0

comment 0

We present a novel theoretical result that generalises the Discriminative Restricted Boltzmann Machine (DRBM). While originally the DRBM was defined assuming the {0, 1}-Bernoulli distribution in each of its hidden units, this result makes it possible to derive cost functions for variants of the DRBM that utilise other distributions, including some that are often encountered in the literature. This is illustrated with the Binomial and {-1, +1}-Bernoulli distributions here. We evaluate these two...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1604.01806
Arxiv.org
by Yun Fei
texts

eye 3

favorite 0

comment 0

In this technical report we derive the analytic form of the Hessian matrix for shape matching energy. Shape matching is a useful technique for meshless deformation, which can be easily combined with multiple techniques in real-time dynamics. Nevertheless, it has been rarely applied in scenarios where implicit integrators are required, and hence strong viscous damping effect, though popular in simulation systems nowadays, is forbidden for shape matching. The reason lies in the difficulty to...
Topics: Graphics, Computing Research Repository
Source: http://arxiv.org/abs/1604.02483
Arxiv.org
by Eyal En Gad; Akshay Gadde; A. Salman Avestimehr; Antonio Ortega
texts

eye 3

favorite 0

comment 0

This paper studies graph-based active learning, where the goal is to reconstruct a binary signal defined on the nodes of a weighted graph, by sampling it on a small subset of the nodes. A new sampling algorithm is proposed, which sequentially selects the graph nodes to be sampled, based on an aggressive search for the boundary of the signal over the graph. The algorithm generalizes a recent method for sampling nodes in unweighted graphs. The generalization improves the sampling performance...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1605.05710
Arxiv.org
texts

eye 3

favorite 0

comment 0

Modern distributed cyber-physical systems encounter a large variety of anomalies and in many cases, they are vulnerable to catastrophic fault propagation scenarios due to strong connectivity among the sub-systems. In this regard, root-cause analysis becomes highly intractable due to complex fault propagation mechanisms in combination with diverse operating modes. This paper presents a new data-driven framework for root-cause analysis for addressing such issues. The framework is based on a...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1605.06421
Arxiv.org
by Harishchandra Dubey; Lakshmish Kaushik; Abhijeet Sangwan; John H. L. Hansen
texts

eye 4

favorite 0

comment 0

Peer-led team learning (PLTL) is a model for teaching STEM courses where small student groups meet periodically to collaboratively discuss coursework. Automatic analysis of PLTL sessions would help education researchers to get insight into how learning outcomes are impacted by individual participation, group behavior, team dynamics, etc.. Towards this, speech and language technology can help, and speaker diarization technology will lay the foundation for analysis. In this study, a new corpus is...
Topics: Sound, Computing Research Repository
Source: http://arxiv.org/abs/1606.07136
Arxiv.org
by Parsa Bagherzadeh; Hadi Sadoghi Yazdi
texts

eye 3

favorite 0

comment 0

The presence of outliers is prevalent in machine learning applications and may produce misleading results. In this paper a new method for dealing with outliers and anomal samples is proposed. To overcome the outlier issue, the proposed method combines the global and local views of the samples. By combination of these views, our algorithm performs in a robust manner. The experimental results show the capabilities of the proposed method.
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1607.00466
Arxiv.org
by Francesco Riccio; Roberto Capobianco; Marc Hanheide; Daniele Nardi
texts

eye 5

favorite 0

comment 0

Affordances have been introduced in literature as action opportunities that objects offer, and used in robotics to semantically represent their interconnection. However, when considering an environment instead of an object, the problem becomes more complex due to the dynamism of its state. To tackle this issue, we introduce the concept of Spatio-Temporal Affordances (STA) and Spatio-Temporal Affordance Map (STAM). Using this formalism, we encode action semantics related to the environment to...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1607.00354
Arxiv.org
by Cheng Zhang; Hedvig Kjellstrom; Carl Henrik Ek; Bo C. Bertilson
texts

eye 6

favorite 0

comment 0

In this paper, we explore the possibility to apply machine learning to make diagnostic predictions using discomfort drawings. A discomfort drawing is an intuitive way for patients to express discomfort and pain related symptoms. These drawings have proven to be an effective method to collect patient data and make diagnostic decisions in real-life practice. A dataset from real-world patient cases is collected for which medical experts provide diagnostic labels. Next, we use a factorized...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1607.08206
Arxiv.org
by Milutin Nikolić; Branislav Borovac; Mirko Raković; Milica Žigić
texts

eye 3

favorite 0

comment 0

Planning of any motion starts by planning the trajectory of the CoM. It is of the highest importance to ensure that the robot will be able to perform planned trajectory. With increasing capabilities of the humanoid robots, the case when contacts are spatially distributed should be considered. In this paper, it is shown that there are some contact configurations in which any acceleration of the center of mass (CoM) is feasible. The procedure for identifying such a configurations is presented, as...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1608.01868
Arxiv.org
by Jaroslaw Szlichta; Parke Godfrey; Lukasz Golab; Mehdi Kargar; Divesh Srivastava
texts

eye 3

favorite 0

comment 0

Integrity constraints (ICs) provide a valuable tool for expressing and enforcing application semantics. However, formulating constraints manually requires domain expertise, is prone to human errors, and may be excessively time consuming, especially on large datasets. Hence, proposals for automatic discovery have been made for some classes of ICs, such as functional dependencies (FDs), and recently, order dependencies (ODs). ODs properly subsume FDs, as they can additionally express business...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1608.06169
Arxiv.org
by He He; Jordan Boyd-Graber; Kevin Kwok; Hal Daumé
texts

eye 5

favorite 0

comment 0

Opponent modeling is necessary in multi-agent settings where secondary agents with competing goals also adapt their strategies, yet it remains challenging because strategies interact with each other and change. Most previous work focuses on developing probabilistic models or parameterized strategies for specific applications. Inspired by the recent success of deep reinforcement learning, we present neural-based models that jointly learn a policy and the behavior of opponents. Instead of...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1609.05559
Arxiv.org
by Se Rim Park; Jinwon Lee
texts

