Paper Group ANR 200
The Singularity May Never Be Near. An efficient Exact-PGA algorithm for constant curvature manifolds. An Adaptive Resample-Move Algorithm for Estimating Normalizing Constants. Revisiting Summarization Evaluation for Scientific Articles. An Efficient Algorithm for Mining Frequent Sequence with Constraint Programming. A Multi-task Deep Network for Pe …
The Singularity May Never Be Near
| Title | The Singularity May Never Be Near |
| Authors | Toby Walsh |
| Abstract | There is both much optimism and pessimism around artificial intelligence (AI) today. The optimists are investing millions of dollars, and even in some cases billions of dollars into AI. The pessimists, on the other hand, predict that AI will end many things: jobs, warfare, and even the human race. Both the optimists and the pessimists often appeal to the idea of a technological singularity, a point in time where machine intelligence starts to run away, and a new, more intelligent species starts to inhabit the earth. If the optimists are right, this will be a moment that fundamentally changes our economy and our society. If the pessimists are right, this will be a moment that also fundamentally changes our economy and our society. It is therefore very worthwhile spending some time deciding if either of them might be right. |
| Tasks | |
| Published | 2016-02-20 |
| URL | http://arxiv.org/abs/1602.06462v1 |
| http://arxiv.org/pdf/1602.06462v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-singularity-may-never-be-near |
| Repo | |
| Framework | |
An efficient Exact-PGA algorithm for constant curvature manifolds
| Title | An efficient Exact-PGA algorithm for constant curvature manifolds |
| Authors | Rudrasis Chakraborty, Dohyung Seo, Baba C. Vemuri |
| Abstract | Manifold-valued datasets are widely encountered in many computer vision tasks. A non-linear analog of the PCA, called the Principal Geodesic Analysis (PGA) suited for data lying on Riemannian manifolds was reported in literature a decade ago. Since the objective function in PGA is highly non-linear and hard to solve efficiently in general, researchers have proposed a linear approximation. Though this linear approximation is easy to compute, it lacks accuracy especially when the data exhibits a large variance. Recently, an alternative called exact PGA was proposed which tries to solve the optimization without any linearization. For general Riemannian manifolds, though it gives better accuracy than the original (linearized) PGA, for data that exhibit large variance, the optimization is not computationally efficient. In this paper, we propose an efficient exact PGA for constant curvature Riemannian manifolds (CCM-EPGA). CCM-EPGA differs significantly from existing PGA algorithms in two aspects, (i) the distance between a given manifold-valued data point and the principal submanifold is computed analytically and thus no optimization is required as in existing methods. (ii) Unlike the existing PGA algorithms, the descent into codimension-1 submanifolds does not require any optimization but is accomplished through the use of the Rimeannian inverse Exponential map and the parallel transport operations. We present theoretical and experimental results for constant curvature Riemannian manifolds depicting favorable performance of CCM-EPGA compared to existing PGA algorithms. We also present data reconstruction from principal components and directions which has not been presented in literature in this setting. |
| Tasks | |
| Published | 2016-03-13 |
| URL | http://arxiv.org/abs/1603.03984v1 |
| http://arxiv.org/pdf/1603.03984v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-exact-pga-algorithm-for-constant |
| Repo | |
| Framework | |
An Adaptive Resample-Move Algorithm for Estimating Normalizing Constants
| Title | An Adaptive Resample-Move Algorithm for Estimating Normalizing Constants |
| Authors | Marco Fraccaro, Ulrich Paquet, Ole Winther |
| Abstract | The estimation of normalizing constants is a fundamental step in probabilistic model comparison. Sequential Monte Carlo methods may be used for this task and have the advantage of being inherently parallelizable. However, the standard choice of using a fixed number of particles at each iteration is suboptimal because some steps will contribute disproportionately to the variance of the estimate. We introduce an adaptive version of the Resample-Move algorithm, in which the particle set is adaptively expanded whenever a better approximation of an intermediate distribution is needed. The algorithm builds on the expression for the optimal number of particles and the corresponding minimum variance found under ideal conditions. Benchmark results on challenging Gaussian Process Classification and Restricted Boltzmann Machine applications show that Adaptive Resample-Move (ARM) estimates the normalizing constant with a smaller variance, using less computational resources, than either Resample-Move with a fixed number of particles or Annealed Importance Sampling. A further advantage over Annealed Importance Sampling is that ARM is easier to tune. |
