Paper Group ANR 182
Detecting and Explaining Drifts in Yearly Grant Applications. Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristics. How Complex is your classification problem? A survey on measuring classification complexity. eCommerceGAN : A Generative Adversarial Network for E-commerce. Post-prognostics decision in Cyber-Physical Sy …
Detecting and Explaining Drifts in Yearly Grant Applications
| Title | Detecting and Explaining Drifts in Yearly Grant Applications |
| Authors | Stephen Pauwels, Toon Calders |
| Abstract | During the lifetime of a Business Process changes can be made to the workflow, the required resources, required documents, . . . . Different traces from the same Business Process within a single log file can thus differ substantially due to these changes. We propose a method that is able to detect concept drift in multivariate log files with a dozen attributes. We test our approach on the BPI Challenge 2018 data con- sisting of applications for EU direct payment from farmers in Germany where we use it to detect Concept Drift. In contrast to other methods our algorithm does not require the manual selection of the features used to detect drift. Our method first creates a model that captures the re- lations between attributes and between events of different time steps. This model is then used to score every event and trace. These scores can be used to detect outlying cases and concept drift. Thanks to the decomposability of the score we are able to perform detailed root-cause analysis. |
| Tasks | |
| Published | 2018-09-15 |
| URL | http://arxiv.org/abs/1809.05650v2 |
| http://arxiv.org/pdf/1809.05650v2.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-and-explaining-drifts-in-yearly |
| Repo | |
| Framework | |
Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristics
| Title | Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristics |
| Authors | Christoffer Holmgård, Michael Cerny Green, Antonios Liapis, Julian Togelius |
| Abstract | This paper describes a method for generative player modeling and its application to the automatic testing of game content using archetypal player models called procedural personas. Theoretically grounded in psychological decision theory, procedural personas are implemented using a variation of Monte Carlo Tree Search (MCTS) where the node selection criteria are developed using evolutionary computation, replacing the standard UCB1 criterion of MCTS. Using these personas we demonstrate how generative player models can be applied to a varied corpus of game levels and demonstrate how different play styles can be enacted in each level. In short, we use artificially intelligent personas to construct synthetic playtesters. The proposed approach could be used as a tool for automatic play testing when human feedback is not readily available or when quick visualization of potential interactions is necessary. Possible applications include interactive tools during game development or procedural content generation systems where many evaluations must be conducted within a short time span. |
| Tasks | |
| Published | 2018-02-19 |
| URL | http://arxiv.org/abs/1802.06881v1 |
| http://arxiv.org/pdf/1802.06881v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-playtesting-with-procedural |
| Repo | |
| Framework | |
How Complex is your classification problem? A survey on measuring classification complexity
| Title | How Complex is your classification problem? A survey on measuring classification complexity |
| Authors | Ana C. Lorena, Luís P. F. Garcia, Jens Lehmann, Marcilio C. P. Souto, Tin K. Ho |
| Abstract | Extracting characteristics from the training datasets of classification problems has proven effective in a number of meta-analyses. Among them, measures of classification complexity can estimate the difficulty in separating the data points into their expected classes. Descriptors of the spatial distribution of the data and estimates of the shape and size of the decision boundary are among the existent measures for this characterization. This information can support the formulation of new data-driven pre-processing and pattern recognition techniques, which can in turn be focused on challenging characteristics of the problems. This paper surveys and analyzes measures which can be extracted from the training datasets in order to characterize the complexity of the respective classification problems. Their use in recent literature is also reviewed and discussed, allowing to prospect opportunities for future work in the area. Finally, descriptions are given on an R package named Extended Complexity Library (ECoL) that implements a set of complexity measures and is made publicly available. |