eye 6

favorite 0

comment 0

In hearing aids, the presence of babble noise degrades hearing intelligibility of human speech greatly. However, removing the babble without creating artifacts in human speech is a challenging task in a low SNR environment. Here, we sought to solve the problem by finding a `mapping' between noisy speech spectra and clean speech spectra via supervised learning. Specifically, we propose using fully Convolutional Neural Networks, which consist of lesser number of parameters than fully connected...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1609.07132
Arxiv.org
by Weixiang Shao; Lifang He; Chun-Ta Lu; Xiaokai Wei; Philip S. Yu
texts

eye 3

favorite 0

comment 0

In the era of big data, it is becoming common to have data with multiple modalities or coming from multiple sources, known as "multi-view data". Multi-view data are usually unlabeled and come from high-dimensional spaces (such as language vocabularies), unsupervised multi-view feature selection is crucial to many applications. However, it is nontrivial due to the following challenges. First, there are too many instances or the feature dimensionality is too large. Thus, the data may...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1609.08286
Arxiv.org
by Xiatian Zhang; Fan Yao; Yongjun Tian
texts

eye 3

favorite 0

comment 0

In this paper we present the greedy step averaging(GSA) method, a parameter-free stochastic optimization algorithm for a variety of machine learning problems. As a gradient-based optimization method, GSA makes use of the information from the minimizer of a single sample's loss function, and takes average strategy to calculate reasonable learning rate sequence. While most existing gradient-based algorithms introduce an increasing number of hyper parameters or try to make a trade-off between...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1611.03608
Arxiv.org
by Ludovic Hofer; Michio Tanaka; Hakaru Tamukoh; Amir Ali Forough Nassiraei; Takashi Morie
texts

eye 3

favorite 0

comment 0

This paper proposes a visual-servoing method dedicated to grasping of daily-life objects. In order to obtain an affordable solution, we use a low-accurate robotic arm. Our method corrects errors by using an RGB-D sensor. It is based on SURF invariant features which allows us to perform object recognition at a high frame rate. We define regions of interest based on depth segmentation, and we use them to speed-up the recognition and to improve reliability. The system has been tested on a...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1612.03784
Arxiv.org
by Brayden Hollis; Stacy Patterson; Jeff Trinkle
texts

eye 4

favorite 0

comment 0

Whole body tactile perception via tactile skins offers large benefits for robots in unstructured environments. To fully realize this benefit, tactile systems must support real-time data acquisition over a massive number of tactile sensor elements. We present a novel approach for scalable tactile data acquisition using compressed sensing. We first demonstrate that the tactile data is amenable to compressed sensing techniques. We then develop a solution for fast data sampling, compression, and...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1603.01324
Arxiv.org
by Michel Coste; Philippe Wenger; Damien Chablat
texts

eye 5

favorite 0

comment 0

This paper investigates a situation pointed out in a recent paper, in which a non-singular change of assembly mode of a planar 2-RPR-PR parallel manipulator was realized by encircling a point of multiplicity 4. It is shown that this situation is, in fact, a non-generic one and gives rise to cusps under a small perturbation. Furthermore , we show that, for a large class of singularities of multiplicity 4, there are only two types of stable singularities occurring in a small perturbation: these...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1604.08742
Arxiv.org
by Jan Winkler; Ferenc Balint-Benczedi; Thiemo Wiedemeyer; Michael Beetz; Narunas Vaskevicius; Christian A. Mueller; Tobias Fromm; Andreas Birk
texts

eye 3

favorite 0

comment 0

Autonomous robots in unstructured and dynamically changing retail environments have to master complex perception, knowledgeprocessing, and manipulation tasks. To enable them to act competently, we propose a framework based on three core components: (o) a knowledge-enabled perception system, capable of combining diverse information sources to cope with occlusions and stacked objects with a variety of textures and shapes, (o) knowledge processing methods produce strategies for tidying up...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1605.04177
Arxiv.org
by Inbal Horev; Florian Yger; Masashi Sugiyama
texts

eye 4

favorite 0

comment 0

In many real-world applications data exhibits non-stationarity, i.e., its distribution changes over time. One approach to handling non-stationarity is to remove or minimize it before attempting to analyze the data. In the context of brain computer interface (BCI) data analysis this may be done by means of stationary subspace analysis (SSA). The classic SSA method finds a matrix that projects the data onto a stationary subspace by optimizing a cost function based on a matrix divergence. In this...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1605.07785
Arxiv.org
by Peter Buneman; Sławek Staworko
texts

eye 4

favorite 0

comment 0

We investigate the problem of aligning two RDF databases, an essential problem in understanding the evolution of ontologies. Our approaches address three fundamental challenges: 1) the use of "blank" (null) names, 2) ontology changes in which different names are used to identify the same entity, and 3) small changes in the data values as well as small changes in the graph structure of the RDF database. We propose approaches inspired by the classical notion of graph bisimulation and...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1606.08657
Arxiv.org
by Charles K. Chui; H. N. Mhaskar
texts

eye 4

favorite 0

comment 0

The problem of extending a function $f$ defined on a training data $\mathcal{C}$ on an unknown manifold $\mathbb{X}$ to the entire manifold and a tubular neighborhood of this manifold is considered in this paper. For $\mathbb{X}$ embedded in a high dimensional ambient Euclidean space $\mathbb{R}^D$, a deep learning algorithm is developed for finding a local coordinate system for the manifold {\bf without eigen--decomposition}, which reduces the problem to the classical problem of function...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1607.07110
Arxiv.org
by Georg Wiedebach; Sylvain Bertrand; Tingfan Wu; Luca Fiorio; Stephen McCrory; Robert Griffin; Francesco Nori; Jerry Pratt
texts

eye 5

favorite 0

comment 0

We present a method for humanoid robot walking on partial footholds such as small stepping stones and rocks with sharp surfaces. Our algorithm does not rely on prior knowledge of the foothold, but information about an expected foothold can be used to improve the stepping performance. After a step is taken, the robot explores the new contact surface by attempting to shift the center of pressure around the foot. The available foothold is inferred by the way in which the foot rotates about contact...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1607.08089
Arxiv.org
by Kai Herrmann; Hannes Voigt; Andreas Behrend; Jonas Rausch; Wolfgang Lehner
texts