| Tasks | |
| Published | 2016-04-07 |
| URL | http://arxiv.org/abs/1604.01972v2 |
| http://arxiv.org/pdf/1604.01972v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-adaptive-resample-move-algorithm-for |
| Repo | |
| Framework | |
Revisiting Summarization Evaluation for Scientific Articles
| Title | Revisiting Summarization Evaluation for Scientific Articles |
| Authors | Arman Cohan, Nazli Goharian |
| Abstract | Evaluation of text summarization approaches have been mostly based on metrics that measure similarities of system generated summaries with a set of human written gold-standard summaries. The most widely used metric in summarization evaluation has been the ROUGE family. ROUGE solely relies on lexical overlaps between the terms and phrases in the sentences; therefore, in cases of terminology variations and paraphrasing, ROUGE is not as effective. Scientific article summarization is one such case that is different from general domain summarization (e.g. newswire data). We provide an extensive analysis of ROUGE’s effectiveness as an evaluation metric for scientific summarization; we show that, contrary to the common belief, ROUGE is not much reliable in evaluating scientific summaries. We furthermore show how different variants of ROUGE result in very different correlations with the manual Pyramid scores. Finally, we propose an alternative metric for summarization evaluation which is based on the content relevance between a system generated summary and the corresponding human written summaries. We call our metric SERA (Summarization Evaluation by Relevance Analysis). Unlike ROUGE, SERA consistently achieves high correlations with manual scores which shows its effectiveness in evaluation of scientific article summarization. |
| Tasks | Text Summarization |
| Published | 2016-04-01 |
| URL | http://arxiv.org/abs/1604.00400v1 |
| http://arxiv.org/pdf/1604.00400v1.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-summarization-evaluation-for |
| Repo | |
| Framework | |
An Efficient Algorithm for Mining Frequent Sequence with Constraint Programming
| Title | An Efficient Algorithm for Mining Frequent Sequence with Constraint Programming |
| Authors | John O. R. Aoga, Tias Guns, Pierre Schaus |
| Abstract | The main advantage of Constraint Programming (CP) approaches for sequential pattern mining (SPM) is their modularity, which includes the ability to add new constraints (regular expressions, length restrictions, etc). The current best CP approach for SPM uses a global constraint (module) that computes the projected database and enforces the minimum frequency; it does this with a filtering algorithm similar to the PrefixSpan method. However, the resulting system is not as scalable as some of the most advanced mining systems like Zaki’s cSPADE. We show how, using techniques from both data mining and CP, one can use a generic constraint solver and yet outperform existing specialized systems. This is mainly due to two improvements in the module that computes the projected frequencies: first, computing the projected database can be sped up by pre-computing the positions at which an symbol can become unsupported by a sequence, thereby avoiding to scan the full sequence each time; and second by taking inspiration from the trailing used in CP solvers to devise a backtracking-aware data structure that allows fast incremental storing and restoring of the projected database. Detailed experiments show how this approach outperforms existing CP as well as specialized systems for SPM, and that the gain in efficiency translates directly into increased efficiency for other settings such as mining with regular expressions. |
| Tasks | Sequential Pattern Mining |
| Published | 2016-04-05 |
| URL | http://arxiv.org/abs/1604.01166v1 |
| http://arxiv.org/pdf/1604.01166v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-algorithm-for-mining-frequent |
| Repo | |
| Framework | |
A Multi-task Deep Network for Person Re-identification
| Title | A Multi-task Deep Network for Person Re-identification |
| Authors | Weihua Chen, Xiaotang Chen, Jianguo Zhang, Kaiqi Huang |
| Abstract | Person re-identification (ReID) focuses on identifying people across different scenes in video surveillance, which is usually formulated as a binary classification task or a ranking task in current person ReID approaches. In this paper, we take both tasks into account and propose a multi-task deep network (MTDnet) that makes use of their own advantages and jointly optimize the two tasks simultaneously for person ReID. To the best of our knowledge, we are the first to integrate both tasks in one network to solve the person ReID. We show that our proposed architecture significantly boosts the performance. Furthermore, deep architecture in general requires a sufficient dataset for training, which is usually not met in person ReID. To cope with this situation, we further extend the MTDnet and propose a cross-domain architecture that is capable of using an auxiliary set to assist training on small target sets. In the experiments, our approach outperforms most of existing person ReID algorithms on representative datasets including CUHK03, CUHK01, VIPeR, iLIDS and PRID2011, which clearly demonstrates the effectiveness of the proposed approach. |