| Tasks | |
| Published | 2018-08-10 |
| URL | https://arxiv.org/abs/1808.03591v2 |
| https://arxiv.org/pdf/1808.03591v2.pdf | |
| PWC | https://paperswithcode.com/paper/how-complex-is-your-classification-problem-a |
| Repo | |
| Framework | |
eCommerceGAN : A Generative Adversarial Network for E-commerce
| Title | eCommerceGAN : A Generative Adversarial Network for E-commerce |
| Authors | Ashutosh Kumar, Arijit Biswas, Subhajit Sanyal |
| Abstract | E-commerce companies such as Amazon, Alibaba and Flipkart process billions of orders every year. However, these orders represent only a small fraction of all plausible orders. Exploring the space of all plausible orders could help us better understand the relationships between the various entities in an e-commerce ecosystem, namely the customers and the products they purchase. In this paper, we propose a Generative Adversarial Network (GAN) for orders made in e-commerce websites. Once trained, the generator in the GAN could generate any number of plausible orders. Our contributions include: (a) creating a dense and low-dimensional representation of e-commerce orders, (b) train an ecommerceGAN (ecGAN) with real orders to show the feasibility of the proposed paradigm, and (c) train an ecommerce-conditional-GAN (ec^2GAN) to generate the plausible orders involving a particular product. We propose several qualitative methods to evaluate ecGAN and demonstrate its effectiveness. The ec^2GAN is used for various kinds of characterization of possible orders involving a product that has just been introduced into the e-commerce system. The proposed approach ec^2GAN performs significantly better than the baseline in most of the scenarios. |
| Tasks | |
| Published | 2018-01-10 |
| URL | http://arxiv.org/abs/1801.03244v1 |
| http://arxiv.org/pdf/1801.03244v1.pdf | |
| PWC | https://paperswithcode.com/paper/ecommercegan-a-generative-adversarial-network |
| Repo | |
| Framework | |
Post-prognostics decision in Cyber-Physical Systems
| Title | Post-prognostics decision in Cyber-Physical Systems |
| Authors | Safa Meraghni, Labib Sadek Terrissa, Soheyb Ayad, Noureddine Zerhouni, Christophe Varnier |
| Abstract | Prognostics and Health Management (PHM) offers several benefits for predictive maintenance. It predicts the future behavior of a system as well as its Remaining Useful Life (RUL). This RUL is used to planned the maintenance operation to avoid the failure, the stop time and optimize the cost of the maintenance and failure. However, with the development of the industry the assets are nowadays distributed this is why the PHM needs to be developed using the new IT. In our work we propose a PHM solution based on Cyber physical system where the physical side is connected to the analyze process of the PHM which are developed in the cloud to be shared and to benefit of the cloud characteristics |
| Tasks | |
| Published | 2018-10-27 |
| URL | http://arxiv.org/abs/1810.11732v1 |
| http://arxiv.org/pdf/1810.11732v1.pdf | |
| PWC | https://paperswithcode.com/paper/post-prognostics-decision-in-cyber-physical |
| Repo | |
| Framework | |
The UAVid Dataset for Video Semantic Segmentation
| Title | The UAVid Dataset for Video Semantic Segmentation |
| Authors | Ye Lyu, George Vosselman, Guisong Xia, Alper Yilmaz, Michael Ying Yang |
| Abstract | Video semantic segmentation has been one of the research focus in computer vision recently. It serves as a perception foundation for many fields such as robotics and autonomous driving. The fast development of semantic segmentation attributes enormously to the large scale datasets, especially for the deep learning related methods. Currently, there already exist several semantic segmentation datasets for complex urban scenes, such as the Cityscapes and CamVid datasets. They have been the standard datasets for comparison among semantic segmentation methods. In this paper, we introduce a new high resolution UAV video semantic segmentation dataset as complement, UAVid. Our UAV dataset consists of 30 video sequences capturing high resolution images. In total, 300 images have been densely labelled with 8 classes for urban scene understanding task. Our dataset brings out new challenges. We provide several deep learning baseline methods, among which the proposed novel Multi-Scale-Dilation net performs the best via multi-scale feature extraction. We have also explored the usability of sequence data by leveraging on CRF model in both spatial and temporal domain. |
| Tasks | Autonomous Driving, Scene Understanding, Semantic Segmentation, Video Semantic Segmentation |
| Published | 2018-10-24 |
| URL | http://arxiv.org/abs/1810.10438v1 |
| http://arxiv.org/pdf/1810.10438v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-uavid-dataset-for-video-semantic |