eye 3

favorite 0

comment 0

We present InVerDa, a tool for end-to-end support of co-existing schema versions within one database. While it is state of the art to run multiple versions of a continuously developed application concurrently, the same is hard for databases. In order to keep multiple co-existing schema versions alive, that all access the same data set, developers usually employ handwritten delta code (e.g. views and triggers in SQL). This delta code is hard to write and hard to maintain: if a database...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1608.05564
Arxiv.org
by Katsumi Kumai; Yuhki Shiraishi; Jianwei Zhang; Hiroyuki Kitagawa; Atsuyuki Morishima
texts

eye 5

favorite 0

comment 0

A common workflow to perform a continuous human task stream is to divide workers into groups, have one group perform the newly-arrived task, and rotate the groups. We call this type of workflow the group rotation. This paper addresses the problem of how to manage Group Rotation Type Crowdsourcing, the group rotation in a crowdsourcing setting. In the group-rotation type crowdsourcing, we must change the group structure dynamically because workers come in and leave frequently. This paper...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1609.00117
Arxiv.org
by Aditya Gopalan; Odalric-Ambrym Maillard; Mohammadi Zaki
texts

eye 4

favorite 0

comment 0

We study the task of maximizing rewards from recommending items (actions) to users sequentially interacting with a recommender system. Users are modeled as latent mixtures of C many representative user classes, where each class specifies a mean reward profile across actions. Both the user features (mixture distribution over classes) and the item features (mean reward vector per class) are unknown a priori. The user identity is the only contextual information available to the learner while...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1609.01508
Arxiv.org
by Kalina Jasinska; Nikos Karampatziakis
texts

eye 5

favorite 0

comment 0

We present LTLS, a technique for multiclass and multilabel prediction that can perform training and inference in logarithmic time and space. LTLS embeds large classification problems into simple structured prediction problems and relies on efficient dynamic programming algorithms for inference. We train LTLS with stochastic gradient descent on a number of multiclass and multilabel datasets and show that despite its small memory footprint it is often competitive with existing approaches.
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1611.01964
Arxiv.org
by Adeline Bailly; Simon Malinowski; Romain Tavenard; Thomas Guyet; Laetitia Chapel
texts

eye 4

favorite 0

comment 0

Time series classification is an application of particular interest with the increase of data to monitor. Classical techniques for time series classification rely on point-to-point distances. Recently, Bag-of-Words approaches have been used in this context. Words are quantized versions of simple features extracted from sliding windows. The SIFT framework has proved efficient for image classification. In this paper, we design a time series classification scheme that builds on the SIFT framework...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1601.01799
Arxiv.org
by Huanhuan Wu; Yuzhen Huang; James Cheng; Jinfeng Li; Yiping Ke
texts

eye 5

favorite 0

comment 0

A temporal graph is a graph in which vertices communicate with each other at specific time, e.g., $A$ calls $B$ at 11 a.m. and talks for 7 minutes, which is modeled by an edge from $A$ to $B$ with starting time "11 a.m." and duration "7 mins". Temporal graphs can be used to model many networks with time-related activities, but efficient algorithms for analyzing temporal graphs are severely inadequate. We study fundamental problems such as answering reachability and...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1601.05909
Arxiv.org
by Yinxiao Li; Xiuhan Hu; Danfei Xu; Yonghao Yue; Eitan Grinspun; Peter Allen
texts

eye 4

favorite 0

comment 0

Robotic manipulation of deformable objects remains a challenging task. One such task is to iron a piece of cloth autonomously. Given a roughly flattened cloth, the goal is to have an ironing plan that can iteratively apply a regular iron to remove all the major wrinkles by a robot. We present a novel solution to analyze the cloth surface by fusing two surface scan techniques: a curvature scan and a discontinuity scan. The curvature scan can estimate the height deviation of the cloth surface,...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1602.04918
Arxiv.org
by Matthieu Courbariaux; Itay Hubara; Daniel Soudry; Ran El-Yaniv; Yoshua Bengio
texts

eye 4

favorite 0

comment 0

We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time. At training-time the binary weights and activations are used for computing the parameters gradients. During the forward pass, BNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations, which is expected to substantially improve power-efficiency. To validate the effectiveness of BNNs we conduct two sets of...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1602.02830
Arxiv.org
by Alireza Ghasemi; Hamid R. Rabiee; Mohammad T. Manzuri; M. H. Rohban
texts

eye 3

favorite 0

comment 0

In this paper, we address the problem of data description using a Bayesian framework. The goal of data description is to draw a boundary around objects of a certain class of interest to discriminate that class from the rest of the feature space. Data description is also known as one-class learning and has a wide range of applications. The proposed approach uses a Bayesian framework to precisely compute the class boundary and therefore can utilize domain information in form of prior knowledge in...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1602.07507
Arxiv.org
texts

eye 3

favorite 0

comment 0

We present a damage-aware planning approach which determines the best sequence to manipulate a number of objects in a scene. This works on task-planning level, abstracts from motion planning and anticipates the dynamics of the scene using a physics simulation. Instead of avoiding interaction with the environment, we take unintended motion of other objects into account and plan manipulation sequences which minimize the potential damage. Our method can also be used as a validation measure to...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1603.00652
Arxiv.org
by Florian T. Pokorny; Yasemin Bekiroglu; Karl Pauwels; Judith Bütepage; Clara Scherer; Danica Kragic
texts

eye 4

favorite 0

comment 0

We present a novel approach and database which combines the inexpensive generation of 3D object models via monocular or RGB-D camera images with 3D printing and a state of the art object tracking algorithm. Unlike recent efforts towards the creation of 3D object databases for robotics, our approach does not require expensive and controlled 3D scanning setups and enables anyone with a camera to scan, print and track complex objects for manipulation research. The proposed approach results in...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1610.05175
Arxiv.org
by Martin Sinclair; Ioannis Raptis
texts

eye 4

favorite 0

comment 0

Large-Scale Actuator Networks (LSAN) are a rapidly growing class of electromechanical systems. A prime application of LSANs in the industrial sector is distributed manipulation. LSAN's are typically implemented using: vibrating plates, air jets, and mobile multi-robot teams. This paper investigates a surface capable of morphing its shape using an array of linear actuators to impose two dimensional translational movement on a set of objects. The collective nature of the actuator network...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1604.04659
Arxiv.org
by Oliver Kroemer; Gaurav S. Sukhatme
texts

