July 28, 2019

2838 words 14 mins read

Paper Group ANR 239

Intelligent Subset Selection of Power Generators for Economic Dispatch. 4d isip: 4d implicit surface interest point detection. Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning. Isomorphism between Differential and Moment Invariants under Affine Transform. Using Global Constraints and Reranking to Improve Cogna …

Intelligent Subset Selection of Power Generators for Economic Dispatch


Title	Intelligent Subset Selection of Power Generators for Economic Dispatch
Authors	Biswarup Bhattacharya, Abhishek Sinha
Abstract	Sustainable and economical generation of electrical power is an essential and mandatory component of infrastructure in today’s world. Optimal generation (generator subset selection) of power requires a careful evaluation of various factors like type of source, generation, transmission & storage capacities, congestion among others which makes this a difficult task. We created a grid to simulate various conditions including stimuli like generator supply, weather and load demand using Siemens PSS/E software and this data is trained using deep learning methods and subsequently tested. The results are highly encouraging. As per our knowledge, this is the first paper to propose a working and scalable deep learning model for this problem.
Tasks
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02513v1
PDF	http://arxiv.org/pdf/1709.02513v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-subset-selection-of-power
Repo
Framework

4d isip: 4d implicit surface interest point detection


Title	4d isip: 4d implicit surface interest point detection
Authors	Shirui Li, Alper Yilmaz, Changlin Xiao, Hua Li
Abstract	In this paper, we propose a new method to detect 4D spatiotemporal interest points though an implicit surface, we refer to as the 4D-ISIP. We use a 3D volume which has a truncated signed distance function(TSDF) for every voxel to represent our 3D object model. The TSDF represents the distance between the spatial points and object surface points which is an implicit surface representation. Our novelty is to detect the points where the local neighborhood has significant variations along both spatial and temporal directions. We established a system to acquire 3D human motion dataset using only one Kinect. Experimental results show that our method can detect 4D-ISIP for different human actions.
Tasks	Interest Point Detection
Published	2017-05-10
URL	http://arxiv.org/abs/1705.03634v2
PDF	http://arxiv.org/pdf/1705.03634v2.pdf
PWC	https://paperswithcode.com/paper/4d-isip-4d-implicit-surface-interest-point
Repo
Framework

Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning


Title	Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning
Authors	Matthew Riemer, Elham Khabiri, Richard Goodwin
Abstract	Although neural networks are well suited for sequential transfer learning tasks, the catastrophic forgetting problem hinders proper integration of prior knowledge. In this work, we propose a solution to this problem by using a multi-task objective based on the idea of distillation and a mechanism that directly penalizes forgetting at the shared representation layer during the knowledge integration phase of training. We demonstrate our approach on a Twitter domain sentiment analysis task with sequential knowledge transfer from four related tasks. We show that our technique outperforms networks fine-tuned to the target task. Additionally, we show both through empirical evidence and examples that it does not forget useful knowledge from the source task that is forgotten during standard fine-tuning. Surprisingly, we find that first distilling a human made rule based sentiment engine into a recurrent neural network and then integrating the knowledge with the target task data leads to a substantial gain in generalization performance. Our experiments demonstrate the power of multi-source transfer techniques in practical text analytics problems when paired with distillation. In particular, for the SemEval 2016 Task 4 Subtask A (Nakov et al., 2016) dataset we surpass the state of the art established during the competition with a comparatively simple model architecture that is not even competitive when trained on only the labeled task specific data.
Tasks	Sentiment Analysis, Transfer Learning
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03617v1
PDF	http://arxiv.org/pdf/1704.03617v1.pdf
PWC	https://paperswithcode.com/paper/representation-stability-as-a-regularizer-for
Repo
Framework

Isomorphism between Differential and Moment Invariants under Affine Transform


Title	Isomorphism between Differential and Moment Invariants under Affine Transform
Authors	Erbo Li, Hua Li
Abstract	The invariant is one of central topics in science, technology and engineering. The differential invariant is essential in understanding or describing some important phenomena or procedures in mathematics, physics, chemistry, biology or computer science etc. The derivation of differential invariants is usually difficult or complicated. This paper reports a discovery that under the affine transform, differential invariants have similar structures with moment invariants up to a scalar function of transform parameters. If moment invariants are known, relative differential invariants can be obtained by the substitution of moments by derivatives with the same order. Whereas moment invariants can be calculated by multiple integrals, this method provides a simple way to derive differential invariants without the need to resolve any equation system. Since the definition of moments on different manifolds or in different dimension of spaces is well established, differential invariants on or in them will also be well defined. Considering that moments have a strong background in mathematics and physics, this technique offers a new view angle to the inner structure of invariants. Projective differential invariants can also be found in this way with a screening process.
Tasks
Published	2017-05-20
URL	http://arxiv.org/abs/1705.08264v2
PDF	http://arxiv.org/pdf/1705.08264v2.pdf
PWC	https://paperswithcode.com/paper/isomorphism-between-differential-and-moment
Repo
Framework

