Paper Group ANR 858
Gaussian Mixture Reduction for Time-Constrained Approximate Inference in Hybrid Bayesian Networks. AI in Education needs interpretable machine learning: Lessons from Open Learner Modelling. Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks. On Geometric Analysis of Affine Sparse Subspace Clustering. The comb …
Gaussian Mixture Reduction for Time-Constrained Approximate Inference in Hybrid Bayesian Networks
| Title | Gaussian Mixture Reduction for Time-Constrained Approximate Inference in Hybrid Bayesian Networks |
| Authors | Cheol Young Park, Kathryn Blackmond Laskey, Paulo C. G. Costa, Shou Matsumoto |
| Abstract | Hybrid Bayesian Networks (HBNs), which contain both discrete and continuous variables, arise naturally in many application areas (e.g., image understanding, data fusion, medical diagnosis, fraud detection). This paper concerns inference in an important subclass of HBNs, the conditional Gaussian (CG) networks, in which all continuous random variables have Gaussian distributions and all children of continuous random variables must be continuous. Inference in CG networks can be NP-hard even for special-case structures, such as poly-trees, where inference in discrete Bayesian networks can be performed in polynomial time. Therefore, approximate inference is required. In approximate inference, it is often necessary to trade off accuracy against solution time. This paper presents an extension to the Hybrid Message Passing inference algorithm for general CG networks and an algorithm for optimizing its accuracy given a bound on computation time. The extended algorithm uses Gaussian mixture reduction to prevent an exponential increase in the number of Gaussian mixture components. The trade-off algorithm performs pre-processing to find optimal run-time settings for the extended algorithm. Experimental results for four CG networks compare performance of the extended algorithm with existing algorithms and show the optimal settings for these CG networks. |
| Tasks | Fraud Detection, Medical Diagnosis |
| Published | 2018-06-06 |
| URL | http://arxiv.org/abs/1806.02415v1 |
| http://arxiv.org/pdf/1806.02415v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-mixture-reduction-for-time |
| Repo | |
| Framework | |
AI in Education needs interpretable machine learning: Lessons from Open Learner Modelling
| Title | AI in Education needs interpretable machine learning: Lessons from Open Learner Modelling |
| Authors | Cristina Conati, Kaska Porayska-Pomsta, Manolis Mavrikis |
| Abstract | Interpretability of the underlying AI representations is a key raison d’^{e}tre for Open Learner Modelling (OLM) – a branch of Intelligent Tutoring Systems (ITS) research. OLMs provide tools for ‘opening’ up the AI models of learners’ cognition and emotions for the purpose of supporting human learning and teaching. Over thirty years of research in ITS (also known as AI in Education) produced important work, which informs about how AI can be used in Education to best effects and, through the OLM research, what are the necessary considerations to make it interpretable and explainable for the benefit of learning. We argue that this work can provide a valuable starting point for a framework of interpretable AI, and as such is of relevance to the application of both knowledge-based and machine learning systems in other high-stakes contexts, beyond education. |
| Tasks | Interpretable Machine Learning |
| Published | 2018-06-30 |
| URL | http://arxiv.org/abs/1807.00154v1 |
| http://arxiv.org/pdf/1807.00154v1.pdf | |
| PWC | https://paperswithcode.com/paper/ai-in-education-needs-interpretable-machine |
| Repo | |
| Framework | |
Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks
| Title | Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks |
| Authors | Minjun Li, Haozhi Huang, Lin Ma, Wei Liu, Tong Zhang, Yu-Gang Jiang |
| Abstract | Recent studies on unsupervised image-to-image translation have made a remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss. However, such unsupervised methods may generate inferior results when the image resolution is high or the two image domains are of significant appearance differences, such as the translations between semantic layouts and natural images in the Cityscapes dataset. In this paper, we propose novel Stacked Cycle-Consistent Adversarial Networks (SCANs) by decomposing a single translation into multi-stage transformations, which not only boost the image translation quality but also enable higher resolution image-to-image translations in a coarse-to-fine manner. Moreover, to properly exploit the information from the previous stage, an adaptive fusion block is devised to learn a dynamic integration of the current stage’s output and the previous stage’s output. Experiments on multiple datasets demonstrate that our proposed approach can improve the translation quality compared with previous single-stage unsupervised methods. |