eye 4

favorite 0

comment 0

Robots can generalize manipulation skills between different scenarios by adapting to the features of the objects being manipulated. Selecting the set of relevant features for generalizing skills has usually been performed manually by a human. Alternatively, a robot can learn to select relevant features autonomously. However, feature selection usually requires a large amount of training data, which would require many demonstrations. In order to learn the relevant features more efficiently, we...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1605.04439
Arxiv.org
by Saeed Ranjbar Alvar; Fatih Kamisli
texts

eye 6

favorite 0

comment 0

In pixel-by-pixel spatial prediction methods for lossless intra coding, the prediction is obtained by a weighted sum of neighbouring pixels. The proposed prediction approach in this paper uses a weighted sum of three neighbor pixels according to a two-dimensional correlation model. The weights are obtained after a three step optimization procedure. The first two stages are offline procedures where the computed prediction weights are obtained offline from training sequences. The third stage is...
Topics: Multimedia, Computing Research Repository
Source: http://arxiv.org/abs/1604.07051
Arxiv.org
by Yongxin Yang; Timothy Hospedales
texts

eye 3

favorite 0

comment 0

Most contemporary multi-task learning methods assume linear models. This setting is considered shallow in the era of deep learning. In this paper, we present a new deep multi-task representation learning framework that learns cross-task sharing structure at every layer in a deep network. Our approach is based on generalising the matrix factorisation techniques explicitly or implicitly used by many conventional MTL algorithms to tensor factorisation, to realise automatic learning of end-to-end...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1605.06391
Arxiv.org
by Ye Zhu; Tian-Tsong Ng; Xuanjing Shen; Bihan Wen
texts

eye 4

favorite 0

comment 0

Many images, of natural or man-made scenes often contain Similar but Genuine Objects (SGO). This poses a challenge to existing Copy-Move Forgery Detection (CMFD) methods which match the key points / blocks, solely based on the pair similarity in the scene. To address such issue, we propose a novel CMFD method using Scaled Harris Feature Descriptors (SHFD) that preform consistently well on forged images with SGO. It involves the following main steps: (i) Pyramid scale space and orientation...
Topics: Multimedia, Computing Research Repository
Source: http://arxiv.org/abs/1601.07262
Arxiv.org
texts

eye 7

favorite 0

comment 0

Unsupervised learning aims at the discovery of hidden structure that drives the observations in the real world. It is essential for success in modern machine learning. Latent variable models are versatile in unsupervised learning and have applications in almost every domain. Training latent variable models is challenging due to the non-convexity of the likelihood objective. An alternative method is based on the spectral decomposition of low order moment tensors. This versatile framework is...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1606.03212
Arxiv.org
by Thông T. Nguyên; Xiaokui Xiao; Yin Yang; Siu Cheung Hui; Hyejin Shin; Junbum Shin
texts

eye 4

favorite 0

comment 0

Organizations with a large user base, such as Samsung and Google, can potentially benefit from collecting and mining users' data. However, doing so raises privacy concerns, and risks accidental privacy breaches with serious consequences. Local differential privacy (LDP) techniques address this problem by only collecting randomized answers from each user, with guarantees of plausible deniability; meanwhile, the aggregator can still build accurate models and predictors by analyzing large amounts...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1606.05053
Arxiv.org
by Michael Bloesch; Hannes Sommer; Tristan Laidlow; Michael Burri; Gabriel Nuetzi; Péter Fankhauser; Dario Bellicoso; Christian Gehring; Stefan Leutenegger; Marco Hutter; Roland Siegwart
texts

eye 7

favorite 0

comment 0

The proper handling of 3D orientations is a central element in many optimization problems in engineering. Unfortunately many researchers and engineers struggle with the formulation of such problems and often fall back to suboptimal solutions. The existence of many different conventions further complicates this issue, especially when interfacing multiple differing implementations. This document discusses an alternative approach which makes use of a more abstract notion of 3D orientations. The...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1606.05285
Arxiv.org
by Yong Kiam Tan; Xinxing Xu; Yong Liu
texts

eye 4

favorite 0

comment 0

Recurrent neural networks (RNNs) were recently proposed for the session-based recommendation task. The models showed promising improvements over traditional recommendation approaches. In this work, we further study RNN-based models for session-based recommendations. We propose the application of two techniques to improve model performance, namely, data augmentation, and a method to account for shifts in the input data distribution. We also empirically study the use of generalised distillation,...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1606.08117
Arxiv.org
texts

eye 3

favorite 0

comment 0

Efficient evaluation of multi-dimensional range queries in a main-memory database is an important, but difficult task. State-of-the-art techniques rely on optimised sequential scans or tree-based structures. For range queries with small result sets, sequential scans exhibit poor asymptotic performance. Also, as the dimensionality of the data set increases, the performance of tree-based structures degenerates due to the curse of dimensionality. Recent literature proposed the Elf, a main-memory...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1609.01319
Arxiv.org
texts

eye 7

favorite 0

comment 0

We propose a novel unifying scheme for parallel implementation of articulated robot dynamics algorithms. It is based on a unified Lie group notation for deriving the equations of motion of articulated robots, where various well-known forward algorithms differ only by their joint inertia matrix inversion strategies. This new scheme leads to a unified abstraction of state-of-the-art forward dynamics algorithms into combinations of block bi-diagonal and/or block tri-diagonal systems, which may be...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1609.06779
Arxiv.org
by Yonghui Xiao; Yilin Shen; Jinfei Liu; Li Xiong; Hongxia Jin; Xiaofeng Xu
texts

eye 4

favorite 0

comment 0

Hidden Markov model (HMM) has been well studied and extensively used. In this paper, we present DPHMM ({Differentially Private Hidden Markov Model}), an HMM embedded with a private data release mechanism, in which the privacy of the data is protected through a graph. Specifically, we treat every state in Markov model as a node, and use a graph to represent the privacy policy, in which "indistinguishability" between states is denoted by edges between nodes. Due to the temporal...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1609.09172
Arxiv.org
by Majid Khadiv; Sebastien Kleff; Alexander Herzog; S. Ali. A. Moosavian; Stefan Schaal; Ludovic Righetti
texts