| Repo | |
| Framework | |
NFFT meets Krylov methods: Fast matrix-vector products for the graph Laplacian of fully connected networks
| Title | NFFT meets Krylov methods: Fast matrix-vector products for the graph Laplacian of fully connected networks |
| Authors | Dominik Alfke, Daniel Potts, Martin Stoll, Toni Volkmer |
| Abstract | The graph Laplacian is a standard tool in data science, machine learning, and image processing. The corresponding matrix inherits the complex structure of the underlying network and is in certain applications densely populated. This makes computations, in particular matrix-vector products, with the graph Laplacian a hard task. A typical application is the computation of a number of its eigenvalues and eigenvectors. Standard methods become infeasible as the number of nodes in the graph is too large. We propose the use of the fast summation based on the nonequispaced fast Fourier transform (NFFT) to perform the dense matrix-vector product with the graph Laplacian fast without ever forming the whole matrix. The enormous flexibility of the NFFT algorithm allows us to embed the accelerated multiplication into Lanczos-based eigenvalues routines or iterative linear system solvers and even consider other than the standard Gaussian kernels. We illustrate the feasibility of our approach on a number of test problems from image segmentation to semi-supervised learning based on graph-based PDEs. In particular, we compare our approach with the Nystr"om method. Moreover, we present and test an enhanced, hybrid version of the Nystr"om method, which internally uses the NFFT. |
| Tasks | Semantic Segmentation |
| Published | 2018-08-14 |
| URL | http://arxiv.org/abs/1808.04580v2 |
| http://arxiv.org/pdf/1808.04580v2.pdf | |
| PWC | https://paperswithcode.com/paper/nfft-meets-krylov-methods-fast-matrix-vector |
| Repo | |
| Framework | |
Phonetic and Graphemic Systems for Multi-Genre Broadcast Transcription
| Title | Phonetic and Graphemic Systems for Multi-Genre Broadcast Transcription |
| Authors | Yu Wang, Xie Chen, Mark Gales, Anton Ragni, Jeremy Wong |
| Abstract | State-of-the-art English automatic speech recognition systems typically use phonetic rather than graphemic lexicons. Graphemic systems are known to perform less well for English as the mapping from the written form to the spoken form is complicated. However, in recent years the representational power of deep-learning based acoustic models has improved, raising interest in graphemic acoustic models for English, due to the simplicity of generating the lexicon. In this paper, phonetic and graphemic models are compared for an English Multi-Genre Broadcast transcription task. A range of acoustic models based on lattice-free MMI training are constructed using phonetic and graphemic lexicons. For this task, it is found that having a long-span temporal history reduces the difference in performance between the two forms of models. In addition, system combination is examined, using parameter smoothing and hypothesis combination. As the combination approaches become more complicated the difference between the phonetic and graphemic systems further decreases. Finally, for all configurations examined the combination of phonetic and graphemic systems yields consistent gains. |
| Tasks | Speech Recognition |
| Published | 2018-02-01 |
| URL | http://arxiv.org/abs/1802.00254v1 |
| http://arxiv.org/pdf/1802.00254v1.pdf | |
| PWC | https://paperswithcode.com/paper/phonetic-and-graphemic-systems-for-multi |
| Repo | |
| Framework | |
Mask Propagation Network for Video Object Segmentation
| Title | Mask Propagation Network for Video Object Segmentation |
| Authors | Jia Sun, Dongdong Yu, Yinghong Li, Changhu Wang |
| Abstract | In this work, we propose a mask propagation network to treat the video segmentation problem as a concept of the guided instance segmentation. Similar to most MaskTrack based video segmentation methods, our method takes the mask probability map of previous frame and the appearance of current frame as inputs, and predicts the mask probability map for the current frame. Specifically, we adopt the Xception backbone based DeepLab v3+ model as the probability map predictor in our prediction pipeline. Besides, instead of the full image and the original mask probability, our network takes the region of interest of the instance, and the new mask probability which warped by the optical flow between the previous and current frames as the inputs. We also ensemble the modified One-Shot Video Segmentation Network to make the final predictions in order to retrieve and segment the missing instance. |