| Tasks | Image-to-Image Translation, Unsupervised Image-To-Image Translation |
| Published | 2018-07-23 |
| URL | http://arxiv.org/abs/1807.08536v2 |
| http://arxiv.org/pdf/1807.08536v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-image-to-image-translation-with-2 |
| Repo | |
| Framework | |
On Geometric Analysis of Affine Sparse Subspace Clustering
| Title | On Geometric Analysis of Affine Sparse Subspace Clustering |
| Authors | Chun-Guang Li, Chong You, René Vidal |
| Abstract | Sparse subspace clustering (SSC) is a state-of-the-art method for segmenting a set of data points drawn from a union of subspaces into their respective subspaces. It is now well understood that SSC produces subspace-preserving data affinity under broad geometric conditions but suffers from a connectivity issue. In this paper, we develop a novel geometric analysis for a variant of SSC, named affine SSC (ASSC), for the problem of clustering data from a union of affine subspaces. Our contributions include a new concept called affine independence for capturing the arrangement of a collection of affine subspaces. Under the affine independence assumption, we show that ASSC is guaranteed to produce subspace-preserving affinity. Moreover, inspired by the phenomenon that the $\ell_1$ regularization no longer induces sparsity when the solution is nonnegative, we further show that subspace-preserving recovery can be achieved under much weaker conditions for all data points other than the extreme points of samples from each subspace. In addition, we confirm a curious observation that the affinity produced by ASSC may be subspace-dense—which could guarantee the subspace-preserving affinity of ASSC to produce correct clustering under rather weak conditions. We validate the theoretical findings on carefully designed synthetic data and evaluate the performance of ASSC on several real data sets. |
| Tasks | |
| Published | 2018-08-17 |
| URL | http://arxiv.org/abs/1808.05965v4 |
| http://arxiv.org/pdf/1808.05965v4.pdf | |
| PWC | https://paperswithcode.com/paper/on-geometric-analysis-of-affine-sparse |
| Repo | |
| Framework | |
The combination of context information to enhance simple question answering
| Title | The combination of context information to enhance simple question answering |
| Authors | Zhaohui Chao, Lin Li |
| Abstract | With the rapid development of knowledge base,question answering based on knowledge base has been a hot research issue. In this paper, we focus on answering singlerelation factoid questions based on knowledge base. We build a question answering system and study the effect of context information on fact selection, such as entity’s notable type,outdegree. Experimental results show that context information can improve the result of simple question answering. |
| Tasks | Knowledge Base Question Answering, Question Answering |
| Published | 2018-10-09 |
| URL | http://arxiv.org/abs/1810.04000v1 |
| http://arxiv.org/pdf/1810.04000v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-combination-of-context-information-to |
| Repo | |
| Framework | |
A survey on trajectory clustering analysis
| Title | A survey on trajectory clustering analysis |
| Authors | Jiang Bian, Dayong Tian, Yuanyan Tang, Dacheng Tao |
| Abstract | This paper comprehensively surveys the development of trajectory clustering. Considering the critical role of trajectory data mining in modern intelligent systems for surveillance security, abnormal behavior detection, crowd behavior analysis, and traffic control, trajectory clustering has attracted growing attention. Existing trajectory clustering methods can be grouped into three categories: unsupervised, supervised and semi-supervised algorithms. In spite of achieving a certain level of development, trajectory clustering is limited in its success by complex conditions such as application scenarios and data dimensions. This paper provides a holistic understanding and deep insight into trajectory clustering, and presents a comprehensive analysis of representative methods and promising future directions. |
| Tasks | |
| Published | 2018-02-20 |
