Paper Group ANR 732
An Introduction to the Practical and Theoretical Aspects of Mixture-of-Experts Modeling. Inference of Fine-Grained Event Causality from Blogs and Films. Clonal analysis of newborn hippocampal dentate granule cell proliferation and development in temporal lobe epilepsy. Large-Scale Goodness Polarity Lexicons for Community Question Answering. Dimensi …
An Introduction to the Practical and Theoretical Aspects of Mixture-of-Experts Modeling
| Title | An Introduction to the Practical and Theoretical Aspects of Mixture-of-Experts Modeling |
| Authors | Hien D. Nguyen, Faicel Chamroukhi |
| Abstract | Mixture-of-experts (MoE) models are a powerful paradigm for modeling of data arising from complex data generating processes (DGPs). In this article, we demonstrate how different MoE models can be constructed to approximate the underlying DGPs of arbitrary types of data. Due to the probabilistic nature of MoE models, we propose the maximum quasi-likelihood (MQL) estimator as a method for estimating MoE model parameters from data, and we provide conditions under which MQL estimators are consistent and asymptotically normal. The blockwise minorization-maximizatoin (blockwise-MM) algorithm framework is proposed as an all-purpose method for constructing algorithms for obtaining MQL estimators. An example derivation of a blockwise-MM algorithm is provided. We then present a method for constructing information criteria for estimating the number of components in MoE models and provide justification for the classic Bayesian information criterion (BIC). We explain how MoE models can be used to conduct classification, clustering, and regression and we illustrate these applications via a pair of worked examples. |
| Tasks | |
| Published | 2017-07-12 |
| URL | http://arxiv.org/abs/1707.03538v1 |
| http://arxiv.org/pdf/1707.03538v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-introduction-to-the-practical-and |
| Repo | |
| Framework | |
Inference of Fine-Grained Event Causality from Blogs and Films
| Title | Inference of Fine-Grained Event Causality from Blogs and Films |
| Authors | Zhichao Hu, Elahe Rahimtoroghi, Marilyn A Walker |
| Abstract | Human understanding of narrative is mainly driven by reasoning about causal relations between events and thus recognizing them is a key capability for computational models of language understanding. Computational work in this area has approached this via two different routes: by focusing on acquiring a knowledge base of common causal relations between events, or by attempting to understand a particular story or macro-event, along with its storyline. In this position paper, we focus on knowledge acquisition approach and claim that newswire is a relatively poor source for learning fine-grained causal relations between everyday events. We describe experiments using an unsupervised method to learn causal relations between events in the narrative genres of first-person narratives and film scene descriptions. We show that our method learns fine-grained causal relations, judged by humans as likely to be causal over 80% of the time. We also demonstrate that the learned event pairs do not exist in publicly available event-pair datasets extracted from newswire. |
| Tasks | |
| Published | 2017-08-30 |
| URL | http://arxiv.org/abs/1708.09453v1 |
| http://arxiv.org/pdf/1708.09453v1.pdf | |
| PWC | https://paperswithcode.com/paper/inference-of-fine-grained-event-causality |
| Repo | |
| Framework | |
Clonal analysis of newborn hippocampal dentate granule cell proliferation and development in temporal lobe epilepsy
| Title | Clonal analysis of newborn hippocampal dentate granule cell proliferation and development in temporal lobe epilepsy |
| Authors | Shatrunjai P. Singh, Candi L. LaSarge, Amen An, John J. McAuliffe, Steve C. Danzer |
| Abstract | Hippocampal dentate granule cells are among the few neuronal cell types generated throughout adult life in mammals. In the normal brain, new granule cells are generated from progenitors in the subgranular zone and integrate in a typical fashion. During the development of epilepsy, granule cell integration is profoundly altered. The new cells migrate to ectopic locations and develop misoriented basal dendrites. Although it has been established that these abnormal cells are newly generated, it is not known whether they arise ubiquitously throughout the progenitor cell pool or are derived from a smaller number of bad actor progenitors. To explore this question, we conducted a clonal analysis study in mice expressing the Brainbow fluorescent protein reporter construct in dentate granule cell progenitors. Mice were examined 2 months after pilocarpine-induced status epilepticus, a treatment that leads to the development of epilepsy. Brain sections were rendered translucent so that entire hippocampi could be reconstructed and all fluorescently labeled cells identified. Our findings reveal that a small number of progenitors produce the majority of ectopic cells following status epilepticus, indicating that either the affected progenitors or their local microenvironments have become pathological. By contrast, granule cells with basal dendrites were equally distributed among clonal groups. This indicates that these progenitors can produce normal cells and suggests that global factors sporadically disrupt the dendritic development of some new cells. Together, these findings strongly predict that distinct mechanisms regulate different aspects |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.08063v1 |
| http://arxiv.org/pdf/1711.08063v1.pdf | |
| PWC | https://paperswithcode.com/paper/clonal-analysis-of-newborn-hippocampal |
| Repo | |
| Framework | |
Large-Scale Goodness Polarity Lexicons for Community Question Answering
| Title | Large-Scale Goodness Polarity Lexicons for Community Question Answering |
| Authors | Todor Mihaylov, Daniel Belchev, Yasen Kiprov, Ivan Koychev, Preslav Nakov |