eye 3

favorite 0

comment 0

In this paper, a method for stabilizing biped robots stepping by a combination of Divergent Component of Motion (DCM) tracking and step adjustment is proposed. In this method, the DCM trajectory is generated, consistent with the predefined footprints. Furthermore, a swing foot trajectory modification strategy is proposed to adapt the landing point, using DCM measurement. In order to apply the generated trajectories to the full robot, a Hierarchical Inverse Dynamics (HID) is employed. The HID...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1609.09822
Arxiv.org
by Jack W Rae; Jonathan J Hunt; Tim Harley; Ivo Danihelka; Andrew Senior; Greg Wayne; Alex Graves; Timothy P Lillicrap
texts

eye 5

favorite 0

comment 0

Neural networks augmented with external memory have the ability to learn algorithmic solutions to complex tasks. These models appear promising for applications such as language modeling and machine translation. However, they scale poorly in both space and time as the amount of memory grows --- limiting their applicability to real-world domains. Here, we present an end-to-end differentiable memory access scheme, which we call Sparse Access Memory (SAM), that retains the representational power of...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1610.09027
Arxiv.org
by Chuyang Ke; Yan Jin; Heather Evans; Bill Lober; Xiaoning Qian; Ji Liu; Shuai Huang
texts

eye 7

favorite 0

comment 0

Surgical Site Infection (SSI) is a national priority in healthcare research. Much research attention has been attracted to develop better SSI risk prediction models. However, most of the existing SSI risk prediction models are built on static risk factors such as comorbidities and operative factors. In this paper, we investigate the use of the dynamic wound data for SSI risk prediction. There have been emerging mobile health (mHealth) tools that can closely monitor the patients and generate...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1611.04049
Arxiv.org
by Yiwen Tang; Hongzhi Wang; Shiwei Zhang; Huijun Zhang; Ruoxi Shi
texts

eye 4

favorite 0

comment 0

A challenge for data imputation is the lack of knowledge. In this paper, we attempt to address this challenge by involving extra knowledge from web. To achieve high-performance web-based imputation, we use the dependency, i.e.FDs and CFDs, to impute as many as possible values automatically and fill in the other missing values with the minimal access of web, whose cost is relatively large. To make sufficient use of dependencies, We model the dependency set on the data as a graph and perform...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1611.04288
Arxiv.org
by Vaidehi Dalmia; Hongyi Liu; Shih-Fu Chang
texts

eye 4

favorite 0

comment 0

The Multilingual Visual Sentiment Ontology (MVSO) consists of 15,600 concepts in 12 different languages that are strongly related to emotions and sentiments expressed in images. These concepts are defined in the form of Adjective-Noun Pair (ANP), which are crawled and discovered from online image forum Flickr. In this work, we used Amazon Mechanical Turk as a crowd-sourcing platform to collect human judgments on sentiments expressed in images that are uniformly sampled over 3,911 English ANPs...
Topics: Multimedia, Computing Research Repository
Source: http://arxiv.org/abs/1611.04455
Arxiv.org
by Susmita Bhaduri; Dipak Ghosh
texts

eye 8

favorite 0

comment 0

In North-Indian-Music-System(NIMS),tabla is mostly used as percussive accompaniment for vocal-music in polyphonic-compositions. The human auditory system uses perceptual grouping of musical-elements and easily filters the tabla component, thereby decoding prominent rhythmic features like tala, tempo from a polyphonic composition. For Western music, lots of work have been reported for automated drum analysis of polyphonic composition. However, attempts at computational analysis of tala by...
Topics: Sound, Computing Research Repository
Source: http://arxiv.org/abs/1611.05182
Arxiv.org
by Shahab Heshmati-alamdari; Alexandros Nikou; Kostas J. Kyriakopoulos; Dimos V. Dimarogonas
texts

eye 5

favorite 0

comment 0

In various interaction tasks using Underwater Vehicle Manipulator Systems (UVMSs) (e.g. sampling of the sea organisms, underwater welding), important factors such as: i) uncertainties and complexity of UVMS dynamic model ii) external disturbances (e.g. sea currents and waves) iii) imperfection and noises of measuring sensors iv) steady state performance as well as v) inferior overshoot of interaction force error, should be addressed during the force control design. Motivated by the above...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1611.07399
Arxiv.org
by Xiangnan Ren; Houda Khrouf; Zakia Kazi-Aoul; Yousra Chabchoub; Olivier Curé
texts

eye 3

favorite 0

comment 0

To cope with the massive growth of semantic data streams, several RDF Stream Processing (RSP) engines have been implemented. The efficiency of their throughput, latency and memory consumption can be evaluated using available benchmarks such as LSBench and City- Bench. Nevertheless, these benchmarks lack an in-depth performance evaluation as some measurement metrics have not been considered. The main goal of this paper is to analyze the performance of two popular RSP engines, namely C-SPARQL and...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1611.08269
Arxiv.org
texts

eye 6

favorite 0

comment 0

We present an architecture which lets us train deep, directed generative models with many layers of latent variables. We include deterministic paths between all latent variables and the generated output, and provide a richer set of connections between computations for inference and generation, which enables more effective communication of information throughout the model during training. To improve performance on natural images, we incorporate a lightweight autoregressive model in the...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1612.04739
Arxiv.org
texts

eye 6

favorite 0

comment 0

Some glottal analysis approaches based upon linear prediction or complex cepstrum approaches have been proved to be effective to estimate glottal source from real speech utterances. We propose a new approach employing both an all-pole odd-order linear prediction to provide a coarse estimation and phase decomposition based causality/anti-causality separation to generate further refinements. The obtained measures show that this method improved performance in terms of reducing source-filter...
Topics: Sound, Computing Research Repository
Source: http://arxiv.org/abs/1612.04919
Arxiv.org
by Franziska Meier; Stefan Schaal
texts

eye 6

favorite 0

comment 0

Dynamic Movement Primitives have successfully been used to realize imitation learning, trial-and-error learning, reinforce- ment learning, movement recognition and segmentation and control. Because of this they have become a popular represen- tation for motor primitives. In this work, we showcase how DMPs can be reformulated as a probabilistic linear dynamical system with control inputs. Through this probabilistic repre- sentation of DMPs, algorithms such as Kalman filtering and smoothing are...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1612.05932
Arxiv.org
by Kimberly McGuire; Guido de Croon; Christophe De Wagter; Karl Tuyls; Hilbert Kappen
texts

