PyTorchKR Papers

최신 논문

총 3,383편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1402.0556

Generating Extractive Summaries of Scientific Paradigms

Researchers and scientists increasingly find themselves in the position of having to quickly understand large amounts of technical material. Our goal is to effectively serve this need by using bibliometric text mining and summarization techniques to generate summaries of scientific literature. We show how we can use citations to produce automatically generated, readily consumable, technical extractive summaries. We first propose C-LexRank, a model for summarizing single scientific articles based on citations, which employs community detection and extracts salient information-rich sentences. Next, we further extend our experiments to summarize a set of papers, which cover the same scientific topic. We generate extractive summaries of a set of Question Answering (QA) and Dependency Parsing (DP) papers, their abstracts, and their citation sentences and show that citations have unique information amenable to creating a summary.

arXiv:1312.5869

Principled Non-Linear Feature Selection

Recent non-linear feature selection approaches employing greedy optimisation of Centred Kernel Target Alignment(KTA) exhibit strong results in terms of generalisation accuracy and sparsity. However, they are computationally prohibitive for large datasets. We propose randSel, a randomised feature selection algorithm, with attractive scaling properties. Our theoretical analysis of randSel provides strong probabilistic guarantees for correct identification of relevant features. RandSel's characteristics make it an ideal candidate for identifying informative learned representations. We've conducted experimentation to establish the performance of this approach, and present encouraging results, including a 3rd position result in the recent ICML black box learning challenge as well as competitive results for signal peptide prediction, an important problem in bioinformatics.

arXiv:1402.5708

The Cerebellum: New Computational Model that Reveals its Primary Function to Calculate Multibody Dynamics Conform to Lagrange-Euler Formulation

Cerebellum is part of the brain that occupies only 10% of the brain volume, but it contains about 80% of total number of brain neurons. New cerebellar function model is developed that sets cerebellar circuits in context of multibody dynamics model computations, as important step in controlling balance and movement coordination, functions performed by two oldest parts of the cerebellum. Model gives new functional interpretation for granule cells-Golgi cell circuit, including distinct function for upper and lower Golgi cell dendritc trees, and resolves issue of sharing Granule cells between Purkinje cells. Sets new function for basket cells, and for stellate cells according to position in molecular layer. New model enables easily and direct integration of sensory information from vestibular system and cutaneous mechanoreceptors, for balance, movement and interaction with environments. Model gives explanation of Purkinje cells convergence on deep-cerebellar nuclei.

arXiv:1403.0778

Dynamic Move Chains -- a Forward Pruning Approach to Tree Search in Computer Chess

This paper proposes a new mechanism for pruning a search game-tree in computer chess. The algorithm stores and then reuses chains or sequences of moves, built up from previous searches. These move sequences have a built-in forward-pruning mechanism that can radically reduce the search space. A typical search process might retrieve a move from a Transposition Table, where the decision of what move to retrieve would be based on the position itself. This algorithm stores move sequences based on what previous sequences were better, or caused cutoffs. This is therefore position independent and so it could also be useful in games with imperfect information or uncertainty, where the whole situation is not known at any one time. Over a small set of tests, the algorithm was shown to clearly out-perform Transposition Tables, both in terms of search reduction and game-play results.

arXiv:1402.2016

Leveraging Long-Term Predictions and Online-Learning in Agent-based Multiple Person Tracking

We present a multiple-person tracking algorithm, based on combining particle filters and RVO, an agent-based crowd model that infers collision-free velocities so as to predict pedestrian's motion. In addition to position and velocity, our tracking algorithm can estimate the internal goals (desired destination or desired velocity) of the tracked pedestrian in an online manner, thus removing the need to specify this information beforehand. Furthermore, we leverage the longer-term predictions of RVO by deriving a higher-order particle filter, which aggregates multiple predictions from different prior time steps. This yields a tracker that can recover from short-term occlusions and spurious noise in the appearance model. Experimental results show that our tracking algorithm is suitable for predicting pedestrians' behaviors online without needing scene priors or hand-annotated goal information, and improves tracking in real-world crowded scenes under low frame rates.

arXiv:1405.4390

Real Time Object Tracking Based on Inter-frame Coding: A Review

Inter-frame Coding plays significant role for video Compression and Computer Vision. Computer vision systems have been incorporated in many real life applications (e.g. surveillance systems, medical imaging, robot navigation and identity verification systems). Object tracking is a key computer vision topic, which aims at detecting the position of a moving object from a video sequence. The application of Inter-frame Coding for low frame rate video, as well as for low resolution video. Various methods based on Top-down approach just like kernel based or mean shift technique are used to track the object for video, So, Inter-frame Coding algorithms are widely adopted by video coding standards, mainly due to their simplicity and good distortion performance for object tracking.

arXiv:1406.1509

Systematic N-tuple Networks for Position Evaluation: Exceeding 90% in the Othello League