| Tasks | Person Re-Identification |
| Published | 2016-07-19 |
| URL | http://arxiv.org/abs/1607.05369v3 |
| http://arxiv.org/pdf/1607.05369v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-task-deep-network-for-person-re |
| Repo | |
| Framework | |
An improved uncertainty decoding scheme with weighted samples for DNN-HMM hybrid systems
| Title | An improved uncertainty decoding scheme with weighted samples for DNN-HMM hybrid systems |
| Authors | Christian Huemmer, Ramón Fernández Astudillo, Walter Kellermann |
| Abstract | In this paper, we advance a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems. This numerical sampling concept averages DNN outputs produced by a finite set of feature samples (drawn from a probabilistic distortion model) to approximate the posterior likelihoods of the context-dependent HMM states. As main innovation, we propose a weighted DNN-output averaging based on a minimum classification error criterion and apply it to a probabilistic distortion model for spatial diffuseness features. The experimental evaluation is performed on the 8-channel REVERB Challenge task using a DNN-HMM hybrid system with multichannel front-end signal enhancement. We show that the recognition accuracy of the DNN-HMM hybrid system improves by incorporating uncertainty decoding based on random sampling and that the proposed weighted DNN-output averaging further reduces the word error rate scores. |
| Tasks | |
| Published | 2016-08-04 |
| URL | http://arxiv.org/abs/1609.02082v1 |
| http://arxiv.org/pdf/1609.02082v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-improved-uncertainty-decoding-scheme-with |
| Repo | |
| Framework | |
Discovering Sound Concepts and Acoustic Relations In Text
| Title | Discovering Sound Concepts and Acoustic Relations In Text |
| Authors | Anurag Kumar, Bhiksha Raj, Ndapandula Nakashole |
| Abstract | In this paper we describe approaches for discovering acoustic concepts and relations in text. The first major goal is to be able to identify text phrases which contain a notion of audibility and can be termed as a sound or an acoustic concept. We also propose a method to define an acoustic scene through a set of sound concepts. We use pattern matching and parts of speech tags to generate sound concepts from large scale text corpora. We use dependency parsing and LSTM recurrent neural network to predict a set of sound concepts for a given acoustic scene. These methods are not only helpful in creating an acoustic knowledge base but in the future can also directly help acoustic event and scene detection research. |
| Tasks | Dependency Parsing |
| Published | 2016-09-23 |
| URL | http://arxiv.org/abs/1609.07384v2 |
| http://arxiv.org/pdf/1609.07384v2.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-sound-concepts-and-acoustic |
| Repo | |
| Framework | |
Clustering with phylogenetic tools in astrophysics
| Title | Clustering with phylogenetic tools in astrophysics |
| Authors | Didier Fraix-Burnet |
| Abstract | Phylogenetic approaches are finding more and more applications outside the field of biology. Astrophysics is no exception since an overwhelming amount of multivariate data has appeared in the last twenty years or so. In particular, the diversification of galaxies throughout the evolution of the Universe quite naturally invokes phylogenetic approaches. We have demonstrated that Maximum Parsimony brings useful astrophysical results, and we now proceed toward the analyses of large datasets for galaxies. In this talk I present how we solve the major difficulties for this goal: the choice of the parameters, their discretization, and the analysis of a high number of objects with an unsupervised NP-hard classification technique like cladistics. 1. Introduction How do the galaxy form, and when? How did the galaxy evolve and transform themselves to create the diversity we observe? What are the progenitors to present-day galaxies? To answer these big questions, observations throughout the Universe and the physical modelisation are obvious tools. But between these, there is a key process, without which it would be impossible to extract some digestible information from the complexity of these systems. This is classification. One century ago, galaxies were discovered by Hubble. From images obtained in the visible range of wavelengths, he synthetised his observations through the usual process: classification. With only one parameter (the shape) that is qualitative and determined with the eye, he found four categories: ellipticals, spirals, barred spirals and irregulars. This is the famous Hubble classification. He later