Paper Group ANR 171
Proposal for a Leaky-Integrate-Fire Spiking Neuron based on Magneto-Electric Switching of Ferro-magnets. Vicinity-Driven Paragraph and Sentence Alignment for Comparable Corpora. Incremental Nonlinear System Identification and Adaptive Particle Filtering Using Gaussian Process. Automatic Selection of Stochastic Watershed Hierarchies. Multi-source Tr …
Proposal for a Leaky-Integrate-Fire Spiking Neuron based on Magneto-Electric Switching of Ferro-magnets
| Title | Proposal for a Leaky-Integrate-Fire Spiking Neuron based on Magneto-Electric Switching of Ferro-magnets |
| Authors | Akhilesh Jaiswal, Sourjya Roy, Gopalakrishnan Srinivasan, Kaushik Roy |
| Abstract | The efficiency of the human brain in performing classification tasks has attracted considerable research interest in brain-inspired neuromorphic computing. Hardware implementations of a neuromorphic system aims to mimic the computations in the brain through interconnection of neurons and synaptic weights. A leaky-integrate-fire (LIF) spiking model is widely used to emulate the dynamics of neuronal action potentials. In this work, we propose a spin based LIF spiking neuron using the magneto-electric (ME) switching of ferro-magnets. The voltage across the ME oxide exhibits a typical leaky-integrate behavior, which in turn switches an underlying ferro-magnet. Due to the effect of thermal noise, the ferro-magnet exhibits probabilistic switching dynamics, which is reminiscent of the stochasticity exhibited by biological neurons. The energy-efficiency of the ME switching mechanism coupled with the intrinsic non-volatility of ferro-magnets result in lower energy consumption, when compared to a CMOS LIF neuron. A device to system-level simulation framework has been developed to investigate the feasibility of the proposed LIF neuron for a hand-written digit recognition problem |
| Tasks | |
| Published | 2016-09-29 |
| URL | http://arxiv.org/abs/1609.09158v1 |
| http://arxiv.org/pdf/1609.09158v1.pdf | |
| PWC | https://paperswithcode.com/paper/proposal-for-a-leaky-integrate-fire-spiking |
| Repo | |
| Framework | |
Vicinity-Driven Paragraph and Sentence Alignment for Comparable Corpora
| Title | Vicinity-Driven Paragraph and Sentence Alignment for Comparable Corpora |
| Authors | Gustavo Henrique Paetzold, Lucia Specia |
| Abstract | Parallel corpora have driven great progress in the field of Text Simplification. However, most sentence alignment algorithms either offer a limited range of alignment types supported, or simply ignore valuable clues present in comparable documents. We address this problem by introducing a new set of flexible vicinity-driven paragraph and sentence alignment algorithms that 1-N, N-1, N-N and long distance null alignments without the need for hard-to-replicate supervised models. |
| Tasks | Text Simplification |
| Published | 2016-12-13 |
| URL | http://arxiv.org/abs/1612.04113v1 |
| http://arxiv.org/pdf/1612.04113v1.pdf | |
| PWC | https://paperswithcode.com/paper/vicinity-driven-paragraph-and-sentence |
| Repo | |
| Framework | |
Incremental Nonlinear System Identification and Adaptive Particle Filtering Using Gaussian Process
| Title | Incremental Nonlinear System Identification and Adaptive Particle Filtering Using Gaussian Process |
| Authors | Vahid Bastani, Lucio Marcenaro, Carlo Regazzoni |
| Abstract | An incremental/online state dynamic learning method is proposed for identification of the nonlinear Gaussian state space models. The method embeds the stochastic variational sparse Gaussian process as the probabilistic state dynamic model inside a particle filter framework. Model updating is done at measurement sample rate using stochastic gradient descent based optimization implemented in the state estimation filtering loop. The performance of the proposed method is compared with state-of-the-art Gaussian process based batch learning methods. Finally, it is shown that the state estimation performance significantly improves due to the online learning of state dynamics. |
| Tasks | |
| Published | 2016-08-30 |
| URL | http://arxiv.org/abs/1608.08362v1 |
| http://arxiv.org/pdf/1608.08362v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-nonlinear-system-identification |
| Repo | |
| Framework | |
Automatic Selection of Stochastic Watershed Hierarchies
| Title | Automatic Selection of Stochastic Watershed Hierarchies |
| Authors | Amin Fehri, Santiago Velasco-Forero, Fernand Meyer |