Using Global Constraints and Reranking to Improve Cognates Detection


Title	Using Global Constraints and Reranking to Improve Cognates Detection
Authors	Michael Bloodgood, Benjamin Strauss
Abstract	Global constraints and reranking have not been used in cognates detection research to date. We propose methods for using global constraints by performing rescoring of the score matrices produced by state of the art cognates detection systems. Using global constraints to perform rescoring is complementary to state of the art methods for performing cognates detection and results in significant performance improvements beyond current state of the art performance on publicly available datasets with different language pairs and various conditions such as different levels of baseline state of the art performance and different data size conditions, including with more realistic large data size conditions than have been evaluated with in the past.
Tasks
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07050v2
PDF	http://arxiv.org/pdf/1704.07050v2.pdf
PWC	https://paperswithcode.com/paper/using-global-constraints-and-reranking-to
Repo
Framework

Laplacian Prior Variational Automatic Relevance Determination for Transmission Tomography


Title	Laplacian Prior Variational Automatic Relevance Determination for Transmission Tomography
Authors	Jingwei Lu, David G. Politte, Joseph A. O’Sullivan
Abstract	In the classic sparsity-driven problems, the fundamental L-1 penalty method has been shown to have good performance in reconstructing signals for a wide range of problems. However this performance relies on a good choice of penalty weight which is often found from empirical experiments. We propose an algorithm called the Laplacian variational automatic relevance determination (Lap-VARD) that takes this penalty weight as a parameter of a prior Laplace distribution. Optimization of this parameter using an automatic relevance determination framework results in a balance between the sparsity and accuracy of signal reconstruction. Our algorithm is implemented in a transmission tomography model with sparsity constraint in wavelet domain.
Tasks
Published	2017-10-26
URL	http://arxiv.org/abs/1710.09522v1
PDF	http://arxiv.org/pdf/1710.09522v1.pdf
PWC	https://paperswithcode.com/paper/laplacian-prior-variational-automatic
Repo
Framework

Multi-Robot Active Information Gathering with Periodic Communication


Title	Multi-Robot Active Information Gathering with Periodic Communication
Authors	Mikko Lauri, Eero Heinänen, Simone Frintrop
Abstract	A team of robots sharing a common goal can benefit from coordination of the activities of team members, helping the team to reach the goal more reliably or quickly. We address the problem of coordinating the actions of a team of robots with periodic communication capability executing an information gathering task. We cast the problem as a multi-agent optimal decision-making problem with an information theoretic objective function. We show that appropriate techniques for solving decentralized partially observable Markov decision processes (Dec-POMDPs) are applicable in such information gathering problems. We quantify the usefulness of coordinated information gathering through simulation studies, and demonstrate the feasibility of the method in a real-world target tracking domain.
Tasks	Decision Making
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02610v1
PDF	http://arxiv.org/pdf/1703.02610v1.pdf
PWC	https://paperswithcode.com/paper/multi-robot-active-information-gathering-with
Repo
Framework

Spectrum Access In Cognitive Radio Using A Two Stage Reinforcement Learning Approach


Title	Spectrum Access In Cognitive Radio Using A Two Stage Reinforcement Learning Approach
Authors	Vishnu Raj, Irene Dias, Thulasi Tholeti, Sheetal Kalyani
Abstract	With the advent of the 5th generation of wireless standards and an increasing demand for higher throughput, methods to improve the spectral efficiency of wireless systems have become very important. In the context of cognitive radio, a substantial increase in throughput is possible if the secondary user can make smart decisions regarding which channel to sense and when or how often to sense. Here, we propose an algorithm to not only select a channel for data transmission but also to predict how long the channel will remain unoccupied so that the time spent on channel sensing can be minimized. Our algorithm learns in two stages - a reinforcement learning approach for channel selection and a Bayesian approach to determine the optimal duration for which sensing can be skipped. Comparisons with other learning methods are provided through extensive simulations. We show that the number of sensing is minimized with negligible increase in primary interference; this implies that lesser energy is spent by the secondary user in sensing and also higher throughput is achieved by saving on sensing.
Tasks
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09792v1
PDF	http://arxiv.org/pdf/1707.09792v1.pdf
PWC	https://paperswithcode.com/paper/spectrum-access-in-cognitive-radio-using-a
Repo
Framework