hypothetized relationships between these classes, building the Hubble Tuning Fork. The Hubble classification has been refined, notably by de Vaucouleurs, and is still used as the only global classification of galaxies. Even though the physical relationships proposed by Hubble are not retained any more, the Hubble Tuning Fork is nearly always used to represent the classification of the galaxy diversity under its new name the Hubble sequence (e.g. Delgado-Serrano, 2012). Its success is impressive and can be understood by its simplicity, even its beauty, and by the many correlations found between the morphology of galaxies and their other properties. And one must admit that there is no alternative up to now, even though both the Hubble classification and diagram have been recognised to be unsatisfactory. Among the most obvious flaws of this classification, one must mention its monovariate, qualitative, subjective and old-fashioned nature, as well as the difficulty to characterise the morphology of distant galaxies. The first two most significant multivariate studies were by Watanabe et al. (1985) and Whitmore (1984). Since the year 2005, the number of studies attempting to go beyond the Hubble classification has increased largely. Why, despite of this, the Hubble classification and its sequence are still alive and no alternative have yet emerged (Sandage, 2005)? My feeling is that the results of the multivariate analyses are not easily integrated into a one-century old practice of modeling the observations. In addition, extragalactic objects like galaxies, stellar clusters or stars do evolve. Astronomy now provides data on very distant objects, raising the question of the relationships between those and our present day nearby galaxies. Clearly, this is a phylogenetic problem. Astrocladistics 1 aims at exploring the use of phylogenetic tools in astrophysics (Fraix-Burnet et al., 2006a,b). We have proved that Maximum Parsimony (or cladistics) can be applied in astrophysics and provides a new exploration tool of the data (Fraix-Burnet et al., 2009, 2012, Cardone & Fraix-Burnet, 2013). As far as the classification of galaxies is concerned, a larger number of objects must now be analysed. In this paper, I |
| Tasks | |
| Published | 2016-06-01 |
| URL | http://arxiv.org/abs/1606.00235v1 |
| http://arxiv.org/pdf/1606.00235v1.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-with-phylogenetic-tools-in |
| Repo | |
| Framework | |
The Effects of Age, Gender and Region on Non-standard Linguistic Variation in Online Social Networks
| Title | The Effects of Age, Gender and Region on Non-standard Linguistic Variation in Online Social Networks |
| Authors | Claudia Peersman, Walter Daelemans, Reinhild Vandekerckhove, Bram Vandekerckhove, Leona Van Vaerenbergh |
| Abstract | We present a corpus-based analysis of the effects of age, gender and region of origin on the production of both “netspeak” or “chatspeak” features and regional speech features in Flemish Dutch posts that were collected from a Belgian online social network platform. The present study shows that combining quantitative and qualitative approaches is essential for understanding non-standard linguistic variation in a CMC corpus. It also presents a methodology that enables the systematic study of this variation by including all non-standard words in the corpus. The analyses resulted in a convincing illustration of the Adolescent Peak Principle. In addition, our approach revealed an intriguing correlation between the use of regional speech features and chatspeak features. |
| Tasks | |
| Published | 2016-01-11 |
| URL | http://arxiv.org/abs/1601.02431v1 |
| http://arxiv.org/pdf/1601.02431v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-effects-of-age-gender-and-region-on-non |
| Repo | |
| Framework | |
Symmetry Breaking Predicates for SAT-based DFA Identification
| Title | Symmetry Breaking Predicates for SAT-based DFA Identification |
| Authors | Vladimir Ulyantsev, Ilya Zakirzyanov, Anatoly Shalyto |
| Abstract | It was shown before that the NP-hard problem of deterministic finite automata (DFA) identification can be effectively translated to Boolean satisfiability (SAT). Modern SAT-solvers can tackle hard DFA identification instances efficiently. We present a technique to reduce the problem search space by enforcing an enumeration of DFA states in depth-first search (DFS) or breadth-first search (BFS) order. We propose symmetry breaking predicates, which can be added to Boolean formulae representing various DFA identification problems. We show how to apply this technique to DFA identification from both noiseless and noisy data. Also we propose a method to identify all automata of the desired size. The proposed approach outperforms the current state-of-the-art DFASAT method for DFA identification from noiseless data. A big advantage of the proposed approach is that it allows to determine exactly the existence or non-existence of a solution of the noisy DFA identification problem unlike metaheuristic approaches such as genetic algorithms. |