| URL | http://arxiv.org/abs/1802.06971v1 |
| http://arxiv.org/pdf/1802.06971v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-on-trajectory-clustering-analysis |
| Repo | |
| Framework | |
A Novel Variational Family for Hidden Nonlinear Markov Models
| Title | A Novel Variational Family for Hidden Nonlinear Markov Models |
| Authors | Daniel Hernandez, Antonio Khalil Moretti, Ziqiang Wei, Shreya Saxena, John Cunningham, Liam Paninski |
| Abstract | Latent variable models have been widely applied for the analysis and visualization of large datasets. In the case of sequential data, closed-form inference is possible when the transition and observation functions are linear. However, approximate inference techniques are usually necessary when dealing with nonlinear dynamics and observation functions. Here, we propose a novel variational inference framework for the explicit modeling of time series, Variational Inference for Nonlinear Dynamics (VIND), that is able to uncover nonlinear observation and transition functions from sequential data. The framework includes a structured approximate posterior, and an algorithm that relies on the fixed-point iteration method to find the best estimate for latent trajectories. We apply the method to several datasets and show that it is able to accurately infer the underlying dynamics of these systems, in some cases substantially outperforming state-of-the-art methods. |
| Tasks | Latent Variable Models, Time Series |
| Published | 2018-11-06 |
| URL | https://arxiv.org/abs/1811.02459v2 |
| https://arxiv.org/pdf/1811.02459v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-variational-family-for-hidden |
| Repo | |
| Framework | |
Exploration Bonus for Regret Minimization in Undiscounted Discrete and Continuous Markov Decision Processes
| Title | Exploration Bonus for Regret Minimization in Undiscounted Discrete and Continuous Markov Decision Processes |
| Authors | Jian Qian, Ronan Fruit, Matteo Pirotta, Alessandro Lazaric |
| Abstract | We introduce and analyse two algorithms for exploration-exploitation in discrete and continuous Markov Decision Processes (MDPs) based on exploration bonuses. SCAL$^+$ is a variant of SCAL (Fruit et al., 2018) that performs efficient exploration-exploitation in any unknown weakly-communicating MDP for which an upper bound C on the span of the optimal bias function is known. For an MDP with $S$ states, $A$ actions and $\Gamma \leq S$ possible next states, we prove that SCAL$^+$ achieves the same theoretical guarantees as SCAL (i.e., a high probability regret bound of $\widetilde{O}(C\sqrt{\Gamma SAT})$), with a much smaller computational complexity. Similarly, C-SCAL$^+$ exploits an exploration bonus to achieve sublinear regret in any undiscounted MDP with continuous state space. We show that C-SCAL$^+$ achieves the same regret bound as UCCRL (Ortner and Ryabko, 2012) while being the first implementable algorithm with regret guarantees in this setting. While optimistic algorithms such as UCRL, SCAL or UCCRL maintain a high-confidence set of plausible MDPs around the true unknown MDP, SCAL$^+$ and C-SCAL$^+$ leverage on an exploration bonus to directly plan on the empirically estimated MDP, thus being more computationally efficient. |
| Tasks | Efficient Exploration |
| Published | 2018-12-11 |
| URL | http://arxiv.org/abs/1812.04363v1 |
| http://arxiv.org/pdf/1812.04363v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploration-bonus-for-regret-minimization-in |
| Repo | |
| Framework | |
Exponentially Consistent Kernel Two-Sample Tests
| Title | Exponentially Consistent Kernel Two-Sample Tests |
| Authors | Shengyu Zhu, Biao Chen, Zhitang Chen |
| Abstract | Given two sets of independent samples from unknown distributions $P$ and $Q$, a two-sample test decides whether to reject the null hypothesis that $P=Q$. Recent attention has focused on kernel two-sample tests as the test statistics are easy to compute, converge fast, and have low bias with their finite sample estimates. However, there still lacks an exact characterization on the asymptotic performance of such tests, and in particular, the rate at which the type-II error probability decays to zero in the large sample limit. In this work, we establish that a class of kernel two-sample tests are exponentially consistent with Polish, locally compact Hausdorff sample space, e.g., $\mathbb R^d$. The obtained exponential decay rate is further shown to be optimal among all two-sample tests satisfying the level constraint, and is independent of particular kernels provided that they are bounded continuous and characteristic. Our results gain new insights into related issues such as fair alternative for testing and kernel selection strategy. Finally, as an application, we show that a kernel based test achieves the optimal detection for off-line change detection in the nonparametric setting. |