Efficient Estimation of Generalization Error and Bias-Variance Components of Ensembles


Title	Efficient Estimation of Generalization Error and Bias-Variance Components of Ensembles
Authors	Dhruv Mahajan, Vivek Gupta, S Sathiya Keerthi, Sellamanickam Sundararajan, Shravan Narayanamurthy, Rahul Kidambi
Abstract	For many applications, an ensemble of base classifiers is an effective solution. The tuning of its parameters(number of classes, amount of data on which each classifier is to be trained on, etc.) requires G, the generalization error of a given ensemble. The efficient estimation of G is the focus of this paper. The key idea is to approximate the variance of the class scores/probabilities of the base classifiers over the randomness imposed by the training subset by normal/beta distribution at each point x in the input feature space. We estimate the parameters of the distribution using a small set of randomly chosen base classifiers and use those parameters to give efficient estimation schemes for G. We give empirical evidence for the quality of the various estimators. We also demonstrate their usefulness in making design choices such as the number of classifiers in the ensemble and the size of a subset of data used for training that is needed to achieve a certain value of generalization error. Our approach also has great potential for designing distributed ensemble classifiers.
Tasks
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05482v1
PDF	http://arxiv.org/pdf/1711.05482v1.pdf
PWC	https://paperswithcode.com/paper/efficient-estimation-of-generalization-error
Repo
Framework

Saccade Sequence Prediction: Beyond Static Saliency Maps


Title	Saccade Sequence Prediction: Beyond Static Saliency Maps
Authors	Calden Wloka, Iuliia Kotseruba, John K. Tsotsos
Abstract	Visual attention is a field with a considerable history, with eye movement control and prediction forming an important subfield. Fixation modeling in the past decades has been largely dominated computationally by a number of highly influential bottom-up saliency models, such as the Itti-Koch-Niebur model. The accuracy of such models has dramatically increased recently due to deep learning. However, on static images the emphasis of these models has largely been based on non-ordered prediction of fixations through a saliency map. Very few implemented models can generate temporally ordered human-like sequences of saccades beyond an initial fixation point. Towards addressing these shortcomings we present STAR-FC, a novel multi-saccade generator based on a central/peripheral integration of deep learning-based saliency and lower-level feature-based saliency. We have evaluated our model using the CAT2000 database, successfully predicting human patterns of fixation with equivalent accuracy and quality compared to what can be achieved by using one human sequence to predict another. This is a significant improvement over fixation sequences predicted by state-of-the-art saliency algorithms.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10959v1
PDF	http://arxiv.org/pdf/1711.10959v1.pdf
PWC	https://paperswithcode.com/paper/saccade-sequence-prediction-beyond-static
Repo
Framework

Image Inpainting for High-Resolution Textures using CNN Texture Synthesis


Title	Image Inpainting for High-Resolution Textures using CNN Texture Synthesis
Authors	Pascal Laube, Michael Grunwald, Matthias O. Franz, Georg Umlauf
Abstract	Deep neural networks have been successfully applied to problems such as image segmentation, image super-resolution, coloration and image inpainting. In this work we propose the use of convolutional neural networks (CNN) for image inpainting of large regions in high-resolution textures. Due to limited computational resources processing high-resolution images with neural networks is still an open problem. Existing methods separate inpainting of global structure and the transfer of details, which leads to blurry results and loss of global coherence in the detail transfer step. Based on advances in texture synthesis using CNNs we propose patch-based image inpainting by a CNN that is able to optimize for global as well as detail texture statistics. Our method is capable of filling large inpainting regions, oftentimes exceeding the quality of comparable methods for high-resolution images. For reference patch look-up we propose to use the same summary statistics that are used in the inpainting process.
Tasks	Image Inpainting, Image Super-Resolution, Semantic Segmentation, Super-Resolution, Texture Synthesis
Published	2017-12-08
URL	http://arxiv.org/abs/1712.03111v2
PDF	http://arxiv.org/pdf/1712.03111v2.pdf
PWC	https://paperswithcode.com/paper/image-inpainting-for-high-resolution-textures
Repo
Framework