| Abstract | The segmentation, seen as the association of a partition with an image, is a difficult task. It can be decomposed in two steps: at first, a family of contours associated with a series of nested partitions (or hierarchy) is created and organized, then pertinent contours are extracted. A coarser partition is obtained by merging adjacent regions of a finer partition. The strength of a contour is then measured by the level of the hierarchy for which its two adjacent regions merge. We present an automatic segmentation strategy using a wide range of stochastic watershed hierarchies. For a given set of homogeneous images, our approach selects automatically the best hierarchy and cut level to perform image simplification given an evaluation score. Experimental results illustrate the advantages of our approach on several real-life images datasets. |
| Tasks | |
| Published | 2016-09-09 |
| URL | http://arxiv.org/abs/1609.02715v1 |
| http://arxiv.org/pdf/1609.02715v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-selection-of-stochastic-watershed |
| Repo | |
| Framework | |
Multi-source Transfer Learning with Convolutional Neural Networks for Lung Pattern Analysis
| Title | Multi-source Transfer Learning with Convolutional Neural Networks for Lung Pattern Analysis |
| Authors | Stergios Christodoulidis, Marios Anthimopoulos, Lukas Ebner, Andreas Christe, Stavroula Mougiakakou |
| Abstract | Early diagnosis of interstitial lung diseases is crucial for their treatment, but even experienced physicians find it difficult, as their clinical manifestations are similar. In order to assist with the diagnosis, computer-aided diagnosis (CAD) systems have been developed. These commonly rely on a fixed scale classifier that scans CT images, recognizes textural lung patterns and generates a map of pathologies. In a previous study, we proposed a method for classifying lung tissue patterns using a deep convolutional neural network (CNN), with an architecture designed for the specific problem. In this study, we present an improved method for training the proposed network by transferring knowledge from the similar domain of general texture classification. Six publicly available texture databases are used to pretrain networks with the proposed architecture, which are then fine-tuned on the lung tissue data. The resulting CNNs are combined in an ensemble and their fused knowledge is compressed back to a network with the original architecture. The proposed approach resulted in an absolute increase of about 2% in the performance of the proposed CNN. The results demonstrate the potential of transfer learning in the field of medical image analysis, indicate the textural nature of the problem and show that the method used for training a network can be as important as designing its architecture. |
| Tasks | Texture Classification, Transfer Learning |
| Published | 2016-12-08 |
| URL | http://arxiv.org/abs/1612.02589v1 |
| http://arxiv.org/pdf/1612.02589v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-source-transfer-learning-with |
| Repo | |
| Framework | |
A Novel Approach to Multimedia Ontology Engineering for Automated Reasoning over Audiovisual LOD Datasets
| Title | A Novel Approach to Multimedia Ontology Engineering for Automated Reasoning over Audiovisual LOD Datasets |
| Authors | Leslie F. Sikos |
| Abstract | Multimedia reasoning, which is suitable for, among others, multimedia content analysis and high-level video scene interpretation, relies on the formal and comprehensive conceptualization of the represented knowledge domain. However, most multimedia ontologies are not exhaustive in terms of role definitions, and do not incorporate complex role inclusions and role interdependencies. In fact, most multimedia ontologies do not have a role box at all, and implement only a basic subset of the available logical constructors. Consequently, their application in multimedia reasoning is limited. To address the above issues, VidOnt, the very first multimedia ontology with SROIQ(D) expressivity and a DL-safe ruleset has been introduced for next-generation multimedia reasoning. In contrast to the common practice, the formal grounding has been set in one of the most expressive description logics, and the ontology validated with industry-leading reasoners, namely HermiT and FaCT++. This paper also presents best practices for developing multimedia ontologies, based on my ontology engineering approach. |
| Tasks | |
| Published | 2016-08-26 |
| URL | http://arxiv.org/abs/1608.08072v1 |
| http://arxiv.org/pdf/1608.08072v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-approach-to-multimedia-ontology |
| Repo | |
| Framework | |
A Polynomial-Time Deterministic Approach to the Traveling Salesperson Problem