N-tuple networks have been successfully used as position evaluation functions for board games such as Othello or Connect Four. The effectiveness of such networks depends on their architecture, which is determined by the placement of constituent n-tuples, sequences of board locations, providing input to the network. The most popular method of placing n-tuples consists in randomly generating a small number of long, snake-shaped board location sequences. In comparison, we show that learning n-tuple networks is significantly more effective if they involve a large number of systematically placed, short, straight n-tuples. Moreover, we demonstrate that in order to obtain the best performance and the steepest learning curve for Othello it is enough to use n-tuples of size just 2, yielding a network consisting of only 288 weights. The best such network evolved in this study has been evaluated in the online Othello League, obtaining the performance of nearly 96% --- more than any other player to date.

arXiv:1407.3211

Possibility neutrosophic soft sets with applications in decision making and similarity measure

In this paper, concept of possibility neutrosophic soft set and its operations are defined, and their properties are studied. An application of this theory in decision making is investigated. Also a similarity measure of two possibility neutrosophic soft sets is introduced and discussed. Finally an application of this similarity measure is given to select suitable person for position in a firm.

arXiv:1407.7091

Pushbroom Stereo for High-Speed Navigation in Cluttered Environments

We present a novel stereo vision algorithm that is capable of obstacle detection on a mobile-CPU processor at 120 frames per second. Our system performs a subset of standard block-matching stereo processing, searching only for obstacles at a single depth. By using an onboard IMU and state-estimator, we can recover the position of obstacles at all other depths, building and updating a full depth-map at framerate. Here, we describe both the algorithm and our implementation on a high-speed, small UAV, flying at over 20 MPH (9 m/s) close to obstacles. The system requires no external sensing or computation and is, to the best of our knowledge, the first high-framerate stereo detection system running onboard a small UAV.

arXiv:1408.0703

Computational Analysis of Perfect-Information Position Auctions

After experimentation with other designs, the major search engines converged on the weighted, generalized second-price auction (wGSP) for selling keyword advertisements. Notably, this convergence occurred before position auctions were well understood (or, indeed, widely studied) theoretically. While much progress has been made since, theoretical analysis is still not able to settle the question of why search engines found wGSP preferable to other position auctions. We approach this question in a new way, adopting a new analytical paradigm we dub "computational mechanism analysis." By sampling position auction games from a given distribution, encoding them in a computationally efficient representation language, computing their Nash equilibria, and then calculating economic quantities of interest, we can quantitatively answer questions that theoretical methods have not. We considered seven widely studied valuation models from the literature and three position auction variants (generalized first price, unweighted generalized second price, and wGSP). We found that wGSP consistently showed the best ads of any position auction, measured both by social welfare and by relevance (expected number of clicks). Even in models where wGSP was already known to have bad worse-case efficiency, we found that it almost always performed well on average. In contrast, we found that revenue was extremely variable across auction mechanisms, and was highly sensitive to equilibrium selection, the preference model, and the valuation distribution.

arXiv:1408.0452

Methodology For Detection of QRS Pattern Using Secondary Wavelets

Applications of wavelet transform to the field of health care signals have paved the way for implementing revolutionary approaches in detecting the presence of certain abnormalities in human health patterns. There were extensive studies carried out using primary wavelets in various signals like Electrocardiogram (ECG), sonogram etc. with a certain amount of success. On the other hand analysis using secondary wavelets which inherits the characteristics of a set of variations available in signals like ECG can be a promise to detect diseases with ease. Here a method to create a generalized adapted wavelet is presented which contains the information of QRS pattern collected from an anomaly sample space. The method has been tested and found to be successful in locating the position of R peak in noise embedded ECG signal.

arXiv:1408.0101

Memetic Search in Differential Evolution Algorithm

Differential Evolution (DE) is a renowned optimization stratagem that can easily solve nonlinear and comprehensive problems. DE is a well known and uncomplicated population based probabilistic approach for comprehensive optimization. It has apparently outperformed a number of Evolutionary Algorithms and further search heuristics in the vein of Particle Swarm Optimization at what time of testing over both yardstick and actual world problems. Nevertheless, DE, like other probabilistic optimization algorithms, from time to time exhibits precipitate convergence and stagnates at suboptimal position. In order to stay away from stagnation behavior while maintaining an excellent convergence speed, an innovative search strategy is introduced, named memetic search in DE. In the planned strategy, positions update equation customized as per a memetic search stratagem. In this strategy a better solution participates more times in the position modernize procedure. The position update equation is inspired from the memetic search in artificial bee colony algorithm. The proposed strategy is named as Memetic Search in Differential Evolution (MSDE). To prove efficiency and efficacy of MSDE, it is tested over 8 benchmark optimization problems and three real world optimization problems. A comparative analysis has also been carried out among proposed MSDE and original DE. Results show that the anticipated algorithm go one better than the basic DE and its recent deviations in a good number of the experiments.

arXiv:1408.6915

Binary matrices of optimal autocorrelations as alignment marks

We define a new class of binary matrices by maximizing the peak-sidelobe distances in the aperiodic autocorrelations. These matrices can be used as robust position marks for in-plane spatial alignment. The optimal square matrices of dimensions up to 7 by 7 and optimal diagonally-symmetric matrices of 8 by 8 and 9 by 9 were found by exhaustive searches.