eye 7

favorite 0

comment 0

Miniature Micro Aerial Vehicles (MAV) are very suitable for flying in indoor environments, but autonomous navigation is challenging due to their strict hardware limitations. This paper presents a highly efficient computer vision algorithm called Edge-FS for the determination of velocity and depth. It runs at 20 Hz on a 4 g stereo camera with an embedded STM32F4 microprocessor (168 MHz, 192 kB) and uses feature histograms to calculate optical flow and stereo disparity. The stereo-based distance...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1612.06702
Arxiv.org
by Christopher Schymura; Thomas Walther; Dorothea Kolossa
texts

eye 6

favorite 0

comment 0

This study describes a binaural machine hearing system that is capable of performing auditory stream segregation in scenarios where multiple sound sources are present. The process of stream segregation refers to the capability of human listeners to group acoustic signals into sets of distinct auditory streams, corresponding to individual sound sources. The proposed computational framework mimics this ability via a probabilistic clustering scheme for joint localization and segregation. This...
Topics: Sound, Computing Research Repository
Source: http://arxiv.org/abs/1606.07598
Arxiv.org
by Gaoying Ju; Yongkun Li; Yinlong Xu; Jiqiang Chen; John C. S. Lui
texts

eye 5

favorite 0

comment 0

In recent years, there is an increasing demand of big memory systems so to perform large scale data analytics. Since DRAM memories are expensive, some researchers are suggesting to use other memory systems such as non-volatile memory (NVM) technology to build large-memory computing systems. However, whether the NVM technology can be a viable alternative (either economically and technically) to DRAM remains an open question. To answer this question, it is important to consider how to design a...
Topics: Performance, Computing Research Repository
Source: http://arxiv.org/abs/1607.00714
Arxiv.org
by Maani Ghaffari Jadidi; Jaime Valls Miro; Gamini Dissanayake
texts

eye 3

favorite 0

comment 0

In this article, we propose a sampling-based motion planning algorithm equipped with an information-theoretic convergence criterion for incremental informative motion planning. The proposed approach allows dense map representations and incorporates the full state uncertainty into the planning process. The problem is formulated as a maximization problem with a budget constraint. Our approach is built on rapidly-exploring information gathering algorithms and benefits from advantages of...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1607.01883
Arxiv.org
texts

eye 5

favorite 0

comment 0

The traditional frequent pattern mining algorithms generate an exponentially large number of patterns of which a substantial proportion are not much significant for many data analysis endeavors. Discovery of a small number of personalized interesting patterns from the large output set according to a particular user's interest is an important as well as challenging task. Existing works on pattern summarization do not solve this problem from the personalization viewpoint. In this work, we propose...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1607.05749
Arxiv.org
by Timothy La Fond; Jennifer Neville; Brian Gallagher
texts

eye 4

favorite 0

comment 0

An important task in network analysis is the detection of anomalous events in a network time series. These events could merely be times of interest in the network timeline or they could be examples of malicious activity or network malfunction. Hypothesis testing using network statistics to summarize the behavior of the network provides a robust framework for the anomaly detection decision process. Unfortunately, choosing network statistics that are dependent on confounding factors like the...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1608.00712
Arxiv.org
by Ritambhara Singh; Jack Lanchantin; Gabriel Robins; Yanjun Qi
texts

eye 4

favorite 0

comment 0

Through sequence-based classification, this paper tries to accurately predict the DNA binding sites of transcription factors (TFs) in an unannotated cellular context. Related methods in the literature fail to perform such predictions accurately, since they do not consider sample distribution shift of sequence segments from an annotated (source) context to an unannotated (target) context. We, therefore, propose a method called "Transfer String Kernel" (TSK) that achieves improved...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1609.03490
Arxiv.org
by Stefan Gladisch; Valerius Weigandt; Heidrun Schumann; Christian Tominski
texts

eye 5

favorite 0

comment 0

The EditLens is an interactive lens technique that supports the editing of graphs. The user can insert, update, or delete nodes and edges while maintaining an already existing layout of the graph. For the nodes and edges that are affected by an edit operation, the EditLens suggests suitable locations and routes, which the user can accept or adjust. For this purpose, the EditLens requires an efficient routing algorithm that can compute results at interactive framerates. Existing algorithms...
Topics: Graphics, Computing Research Repository
Source: http://arxiv.org/abs/1612.05064
Arxiv.org
by Nauman Shahid; Nathanael Perraudin; Gilles Puy; Pierre Vandergheynst
texts

eye 3

favorite 0

comment 0

We introduce a novel framework for an approxi- mate recovery of data matrices which are low-rank on graphs, from sampled measurements. The rows and columns of such matrices belong to the span of the first few eigenvectors of the graphs constructed between their rows and columns. We leverage this property to recover the non-linear low-rank structures efficiently from sampled data measurements, with a low cost (linear in n). First, a Resrtricted Isometry Property (RIP) condition is introduced for...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1602.02070
Arxiv.org
texts

eye 8

favorite 0

comment 0

This paper presents a first contribution to the design of a small aerial robot for inhabited microgravity environments, such as orbiting space stations. In particular, we target a fleet of robots for collaborative tasks with humans, such as telepresence and cooperative mobile manipulation. We explore a propeller based propulsion system, arranged in such a way that the translational and the rotational components can be decoupled, resulting in an holonomic hexarotor. Since propellers have limited...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1602.03573
Arxiv.org
texts

eye 5

favorite 0

comment 0

We use random geometric graphs to describe clusters of higher dimensional data points which are bijectively mapped to a (possibly) lower dimensional space where an equivalent random cluster model is used to calculate the expected number of modes to be found when separating the data of a multi-modal data set into distinct clusters. Furthermore, as a function of the expected number of modes and the number of data points in the sample, an upper bound on a given distance measure is found such that...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1602.03822
Arxiv.org
by Sabri Pllana; Ivan Janciak; Peter Brezany; Alexander Wöhrer
texts

eye 6

favorite 0

comment 0

The major aim of this survey is to identify the strengths and weaknesses of a representative set of Data-Mining and Integration (DMI) query languages. We describe a set of properties of DMI-related languages that we use for a systematic evaluation of these languages. In addition, we introduce a scoring system that we use to quantify our opinion on how well a DMI-related language supports a property. The languages surveyed in this paper include: DMQL, MineSQL, MSQL, M2MQL, dmFSQL, OLEDB for DM,...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1603.01113
Arxiv.org
by Roberto L. Shinmoto Torres; Damith C. Ranasinghe; Qinfeng Shi; Anton van den Hengel
texts