| Tasks | |
| Published | 2018-02-23 |
| URL | http://arxiv.org/abs/1802.08407v2 |
| http://arxiv.org/pdf/1802.08407v2.pdf | |
| PWC | https://paperswithcode.com/paper/exponentially-consistent-kernel-two-sample |
| Repo | |
| Framework | |
CompNet: Neural networks growing via the compact network morphism
| Title | CompNet: Neural networks growing via the compact network morphism |
| Authors | Jun Lu, Wei Ma, Boi Faltings |
| Abstract | It is often the case that the performance of a neural network can be improved by adding layers. In real-world practices, we always train dozens of neural network architectures in parallel which is a wasteful process. We explored $CompNet$, in which case we morph a well-trained neural network to a deeper one where network function can be preserved and the added layer is compact. The work of the paper makes two contributions: a). The modified network can converge fast and keep the same functionality so that we do not need to train from scratch again; b). The layer size of the added layer in the neural network is controlled by removing the redundant parameters with sparse optimization. This differs from previous network morphism approaches which tend to add more neurons or channels beyond the actual requirements and result in redundance of the model. The method is illustrated using several neural network structures on different data sets including MNIST and CIFAR10. |
| Tasks | |
| Published | 2018-04-27 |
| URL | http://arxiv.org/abs/1804.10316v1 |
| http://arxiv.org/pdf/1804.10316v1.pdf | |
| PWC | https://paperswithcode.com/paper/compnet-neural-networks-growing-via-the |
| Repo | |
| Framework | |
Corpus Phonetics Tutorial
| Title | Corpus Phonetics Tutorial |
| Authors | Eleanor Chodroff |
| Abstract | Corpus phonetics has become an increasingly popular method of research in linguistic analysis. With advances in speech technology and computational power, large scale processing of speech data has become a viable technique. This tutorial introduces the speech scientist and engineer to various automatic speech processing tools. These include acoustic model creation and forced alignment using the Kaldi Automatic Speech Recognition Toolkit (Povey et al., 2011), forced alignment using FAVE-align (Rosenfelder et al., 2014), the Montreal Forced Aligner (McAuliffe et al., 2017), and the Penn Phonetics Lab Forced Aligner (Yuan & Liberman, 2008), as well as stop consonant burst alignment using AutoVOT (Keshet et al., 2014). The tutorial provides a general overview of each program, step-by-step instructions for running the program, as well as several tips and tricks. |
| Tasks | Speech Recognition |
| Published | 2018-11-13 |
| URL | http://arxiv.org/abs/1811.05553v1 |
| http://arxiv.org/pdf/1811.05553v1.pdf | |
| PWC | https://paperswithcode.com/paper/corpus-phonetics-tutorial |
| Repo | |
| Framework | |
CliCR: A Dataset of Clinical Case Reports for Machine Reading Comprehension
| Title | CliCR: A Dataset of Clinical Case Reports for Machine Reading Comprehension |
| Authors | Simon Šuster, Walter Daelemans |
| Abstract | We present a new dataset for machine comprehension in the medical domain. Our dataset uses clinical case reports with around 100,000 gap-filling queries about these cases. We apply several baselines and state-of-the-art neural readers to the dataset, and observe a considerable gap in performance (20% F1) between the best human and machine readers. We analyze the skills required for successful answering and show how reader performance varies depending on the applicable skills. We find that inferences using domain knowledge and object tracking are the most frequently required skills, and that recognizing omitted information and spatio-temporal reasoning are the most difficult for the machines. |
| Tasks | Machine Reading Comprehension, Object Tracking, Reading Comprehension |
| Published | 2018-03-26 |
| URL | http://arxiv.org/abs/1803.09720v1 |
| http://arxiv.org/pdf/1803.09720v1.pdf | |
| PWC | https://paperswithcode.com/paper/clicr-a-dataset-of-clinical-case-reports-for |
| Repo | |
| Framework | |
Learning to Align Images using Weak Geometric Supervision
| Title | Learning to Align Images using Weak Geometric Supervision |