arXiv:1408.5403

Neural Mechanism of Language

This paper is based on our previous work on neural coding. It is a self-organized model supported by existing evidences. Firstly, we briefly introduce this model in this paper, and then we explain the neural mechanism of language and reasoning with it. Moreover, we find that the position of an area determines its importance. Specifically, language relevant areas are in the capital position of the cortical kingdom. Therefore they are closely related with autonomous consciousness and working memories. In essence, language is a miniature of the real world. Briefly, this paper would like to bridge the gap between molecule mechanism of neurons and advanced functions such as language and reasoning.

arXiv:1409.5752

On the Impact of Multiobjective Scalarizing Functions

Recently, there has been a renewed interest in decomposition-based approaches for evolutionary multiobjective optimization. However, the impact of the choice of the underlying scalarizing function(s) is still far from being well understood. In this paper, we investigate the behavior of different scalarizing functions and their parameters. We thereby abstract firstly from any specific algorithm and only consider the difficulty of the single scalarized problems in terms of the search ability of a (1+lambda)-EA on biobjective NK-landscapes. Secondly, combining the outcomes of independent single-objective runs allows for more general statements on set-based performance measures. Finally, we investigate the correlation between the opening angle of the scalarizing function's underlying contour lines and the position of the final solution in the objective space. Our analysis is of fundamental nature and sheds more light on the key characteristics of multiobjective scalarizing functions.

arXiv:1404.1151

Recognition of Handwritten MODI Numerals using Hu and Zernike features

Handwritten automatic character recognition has attracted many researchers all over the world to contribute automatic character recognition domain. Shape identification and feature extraction is very important part of any character recognition system and success of method is highly dependent on selection of features. However feature extraction is the most important step in defining the shape of the character as precisely and as uniquely as possible. This is indeed the most important step and complex task as well and achieved success by using invariance property, irrespective of position and orientation. Zernike moments describes shape, identify rotation invariant due to its Orthogonality property. MODI is an ancient script of India had cursive and complex representation of characters. The work described in this paper presents efficiency of Zernike moments over Hus moment for automatic recognition of handwritten MODI numerals.

arXiv:1312.4176

Distributed k-means algorithm

In this paper we provide a fully distributed implementation of the k-means clustering algorithm, intended for wireless sensor networks where each agent is endowed with a possibly high-dimensional observation (e.g., position, humidity, temperature, etc.) The proposed algorithm, by means of one-hop communication, partitions the agents into measure-dependent groups that have small in-group and large out-group "distances". Since the partitions may not have a relation with the topology of the network--members of the same clusters may not be spatially close--the algorithm is provided with a mechanism to compute the clusters'centroids even when the clusters are disconnected in several sub-clusters.The results of the proposed distributed algorithm coincide, in terms of minimization of the objective function, with the centralized k-means algorithm. Some numerical examples illustrate the capabilities of the proposed solution.

arXiv:1412.3474

Deep Domain Confusion: Maximizing for Domain Invariance

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an adaptation layer and an additional domain confusion loss, to learn a representation that is both semantically meaningful and domain invariant. We additionally show that a domain confusion metric can be used for model selection to determine the dimension of an adaptation layer and the best position for the layer in the CNN architecture. Our proposed adaptation method offers empirical performance which exceeds previously published results on a standard benchmark visual domain adaptation task.

arXiv:1412.8496

Accurate Localization in Dense Urban Area Using Google Street View Image

Accurate information about the location and orientation of a camera in mobile devices is central to the utilization of location-based services (LBS). Most of such mobile devices rely on GPS data but this data is subject to inaccuracy due to imperfections in the quality of the signal provided by satellites. This shortcoming has spurred the research into improving the accuracy of localization. Since mobile devices have camera, a major thrust of this research has been seeks to acquire the local scene and apply image retrieval techniques by querying a GPS-tagged image database to find the best match for the acquired scene.. The techniques are however computationally demanding and unsuitable for real-time applications such as assistive technology for navigation by the blind and visually impaired which motivated out work. To overcome the high complexity of those techniques, we investigated the use of inertial sensors as an aid in image-retrieval-based approach. Armed with information of media other than images, such as data from the GPS module along with orientation sensors such as accelerometer and gyro, we sought to limit the size of the image set to c search for the best match. Specifically, data from the orientation sensors along with Dilution of precision (DOP) from GPS are used to find the angle of view and estimation of position. We present analysis of the reduction in the image set size for the search as well as simulations to demonstrate the effectiveness in a fast implementation with 98% Estimated Position Error.

arXiv:1501.04309

Information Theory and its Relation to Machine Learning

In this position paper, I first describe a new perspective on machine learning (ML) by four basic problems (or levels), namely, "What to learn?", "How to learn?", "What to evaluate?", and "What to adjust?". The paper stresses more on the first level of "What to learn?", or "Learning Target Selection". Towards this primary problem within the four levels, I briefly review the existing studies about the connection between information theoretical learning (ITL [1]) and machine learning. A theorem is given on the relation between the empirically-defined similarity measure and information measures. Finally, a conjecture is proposed for pursuing a unified mathematical interpretation to learning target selection.