| Title | A Polynomial-Time Deterministic Approach to the Traveling Salesperson Problem |
| Authors | Ali Jazayeri, Hiroki Sayama |
| Abstract | We propose a new polynomial-time deterministic algorithm that produces an approximated solution for the traveling salesperson problem. The proposed algorithm ranks cities based on their priorities calculated using a power function of means and standard deviations of their distances from other cities and then connects the cities to their neighbors in the order of their priorities. When connecting a city, a neighbor is selected based on their neighbors’ priorities calculated as another power function that additionally includes their distance from the focal city to be connected. This repeats until all the cities are connected into a single loop. The time complexity of the proposed algorithm is $O(n^2)$, where $n$ is the number of cities. Numerical evaluation shows that, despite its simplicity, the proposed algorithm produces shorter tours with less time complexity than other conventional tour construction heuristics. The proposed algorithm can be used by itself or as an initial tour generator for other more complex heuristic optimization algorithms. |
| Tasks | |
| Published | 2016-08-04 |
| URL | http://arxiv.org/abs/1608.01716v4 |
| http://arxiv.org/pdf/1608.01716v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-polynomial-time-deterministic-approach-to |
| Repo | |
| Framework | |
Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
| Title | Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries |
| Authors | Stanislav Minsker |
| Abstract | Estimation of the covariance matrix has attracted a lot of attention of the statistical research community over the years, partially due to important applications such as Principal Component Analysis. However, frequently used empirical covariance estimator (and its modifications) is very sensitive to outliers in the data. As P. J. Huber wrote in 1964, “…This raises a question which could have been asked already by Gauss, but which was, as far as I know, only raised a few years ago (notably by Tukey): what happens if the true distribution deviates slightly from the assumed normal one? As is now well known, the sample mean then may have a catastrophically bad performance…” Motivated by this question, we develop a new estimator of the (element-wise) mean of a random matrix, which includes covariance estimation problem as a special case. Assuming that the entries of a matrix possess only finite second moment, this new estimator admits sub-Gaussian or sub-exponential concentration around the unknown mean in the operator norm. We will explain the key ideas behind our construction, as well as applications to covariance estimation and matrix completion problems. |
| Tasks | Matrix Completion |
| Published | 2016-05-23 |
| URL | http://arxiv.org/abs/1605.07129v5 |
| http://arxiv.org/pdf/1605.07129v5.pdf | |
| PWC | https://paperswithcode.com/paper/sub-gaussian-estimators-of-the-mean-of-a-1 |
| Repo | |
| Framework | |
Egyptian Arabic to English Statistical Machine Translation System for NIST OpenMT’2015
| Title | Egyptian Arabic to English Statistical Machine Translation System for NIST OpenMT’2015 |
| Authors | Hassan Sajjad, Nadir Durrani, Francisco Guzman, Preslav Nakov, Ahmed Abdelali, Stephan Vogel, Wael Salloum, Ahmed El Kholy, Nizar Habash |
| Abstract | The paper describes the Egyptian Arabic-to-English statistical machine translation (SMT) system that the QCRI-Columbia-NYUAD (QCN) group submitted to the NIST OpenMT’2015 competition. The competition focused on informal dialectal Arabic, as used in SMS, chat, and speech. Thus, our efforts focused on processing and standardizing Arabic, e.g., using tools such as 3arrib and MADAMIRA. We further trained a phrase-based SMT system using state-of-the-art features and components such as operation sequence model, class-based language model, sparse features, neural network joint model, genre-based hierarchically-interpolated language model, unsupervised transliteration mining, phrase-table merging, and hypothesis combination. Our system ranked second on all three genres. |
| Tasks | Language Modelling, Machine Translation, Transliteration |
| Published | 2016-06-18 |
| URL | http://arxiv.org/abs/1606.05759v1 |
| http://arxiv.org/pdf/1606.05759v1.pdf | |
| PWC | https://paperswithcode.com/paper/egyptian-arabic-to-english-statistical |
| Repo | |
| Framework | |
Effect of Incomplete Meta-dataset on Average Ranking Method
| Title | Effect of Incomplete Meta-dataset on Average Ranking Method |
| Authors | Salisu Mamman Abdulrahman, Pavel Brazdil |