| Authors | Jing Dong, Byron Boots, Frank Dellaert, Ranveer Chandra, Sudipta N. Sinha |
| Abstract | Image alignment tasks require accurate pixel correspondences, which are usually recovered by matching local feature descriptors. Such descriptors are often derived using supervised learning on existing datasets with ground truth correspondences. However, the cost of creating such datasets is usually prohibitive. In this paper, we propose a new approach to align two images related by an unknown 2D homography where the local descriptor is learned from scratch from the images and the homography is estimated simultaneously. Our key insight is that a siamese convolutional neural network can be trained jointly while iteratively updating the homography parameters by optimizing a single loss function. Our method is currently weakly supervised because the input images need to be roughly aligned. We have used this method to align images of different modalities such as RGB and near-infra-red (NIR) without using any prior labeled data. Images automatically aligned by our method were then used to train descriptors that generalize to new images. We also evaluated our method on RGB images. On the HPatches benchmark, our method achieves comparable accuracy to deep local descriptors that were trained offline in a supervised setting. |
| Tasks | |
| Published | 2018-08-04 |
| URL | http://arxiv.org/abs/1808.01424v1 |
| http://arxiv.org/pdf/1808.01424v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-align-images-using-weak-geometric |
| Repo | |
| Framework | |
DeFind: A Protege Plugin for Computing Concept Definitions in EL Ontologies
| Title | DeFind: A Protege Plugin for Computing Concept Definitions in EL Ontologies |
| Authors | Denis Ponomaryov, Stepan Yakovenko |
| Abstract | We introduce an extension to the Protege ontology editor, which allows for discovering concept definitions, which are not explicitly present in axioms, but are logically implied by an ontology. The plugin supports ontologies formulated in the Description Logic EL, which underpins the OWL 2 EL profile of the Web Ontology Language and despite its limited expressiveness captures most of the biomedical ontologies published on the Web. The developed tool allows to verify whether a concept can be defined using a vocabulary of interest specified by a user. In particular, it allows to decide whether some vocabulary items can be omitted in a formulation of a complex concept. The corresponding definitions are presented to the user and are provided with explanations generated by an ontology reasoner. |
| Tasks | |
| Published | 2018-10-10 |
| URL | http://arxiv.org/abs/1810.04363v1 |
| http://arxiv.org/pdf/1810.04363v1.pdf | |
| PWC | https://paperswithcode.com/paper/defind-a-protege-plugin-for-computing-concept |
| Repo | |
| Framework | |
A new approach for pedestrian density estimation using moving sensors and computer vision
| Title | A new approach for pedestrian density estimation using moving sensors and computer vision |
| Authors | Eric K. Tokuda, Yitzchak Lockerman, Gabriel B. A. Ferreira, Ethan Sorrelgreen, David Boyle, Roberto M. Cesar-Jr., Claudio T. Silva |
| Abstract | An understanding of pedestrians dynamics is indispensable for numerous urban applications including the design of transportation networks and planing for business development. Pedestrian counting often requires utilizing manual or technical means to count individual pedestrians in each location of interest. However, such methods do not scale to the size of a city and a new approach to fill this gap is here proposed. In this project, we used a large dense dataset of images of New York City along with deep learning and computer vision techniques to construct a spatio-temporal map of relative pedestrian density. Due to the limitations of state of the art computer vision methods, such automatic detection of pedestrians is inherently subject to errors. We model these errors as a probabilistic process, for which we provide theoretical analysis and through numerical simulations. We demonstrate that, within our assumptions, our methodology can supply a reasonable estimate of pedestrian densities and provide theoretical bounds for the resulting error. |
| Tasks | Density Estimation, Pedestrian Density Estimation |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.05006v1 |
| http://arxiv.org/pdf/1811.05006v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-approach-for-pedestrian-density |
| Repo | |
| Framework | |