eye 3

favorite 0

comment 0

The present study introduces a method for improving the classification performance of imbalanced multiclass data streams from wireless body worn sensors. Data imbalance is an inherent problem in activity recognition caused by the irregular time distribution of activities, which are sequential and dependent on previous movements. We use conditional random fields (CRF), a graphical model for structured classification, to take advantage of dependencies between activities in a sequence. However,...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1603.03627
Arxiv.org
by Weiran Wang; Raman Arora; Karen Livescu; Jeff Bilmes
texts

eye 5

favorite 0

comment 0

We consider learning representations (features) in the setting in which we have access to multiple unlabeled views of the data for learning while only one view is available for downstream tasks. Previous work on this problem has proposed several techniques based on deep neural networks, typically involving either autoencoder-like networks with a reconstruction objective or paired feedforward networks with a batch-style correlation-based objective. We analyze several techniques based on prior...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1602.01024
Arxiv.org
by Erik Cambria; Tam V. Nguyen; Brian Cheng; Kenneth Kwok; Jose Sepulveda
texts

eye 11

favorite 0

comment 0

Commonsense knowledge representation and reasoning is key for tasks such as artificial intelligence and natural language understanding. Since commonsense consists of information that humans take for granted, gathering it is an extremely difficult task. In this paper, we introduce a novel 3D game engine for commonsense knowledge acquisition (GECKA3D) which aims to collect commonsense from game designers through the development of serious games. GECKA3D integrates the potential of serious games...
Topics: Multimedia, Computing Research Repository
Source: http://arxiv.org/abs/1602.01178
Arxiv.org
by H. W. Ho; G. C. H. E. de Croon; E. van Kampen; Q. P. Chu; M. Mulder
texts

eye 8

favorite 0

comment 0

Bio-inspired methods can provide efficient solutions to perform autonomous landing for Micro Air Vehicles (MAVs). Flying insects such as honeybees perform vertical landings by keeping flow divergence constant. This leads to an exponential decay of both height and vertical velocity, and allows for smooth and safe landings. However, the presence of noise and delay in obtaining flow divergence estimates will cause instability of the landing when the control gains are not adapted to the height. In...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1609.06767
Arxiv.org
by Gregory Kahn; Tianhao Zhang; Sergey Levine; Pieter Abbeel
texts

eye 5

favorite 0

comment 0

Policy search can in principle acquire complex strategies for control of robots and other autonomous systems. When the policy is trained to process raw sensory inputs, such as images and depth maps, it can also acquire a strategy that combines perception and control. However, effectively processing such complex inputs requires an expressive policy class, such as a large neural network. These high-dimensional policies are difficult to train, especially when learning to control safety-critical...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1603.00622
Arxiv.org
by Galit Bary-Weisberg; Amit Daniely; Shai Shalev-Shwartz
texts

eye 4

favorite 0

comment 0

The model of learning with \emph{local membership queries} interpolates between the PAC model and the membership queries model by allowing the learner to query the label of any example that is similar to an example in the training set. This model, recently proposed and studied by Awasthi, Feldman and Kanade, aims to facilitate practical use of membership queries. We continue this line of work, proving both positive and negative results in the {\em distribution free} setting. We restrict to the...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1603.03714
Arxiv.org
by Prasenjit Karmakar; Rajkumar Maity; Shalabh Bhatnagar
texts

eye 10

favorite 0

comment 0

In this paper we provide a rigorous convergence analysis of a "off"-policy temporal difference learning algorithm with linear function approximation and per time-step linear computational complexity in "online" learning environment. The algorithm considered here is TDC with importance weighting introduced by Maei et al. We support our theoretical results by providing suitable empirical results for standard off-policy counterexamples.
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1605.06076
Arxiv.org
by Christian Walder
texts

eye 8

favorite 0

comment 0

In this paper, we consider the problem of probabilistically modelling symbolic music data. We introduce a representation which reduces polyphonic music to a univariate categorical sequence. In this way, we are able to apply state of the art natural language processing techniques, namely the long short-term memory sequence model. The representation we employ permits arbitrary rhythmic structure, which we assume to be given. We show that our model is effective on four out of four piano roll based...
Topics: Sound, Computing Research Repository
Source: http://arxiv.org/abs/1606.01368
Arxiv.org
by Shiva Shahrokhi; Arun Mahadev; Aaron T. Becker
texts

eye 6

favorite 0

comment 0

Consider a swarm of particles controlled by global inputs. This paper presents algorithms for shaping such swarms in 2D using boundary walls. The range of configurations created by conforming a swarm to a boundary wall is limited. We describe the set of stable configurations of a swarm in two canonical workspaces, a circle and a square. To increase the diversity of configurations, we add boundary interaction to our model. We provide algorithms using friction with walls to place two robots at...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1609.01830
Arxiv.org
by Wentao Wu; Jeffrey F. Naughton; Harneet Singh
texts

eye 5

favorite 0

comment 0

Despite of decades of work, query optimizers still make mistakes on "difficult" queries because of bad cardinality estimates, often due to the interaction of multiple predicates and correlations in the data. In this paper, we propose a low-cost post-processing step that can take a plan produced by the optimizer, detect when it is likely to have made such a mistake, and take steps to fix it. Specifically, our solution is a sampling-based iterative procedure that requires almost no...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1601.05748
Arxiv.org
by Karol Hausman; James Preiss; Gaurav Sukhatme; Stephan Weiss
texts

eye 4

favorite 0

comment 0

We study the nonlinear observability of a systems states in view of how well they are observable and what control inputs would improve the convergence of their estimates. We use these insights to develop an observability-aware trajectory-optimization framework for nonlinear systems that produces trajectories well suited for self-calibration. Common trajectory-planning algorithms tend to generate motions that lead to an unobservable subspace of the system state, causing suboptimal state...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1604.07905
Arxiv.org
by Xiangjun Qian; Florent Altché; Arnaud de La Fortelle; Fabien Moutarde
texts