| Tasks | Instance Segmentation, Optical Flow Estimation, Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2018-10-24 |
| URL | http://arxiv.org/abs/1810.10289v1 |
| http://arxiv.org/pdf/1810.10289v1.pdf | |
| PWC | https://paperswithcode.com/paper/mask-propagation-network-for-video-object |
| Repo | |
| Framework | |
Large-scale Nonlinear Variable Selection via Kernel Random Features
| Title | Large-scale Nonlinear Variable Selection via Kernel Random Features |
| Authors | Magda Gregorová, Jason Ramapuram, Alexandros Kalousis, Stéphane Marchand-Maillet |
| Abstract | We propose a new method for input variable selection in nonlinear regression. The method is embedded into a kernel regression machine that can model general nonlinear functions, not being a priori limited to additive models. This is the first kernel-based variable selection method applicable to large datasets. It sidesteps the typical poor scaling properties of kernel methods by mapping the inputs into a relatively low-dimensional space of random features. The algorithm discovers the variables relevant for the regression task together with learning the prediction model through learning the appropriate nonlinear random feature maps. We demonstrate the outstanding performance of our method on a set of large-scale synthetic and real datasets. |
| Tasks | |
| Published | 2018-04-19 |
| URL | http://arxiv.org/abs/1804.07169v2 |
| http://arxiv.org/pdf/1804.07169v2.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-nonlinear-variable-selection-via |
| Repo | |
| Framework | |
Elastic CoCoA: Scaling In to Improve Convergence
| Title | Elastic CoCoA: Scaling In to Improve Convergence |
| Authors | Michael Kaufmann, Thomas Parnell, Kornilios Kourtis |
| Abstract | In this paper we experimentally analyze the convergence behavior of CoCoA and show, that the number of workers required to achieve the highest convergence rate at any point in time, changes over the course of the training. Based on this observation, we build Chicle, an elastic framework that dynamically adjusts the number of workers based on feedback from the training algorithm, in order to select the number of workers that results in the highest convergence rate. In our evaluation of 6 datasets, we show that Chicle is able to accelerate the time-to-accuracy by a factor of up to 5.96x compared to the best static setting, while being robust enough to find an optimal or near-optimal setting automatically in most cases. |
| Tasks | |
| Published | 2018-11-06 |
| URL | http://arxiv.org/abs/1811.02322v1 |
| http://arxiv.org/pdf/1811.02322v1.pdf | |
| PWC | https://paperswithcode.com/paper/elastic-cocoa-scaling-in-to-improve |
| Repo | |
| Framework | |
On the Complexity of the Inverse Semivalue Problem for Weighted Voting Games
| Title | On the Complexity of the Inverse Semivalue Problem for Weighted Voting Games |
| Authors | Ilias Diakonikolas, Chrystalla Pavlou |
| Abstract | Weighted voting games are a family of cooperative games, typically used to model voting situations where a number of agents (players) vote against or for a proposal. In such games, a proposal is accepted if an appropriately weighted sum of the votes exceeds a prespecified threshold. As the influence of a player over the voting outcome is not in general proportional to her assigned weight, various power indices have been proposed to measure each player’s influence. The inverse power index problem is the problem of designing a weighted voting game that achieves a set of target influences according to a predefined power index. In this work, we study the computational complexity of the inverse problem when the power index belongs to the class of semivalues. We prove that the inverse problem is computationally intractable for a broad family of semivalues, including all regular semivalues. As a special case of our general result, we establish computational hardness of the inverse problem for the Banzhaf indices and the Shapley values, arguably the most popular power indices. |
| Tasks | |
| Published | 2018-12-31 |
| URL | http://arxiv.org/abs/1812.11712v1 |
| http://arxiv.org/pdf/1812.11712v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-complexity-of-the-inverse-semivalue |
| Repo | |
| Framework | |
Universality of Deep Convolutional Neural Networks
| Title | Universality of Deep Convolutional Neural Networks |
| Authors | Ding-Xuan Zhou |