First-order Methods Almost Always Avoid Saddle Points


Title	First-order Methods Almost Always Avoid Saddle Points
Authors	Jason D. Lee, Ioannis Panageas, Georgios Piliouras, Max Simchowitz, Michael I. Jordan, Benjamin Recht
Abstract	We establish that first-order methods avoid saddle points for almost all initializations. Our results apply to a wide variety of first-order methods, including gradient descent, block coordinate descent, mirror descent and variants thereof. The connecting thread is that such algorithms can be studied from a dynamical systems perspective in which appropriate instantiations of the Stable Manifold Theorem allow for a global stability analysis. Thus, neither access to second-order derivative information nor randomness beyond initialization is necessary to provably avoid saddle points.
Tasks
Published	2017-10-20
URL	http://arxiv.org/abs/1710.07406v1
PDF	http://arxiv.org/pdf/1710.07406v1.pdf
PWC	https://paperswithcode.com/paper/first-order-methods-almost-always-avoid
Repo
Framework

Dense Piecewise Planar RGB-D SLAM for Indoor Environments


Title	Dense Piecewise Planar RGB-D SLAM for Indoor Environments
Authors	Phi-Hung Le, Jana Kosecka
Abstract	The paper exploits weak Manhattan constraints to parse the structure of indoor environments from RGB-D video sequences in an online setting. We extend the previous approach for single view parsing of indoor scenes to video sequences and formulate the problem of recovering the floor plan of the environment as an optimal labeling problem solved using dynamic programming. The temporal continuity is enforced in a recursive setting, where labeling from previous frames is used as a prior term in the objective function. In addition to recovery of piecewise planar weak Manhattan structure of the extended environment, the orthogonality constraints are also exploited by visual odometry and pose graph optimization. This yields reliable estimates in the presence of large motions and absence of distinctive features to track. We evaluate our method on several challenging indoors sequences demonstrating accurate SLAM and dense mapping of low texture environments. On existing TUM benchmark we achieve competitive results with the alternative approaches which fail in our environments.
Tasks	Visual Odometry
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00514v1
PDF	http://arxiv.org/pdf/1708.00514v1.pdf
PWC	https://paperswithcode.com/paper/dense-piecewise-planar-rgb-d-slam-for-indoor
Repo
Framework

Doctoral Advisor or Medical Condition: Towards Entity-specific Rankings of Knowledge Base Properties [Extended Version]


Title	Doctoral Advisor or Medical Condition: Towards Entity-specific Rankings of Knowledge Base Properties [Extended Version]
Authors	Simon Razniewski, Vevake Balaraman, Werner Nutt
Abstract	In knowledge bases such as Wikidata, it is possible to assert a large set of properties for entities, ranging from generic ones such as name and place of birth to highly profession-specific or background-specific ones such as doctoral advisor or medical condition. Determining a preference or ranking in this large set is a challenge in tasks such as prioritisation of edits or natural-language generation. Most previous approaches to ranking knowledge base properties are purely data-driven, that is, as we show, mistake frequency for interestingness. In this work, we have developed a human-annotated dataset of 350 preference judgments among pairs of knowledge base properties for fixed entities. From this set, we isolate a subset of pairs for which humans show a high level of agreement (87.5% on average). We show, however, that baseline and state-of-the-art techniques achieve only 61.3% precision in predicting human preferences for this subset. We then analyze what contributes to one property being rated as more important than another one, and identify that at least three factors play a role, namely (i) general frequency, (ii) applicability to similar entities and (iii) semantic similarity between property and entity. We experimentally analyze the contribution of each factor and show that a combination of techniques addressing all the three factors achieves 74% precision on the task. The dataset is available at www.kaggle.com/srazniewski/wikidatapropertyranking.
Tasks	Semantic Similarity, Semantic Textual Similarity, Text Generation
Published	2017-09-20
URL	http://arxiv.org/abs/1709.06907v1
PDF	http://arxiv.org/pdf/1709.06907v1.pdf
PWC	https://paperswithcode.com/paper/doctoral-advisor-or-medical-condition-towards
Repo
Framework

DICOD: Distributed Convolutional Sparse Coding


Title	DICOD: Distributed Convolutional Sparse Coding
Authors	Thomas Moreau, Laurent Oudre, Nicolas Vayatis
Abstract	In this paper, we introduce DICOD, a convolutional sparse coding algorithm which builds shift invariant representations for long signals. This algorithm is designed to run in a distributed setting, with local message passing, making it communication efficient. It is based on coordinate descent and uses locally greedy updates which accelerate the resolution compared to greedy coordinate selection. We prove the convergence of this algorithm and highlight its computational speed-up which is super-linear in the number of cores used. We also provide empirical evidence for the acceleration properties of our algorithm compared to state-of-the-art methods.
Tasks
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10087v2
PDF	http://arxiv.org/pdf/1705.10087v2.pdf
PWC	https://paperswithcode.com/paper/dicod-distributed-convolutional-sparse-coding
Repo
Framework