eye 8

favorite 0

comment 0

This work presents a novel framework for the formation control of multiple autonomous ground vehicles in an on-road environment. Unique challenges of this problem lie in 1) the design of collision avoidance strategies with obstacles and with other vehicles in a highly structured environment, 2) dynamic reconfiguration of the formation to handle different task specifications. In this paper, we design a local MPC-based tracking controller for each individual vehicle to follow a reference...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1605.00026
Arxiv.org
by Zakaria Ye; Rachid El-Azouzi; Tania Jimenez; Eitan Altman; Stefan Valentin
texts

eye 6

favorite 0

comment 0

Although HTTP-based video streaming can easily penetrate firewalls and profit from Web caches, the underlying TCP may introduce large delays in case of a sudden capacity loss. To avoid an interruption of the video stream in such cases we propose the Backward-Shifted Coding (BSC). Based on Scalable Video Coding (SVC), BSC adds a time-shifted layer of redundancy to the video stream such that future frames are downloaded at any instant. This pre-fetched content maintains a fluent video stream even...
Topics: Multimedia, Computing Research Repository
Source: http://arxiv.org/abs/1605.03815
Arxiv.org
by Neha V. Karanjkar; Madhav P. Desai
texts

eye 5

favorite 0

comment 0

In simulation-based optimization of queuing systems, the presence of discrete-valued parameters (such as buffer sizes and the number of servers) makes the optimization difficult. We propose a novel technique for embedding such discrete parameters into a continuous space, so that optimization can be performed efficiently using continuous-space methods. Unlike spatial interpolation, our embedding technique is based on a randomization of the simulation model. The interpolated value can be computed...
Topics: Performance, Computing Research Repository
Source: http://arxiv.org/abs/1606.02900
Arxiv.org
by Daniel Hein; Alexander Hentschel; Volkmar Sterzing; Michel Tokic; Steffen Udluft
texts

eye 5

favorite 0

comment 0

A novel reinforcement learning benchmark, called Industrial Benchmark, is introduced. The Industrial Benchmark aims at being be realistic in the sense, that it includes a variety of aspects that we found to be vital in industrial applications. It is not designed to be an approximation of any real system, but to pose the same hardness and complexity.
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1610.03793
Arxiv.org
by Bin Gu; Zhouyuan Huo; Heng Huang
texts

eye 5

favorite 0

comment 0

Zeroth-order (derivative-free) optimization attracts a lot of attention in machine learning, because explicit gradient calculations may be computationally expensive or infeasible. To handle large scale problems both in volume and dimension, recently asynchronous doubly stochastic zeroth-order algorithms were proposed. The convergence rate of existing asynchronous doubly stochastic zeroth order algorithms is $O(\frac{1}{\sqrt{T}})$ (also for the sequential stochastic zeroth-order optimization...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1612.01425
Arxiv.org
by Amir Shaikhha; Yannis Klonatos; Christoph Koch
texts

eye 5

favorite 0

comment 0

Abstraction without regret refers to the vision of using high-level programming languages for systems development without experiencing a negative impact on performance. A database system designed according to this vision offers both increased productivity and high performance, instead of sacrificing the former for the latter as is the case with existing, monolithic implementations that are hard to maintain and extend. In this article, we realize this vision in the domain of analytical query...
Topics: Databases, Computing Research Repository
Source: http://arxiv.org/abs/1612.05566
Arxiv.org
by Changsheng Li; Fan Wei; Junchi Yan; Weishan Dong; Qingshan Liu; Xiaoyu Zhang; Hongyuan Zha
texts

eye 8

favorite 0

comment 0

In this paper, we propose a novel multi-label learning framework, called Multi-Label Self-Paced Learning (MLSPL), in an attempt to incorporate the self-paced learning strategy into multi-label learning regime. In light of the benefits of adopting the easy-to-hard strategy proposed by self-paced learning, the devised MLSPL aims to learn multiple labels jointly by gradually including label learning tasks and instances into model training from the easy to the hard. We first introduce a self-paced...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1603.06708
Arxiv.org
by Raviteja Upadrashta; Tarun Choubisa; A. Praneeth; Tony G.; Aswath V. S.; P. Vijay Kumar; Sripad Kowshik; Hari Prasad Gokul R; T. V. Prabhakar
texts

eye 6

favorite 0

comment 0

This paper presents the development of a passive infra-red sensor tower platform along with a classification algorithm to distinguish between human intrusion, animal intrusion and clutter arising from wind-blown vegetative movement in an outdoor environment. The research was aimed at exploring the potential use of wireless sensor networks as an early-warning system to help mitigate human-wildlife conflicts occurring at the edge of a forest. There are three important features to the development....
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1604.03829
Arxiv.org
by Lantao Liu; Gaurav S. Sukhatme
texts

eye 7

favorite 0

comment 0

We consider a decision-making problem where the environment varies both in space and time. Such problems arise naturally when considering e.g., the navigation of an underwater robot amidst ocean currents or the navigation of an aerial vehicle in wind. To model such spatiotemporal variation, we extend the standard Markov Decision Process (MDP) to a new framework called the Time-Varying Markov Decision Process (TVMDP). The TVMDP has a time-varying state transition model and transforms the...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1605.01018
Arxiv.org
by Adam Santoro; Sergey Bartunov; Matthew Botvinick; Daan Wierstra; Timothy Lillicrap
texts

eye 8

favorite 0

comment 0

Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning." Traditional gradient-based networks require a lot of data to learn, often through extensive iterative training. When new data is encountered, the models must inefficiently relearn their parameters to adequately incorporate the new information without catastrophic interference. Architectures with augmented memory capacities, such as...
Topics: Computing Research Repository, Learning
Source: http://arxiv.org/abs/1605.06065
Arxiv.org
by Anirudh Vemula; Katharina Muelling; Jean Oh
texts

eye 6

favorite 0

comment 0

Path planning in the presence of dynamic obstacles is a challenging problem due to the added time dimension in search space. In approaches that ignore the time dimension and treat dynamic obstacles as static, frequent re-planning is unavoidable as the obstacles move, and their solutions are generally sub-optimal and can be incomplete. To achieve both optimality and completeness, it is necessary to consider the time dimension during planning. The notion of adaptive dimensionality has been...
Topics: Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1605.06853