| Abstract | One of the simplest metalearning methods is the average ranking method. This method uses metadata in the form of test results of a given set of algorithms on given set of datasets and calculates an average rank for each algorithm. The ranks are used to construct the average ranking. We investigate the problem of how the process of generating the average ranking is affected by incomplete metadata including fewer test results. This issue is relevant, because if we could show that incomplete metadata does not affect the final results much, we could explore it in future design. We could simply conduct fewer tests and save thus computation time. In this paper we describe an upgraded average ranking method that is capable of dealing with incomplete metadata. Our results show that the proposed method is relatively robust to omission in test results in the meta datasets. |
| Tasks | |
| Published | 2016-08-24 |
| URL | http://arxiv.org/abs/1608.06845v1 |
| http://arxiv.org/pdf/1608.06845v1.pdf | |
| PWC | https://paperswithcode.com/paper/effect-of-incomplete-meta-dataset-on-average |
| Repo | |
| Framework | |
Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back
| Title | Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back |
| Authors | Vitaly Feldman |
| Abstract | In stochastic convex optimization the goal is to minimize a convex function $F(x) \doteq {\mathbf E}{{\mathbf f}\sim D}[{\mathbf f}(x)]$ over a convex set $\cal K \subset {\mathbb R}^d$ where $D$ is some unknown distribution and each $f(\cdot)$ in the support of $D$ is convex over $\cal K$. The optimization is commonly based on i.i.d.~samples $f^1,f^2,\ldots,f^n$ from $D$. A standard approach to such problems is empirical risk minimization (ERM) that optimizes $F_S(x) \doteq \frac{1}{n}\sum{i\leq n} f^i(x)$. Here we consider the question of how many samples are necessary for ERM to succeed and the closely related question of uniform convergence of $F_S$ to $F$ over $\cal K$. We demonstrate that in the standard $\ell_p/\ell_q$ setting of Lipschitz-bounded functions over a $\cal K$ of bounded radius, ERM requires sample size that scales linearly with the dimension $d$. This nearly matches standard upper bounds and improves on $\Omega(\log d)$ dependence proved for $\ell_2/\ell_2$ setting by Shalev-Shwartz et al. (2009). In stark contrast, these problems can be solved using dimension-independent number of samples for $\ell_2/\ell_2$ setting and $\log d$ dependence for $\ell_1/\ell_\infty$ setting using other approaches. We further show that our lower bound applies even if the functions in the support of $D$ are smooth and efficiently computable and even if an $\ell_1$ regularization term is added. Finally, we demonstrate that for a more general class of bounded-range (but not Lipschitz-bounded) stochastic convex programs an infinite gap appears already in dimension 2. |
| Tasks | |
| Published | 2016-08-15 |
| URL | http://arxiv.org/abs/1608.04414v3 |
| http://arxiv.org/pdf/1608.04414v3.pdf | |
| PWC | https://paperswithcode.com/paper/generalization-of-erm-in-stochastic-convex |
| Repo | |
| Framework | |
Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark
| Title | Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark |
| Authors | Xu-Yao Zhang, Yoshua Bengio, Cheng-Lin Liu |
| Abstract | Recent deep learning based methods have achieved the state-of-the-art performance for handwritten Chinese character recognition (HCCR) by learning discriminative representations directly from raw data. Nevertheless, we believe that the long-and-well investigated domain-specific knowledge should still help to boost the performance of HCCR. By integrating the traditional normalization-cooperated direction-decomposed feature map (directMap) with the deep convolutional neural network (convNet), we are able to obtain new highest accuracies for both online and offline HCCR on the ICDAR-2013 competition database. With this new framework, we can eliminate the needs for data augmentation and model ensemble, which are widely used in other systems to achieve their best results. This makes our framework to be efficient and effective for both training and testing. Furthermore, although directMap+convNet can achieve the best results and surpass human-level performance, we show that writer adaptation in this case is still effective. A new adaptation layer is proposed to reduce the mismatch between training and test data on a particular source layer. The adaptation process can be efficiently and effectively implemented in an unsupervised manner. By adding the adaptation layer into the pre-trained convNet, it can adapt to the new handwriting styles of particular writers, and the recognition accuracy can be further improved consistently and significantly. This paper gives an overview and comparison of recent deep learning based approaches for HCCR, and also sets new benchmarks for both online and offline HCCR. |