| Abstract | Deep learning has been widely applied and brought breakthroughs in speech recognition, computer vision, and many other domains. The involved deep neural network architectures and computational issues have been well studied in machine learning. But there lacks a theoretical foundation for understanding the approximation or generalization ability of deep learning methods generated by the network architectures such as deep convolutional neural networks having convolutional structures. Here we show that a deep convolutional neural network (CNN) is universal, meaning that it can be used to approximate any continuous function to an arbitrary accuracy when the depth of the neural network is large enough. This answers an open question in learning theory. Our quantitative estimate, given tightly in terms of the number of free parameters to be computed, verifies the efficiency of deep CNNs in dealing with large dimensional data. Our study also demonstrates the role of convolutions in deep CNNs. |
| Tasks | Speech Recognition |
| Published | 2018-05-28 |
| URL | http://arxiv.org/abs/1805.10769v2 |
| http://arxiv.org/pdf/1805.10769v2.pdf | |
| PWC | https://paperswithcode.com/paper/universality-of-deep-convolutional-neural |
| Repo | |
| Framework | |
Chaotic Quantum Double Delta Swarm Algorithm using Chebyshev Maps: Theoretical Foundations, Performance Analyses and Convergence Issues
| Title | Chaotic Quantum Double Delta Swarm Algorithm using Chebyshev Maps: Theoretical Foundations, Performance Analyses and Convergence Issues |
| Authors | Saptarshi Sengupta, Sanchita Basak, Richard Alan Peters II |
| Abstract | Quantum Double Delta Swarm (QDDS) Algorithm is a new metaheuristic algorithm inspired by the convergence mechanism to the center of potential generated within a single well of a spatially co-located double-delta well setup. It mimics the wave nature of candidate positions in solution spaces and draws upon quantum mechanical interpretations much like other quantum-inspired computational intelligence paradigms. In this work, we introduce a Chebyshev map driven chaotic perturbation in the optimization phase of the algorithm to diversify weights placed on contemporary and historical, socially-optimal agents’ solutions. We follow this up with a characterization of solution quality on a suite of 23 single-objective functions and carry out a comparative analysis with eight other related nature-inspired approaches. By comparing solution quality and successful runs over dynamic solution ranges, insights about the nature of convergence are obtained. A two-tailed t-test establishes the statistical significance of the solution data whereas Cohen’s d and Hedge’s g values provide a measure of effect sizes. We trace the trajectory of the fittest pseudo-agent over all function evaluations to comment on the dynamics of the system and prove that the proposed algorithm is theoretically globally convergent under the assumptions adopted for proofs of other closely-related random search algorithms. |
| Tasks | |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.01945v2 |
| http://arxiv.org/pdf/1811.01945v2.pdf | |
| PWC | https://paperswithcode.com/paper/chaotic-quantum-double-delta-swarm-algorithm |
| Repo | |
| Framework | |
Deep Texture Manifold for Ground Terrain Recognition
| Title | Deep Texture Manifold for Ground Terrain Recognition |
| Authors | Jia Xue, Hang Zhang, Kristin Dana |
| Abstract | We present a texture network called Deep Encoding Pooling Network (DEP) for the task of ground terrain recognition. Recognition of ground terrain is an important task in establishing robot or vehicular control parameters, as well as for localization within an outdoor environment. The architecture of DEP integrates orderless texture details and local spatial information and the performance of DEP surpasses state-of-the-art methods for this task. The GTOS database (comprised of over 30,000 images of 40 classes of ground terrain in outdoor scenes) enables supervised recognition. For evaluation under realistic conditions, we use test images that are not from the existing GTOS dataset, but are instead from hand-held mobile phone videos of similar terrain. This new evaluation dataset, GTOS-mobile, consists of 81 videos of 31 classes of ground terrain such as grass, gravel, asphalt and sand. The resultant network shows excellent performance not only for GTOS-mobile, but also for more general databases (MINC and DTD). Leveraging the discriminant features learned from this network, we build a new texture manifold called DEP-manifold. We learn a parametric distribution in feature space in a fully supervised manner, which gives the distance relationship among classes and provides a means to implicitly represent ambiguous class boundaries. The source code and database are publicly available. |
| Tasks | |
| Published | 2018-03-29 |
| URL | http://arxiv.org/abs/1803.10896v2 |
| http://arxiv.org/pdf/1803.10896v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-texture-manifold-for-ground-terrain |
| Repo | |
| Framework | |