| Tasks | |
| Published | 2016-02-16 |
| URL | http://arxiv.org/abs/1602.05028v2 |
| http://arxiv.org/pdf/1602.05028v2.pdf | |
| PWC | https://paperswithcode.com/paper/symmetry-breaking-predicates-for-sat-based |
| Repo | |
| Framework | |
Robust Deep-Learning-Based Road-Prediction for Augmented Reality Navigation Systems
| Title | Robust Deep-Learning-Based Road-Prediction for Augmented Reality Navigation Systems |
| Authors | Matthias Limmer, Julian Forster, Dennis Baudach, Florian Schüle, Roland Schweiger, Hendrik P. A. Lensch |
| Abstract | This paper proposes an approach that predicts the road course from camera sensors leveraging deep learning techniques. Road pixels are identified by training a multi-scale convolutional neural network on a large number of full-scene-labeled night-time road images including adverse weather conditions. A framework is presented that applies the proposed approach to longer distance road course estimation, which is the basis for an augmented reality navigation application. In this framework long range sensor data (radar) and data from a map database are fused with short range sensor data (camera) to produce a precise longitudinal and lateral localization and road course estimation. The proposed approach reliably detects roads with and without lane markings and thus increases the robustness and availability of road course estimations and augmented reality navigation. Evaluations on an extensive set of high precision ground truth data taken from a differential GPS and an inertial measurement unit show that the proposed approach reaches state-of-the-art performance without the limitation of requiring existing lane markings. |
| Tasks | |
| Published | 2016-05-31 |
| URL | http://arxiv.org/abs/1605.09533v1 |
| http://arxiv.org/pdf/1605.09533v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-deep-learning-based-road-prediction |
| Repo | |
| Framework | |
Designing Intelligent Automation based Solutions for Complex Social Problems
| Title | Designing Intelligent Automation based Solutions for Complex Social Problems |
| Authors | Sanjay Podder, Janardan Misra, Senthil Kumaresan, Neville Dubash, Indrani Bhattacharya |
| Abstract | Deciding effective and timely preventive measures against complex social problems affecting relatively low income geographies is a difficult challenge. There is a strong need to adopt intelligent automation based solutions with low cost imprints to tackle these problems at larger scales. Starting with the hypothesis that analytical modelling and analysis of social phenomena with high accuracy is in general inherently hard, in this paper we propose design framework to enable data-driven machine learning based adaptive solution approach towards enabling more effective preventive measures. We use survey data collected from a socio-economically backward region of India about adolescent girls to illustrate the design approach. |
| Tasks | |
| Published | 2016-06-16 |
| URL | http://arxiv.org/abs/1606.05275v1 |
| http://arxiv.org/pdf/1606.05275v1.pdf | |
| PWC | https://paperswithcode.com/paper/designing-intelligent-automation-based |
| Repo | |
| Framework | |
A Matrix Splitting Perspective on Planning with Options
| Title | A Matrix Splitting Perspective on Planning with Options |
| Authors | Pierre-Luc Bacon, Doina Precup |
| Abstract | We show that the Bellman operator underlying the options framework leads to a matrix splitting, an approach traditionally used to speed up convergence of iterative solvers for large linear systems of equations. Based on standard comparison theorems for matrix splittings, we then show how the asymptotic rate of convergence varies as a function of the inherent timescales of the options. This new perspective highlights a trade-off between asymptotic performance and the cost of computation associated with building a good set of options. |
| Tasks | |
| Published | 2016-12-03 |
| URL | http://arxiv.org/abs/1612.00916v2 |
| http://arxiv.org/pdf/1612.00916v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-matrix-splitting-perspective-on-planning |
| Repo | |
| Framework | |
Improved Recurrent Neural Networks for Session-based Recommendations
| Title | Improved Recurrent Neural Networks for Session-based Recommendations |
| Authors | Yong Kiam Tan, Xinxing Xu, Yong Liu |
| Abstract | 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, and a novel alternative model that directly predicts item embeddings. Experiments on the RecSys Challenge 2015 dataset demonstrate relative improvements of 12.8% and 14.8% over previously reported results on the Recall@20 and Mean Reciprocal Rank@20 metrics respectively. |
| Tasks | Data Augmentation, Session-Based Recommendations |
| Published | 2016-06-27 |
| URL | http://arxiv.org/abs/1606.08117v2 |
| http://arxiv.org/pdf/1606.08117v2.pdf | |
| PWC | https://paperswithcode.com/paper/improved-recurrent-neural-networks-for |
| Repo | |
| Framework | |