| Tasks | Data Augmentation, Offline Handwritten Chinese Character Recognition |
| Published | 2016-06-18 |
| URL | http://arxiv.org/abs/1606.05763v1 |
| http://arxiv.org/pdf/1606.05763v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-and-offline-handwritten-chinese |
| Repo | |
| Framework | |
Authorship attribution via network motifs identification
| Title | Authorship attribution via network motifs identification |
| Authors | Vanessa Queiroz Marinho, Graeme Hirst, Diego Raphael Amancio |
| Abstract | Concepts and methods of complex networks can be used to analyse texts at their different complexity levels. Examples of natural language processing (NLP) tasks studied via topological analysis of networks are keyword identification, automatic extractive summarization and authorship attribution. Even though a myriad of network measurements have been applied to study the authorship attribution problem, the use of motifs for text analysis has been restricted to a few works. The goal of this paper is to apply the concept of motifs, recurrent interconnection patterns, in the authorship attribution task. The absolute frequencies of all thirteen directed motifs with three nodes were extracted from the co-occurrence networks and used as classification features. The effectiveness of these features was verified with four machine learning methods. The results show that motifs are able to distinguish the writing style of different authors. In our best scenario, 57.5% of the books were correctly classified. The chance baseline for this problem is 12.5%. In addition, we have found that function words play an important role in these recurrent patterns. Taken together, our findings suggest that motifs should be further explored in other related linguistic tasks. |
| Tasks | |
| Published | 2016-07-23 |
| URL | http://arxiv.org/abs/1607.06961v1 |
| http://arxiv.org/pdf/1607.06961v1.pdf | |
| PWC | https://paperswithcode.com/paper/authorship-attribution-via-network-motifs |
| Repo | |
| Framework | |
Super-resolving multiresolution images with band-independant geometry of multispectral pixels
| Title | Super-resolving multiresolution images with band-independant geometry of multispectral pixels |
| Authors | Nicolas Brodu |
| Abstract | A new resolution enhancement method is presented for multispectral and multi-resolution images, such as these provided by the Sentinel-2 satellites. Starting from the highest resolution bands, band-dependent information (reflectance) is separated from information that is common to all bands (geometry of scene elements). This model is then applied to unmix low-resolution bands, preserving their reflectance, while propagating band-independent information to preserve the sub-pixel details. A reference implementation is provided, with an application example for super-resolving Sentinel-2 data. |
| Tasks | |
| Published | 2016-09-26 |
| URL | http://arxiv.org/abs/1609.07986v3 |
| http://arxiv.org/pdf/1609.07986v3.pdf | |
| PWC | https://paperswithcode.com/paper/super-resolving-multiresolution-images-with |
| Repo | |
| Framework | |
On the Similarities Between Native, Non-native and Translated Texts
| Title | On the Similarities Between Native, Non-native and Translated Texts |
| Authors | Ella Rabinovich, Sergiu Nisioi, Noam Ordan, Shuly Wintner |
| Abstract | We present a computational analysis of three language varieties: native, advanced non-native, and translation. Our goal is to investigate the similarities and differences between non-native language productions and translations, contrasting both with native language. Using a collection of computational methods we establish three main results: (1) the three types of texts are easily distinguishable; (2) non-native language and translations are closer to each other than each of them is to native language; and (3) some of these characteristics depend on the source or native language, while others do not, reflecting, perhaps, unified principles that similarly affect translations and non-native language. |
| Tasks | |
| Published | 2016-09-11 |
| URL | http://arxiv.org/abs/1609.03204v1 |
| http://arxiv.org/pdf/1609.03204v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-similarities-between-native-non-native |
| Repo | |
| Framework | |