| Abstract | We transfer a key idea from the field of sentiment analysis to a new domain: community question answering (cQA). The cQA task we are interested in is the following: given a question and a thread of comments, we want to re-rank the comments so that the ones that are good answers to the question would be ranked higher than the bad ones. We notice that good vs. bad comments use specific vocabulary and that one can often predict the goodness/badness of a comment even ignoring the question, based on the comment contents only. This leads us to the idea to build a good/bad polarity lexicon as an analogy to the positive/negative sentiment polarity lexicons, commonly used in sentiment analysis. In particular, we use pointwise mutual information in order to build large-scale goodness polarity lexicons in a semi-supervised manner starting with a small number of initial seeds. The evaluation results show an improvement of 0.7 MAP points absolute over a very strong baseline and state-of-the art performance on SemEval-2016 Task 3. |
| Tasks | Community Question Answering, Question Answering, Sentiment Analysis |
| Published | 2017-07-20 |
| URL | http://arxiv.org/abs/1707.06378v1 |
| http://arxiv.org/pdf/1707.06378v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-goodness-polarity-lexicons-for |
| Repo | |
| Framework | |
Dimension Estimation Using Random Connection Models
| Title | Dimension Estimation Using Random Connection Models |
| Authors | Paulo Serra, Michel Mandjes |
| Abstract | Information about intrinsic dimension is crucial to perform dimensionality reduction, compress information, design efficient algorithms, and do statistical adaptation. In this paper we propose an estimator for the intrinsic dimension of a data set. The estimator is based on binary neighbourhood information about the observations in the form of two adjacency matrices, and does not require any explicit distance information. The underlying graph is modelled according to a subset of a specific random connection model, sometimes referred to as the Poisson blob model. Computationally the estimator scales like n log n, and we specify its asymptotic distribution and rate of convergence. A simulation study on both real and simulated data shows that our approach compares favourably with some competing methods from the literature, including approaches that rely on distance information. |
| Tasks | Dimensionality Reduction |
| Published | 2017-11-08 |
| URL | http://arxiv.org/abs/1711.02876v1 |
| http://arxiv.org/pdf/1711.02876v1.pdf | |
| PWC | https://paperswithcode.com/paper/dimension-estimation-using-random-connection |
| Repo | |
| Framework | |
Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks
| Title | Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks |
| Authors | Cem M. Deniz, Siyuan Xiang, Spencer Hallyburton, Arakua Welbeck, James S. Babb, Stephen Honig, Kyunghyun Cho, Gregory Chang |
| Abstract | Magnetic resonance imaging (MRI) has been proposed as a complimentary method to measure bone quality and assess fracture risk. However, manual segmentation of MR images of bone is time-consuming, limiting the use of MRI measurements in the clinical practice. The purpose of this paper is to present an automatic proximal femur segmentation method that is based on deep convolutional neural networks (CNNs). This study had institutional review board approval and written informed consent was obtained from all subjects. A dataset of volumetric structural MR images of the proximal femur from 86 subject were manually-segmented by an expert. We performed experiments by training two different CNN architectures with multiple number of initial feature maps and layers, and tested their segmentation performance against the gold standard of manual segmentations using four-fold cross-validation. Automatic segmentation of the proximal femur achieved a high dice similarity score of 0.94$\pm$0.05 with precision = 0.95$\pm$0.02, and recall = 0.94$\pm$0.08 using a CNN architecture based on 3D convolution exceeding the performance of 2D CNNs. The high segmentation accuracy provided by CNNs has the potential to help bring the use of structural MRI measurements of bone quality into clinical practice for management of osteoporosis. |
| Tasks | |
| Published | 2017-04-20 |
| URL | http://arxiv.org/abs/1704.06176v5 |
| http://arxiv.org/pdf/1704.06176v5.pdf | |
| PWC | https://paperswithcode.com/paper/segmentation-of-the-proximal-femur-from-mr |
| Repo | |
| Framework | |
Health Analytics: a systematic review of approaches to detect phenotype cohorts using electronic health records
| Title | Health Analytics: a systematic review of approaches to detect phenotype cohorts using electronic health records |
| Authors | Norman Hiob, Stefan Lessmann |
| Abstract | The paper presents a systematic review of state-of-the-art approaches to identify patient cohorts using electronic health records. It gives a comprehensive overview of the most commonly de-tected phenotypes and its underlying data sets. Special attention is given to preprocessing of in-put data and the different modeling approaches. The literature review confirms natural language processing to be a promising approach for electronic phenotyping. However, accessibility and lack of natural language process standards for medical texts remain a challenge. Future research should develop such standards and further investigate which machine learning approaches are best suited to which type of medical data. |
| Tasks | |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07425v1 |
| http://arxiv.org/pdf/1707.07425v1.pdf | |
| PWC | https://paperswithcode.com/paper/health-analytics-a-systematic-review-of |
| Repo | |
| Framework | |
Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning
| Title | Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning |
| Authors | Yuanlong Li, Yonggang Wen, Kyle Guan, Dacheng Tao |
| Abstract | Cooling system plays a critical role in a modern data center (DC). Developing an optimal control policy for DC cooling system is a challenging task. The prevailing approaches often rely on approximating system models that are built upon the knowledge of mechanical cooling, electrical and thermal management, which is difficult to design and may lead to sub-optimal or unstable performances. In this paper, we propose utilizing the large amount of monitoring data in DC to optimize the control policy. To do so, we cast the cooling control policy design into an energy cost minimization problem with temperature constraints, and tap it into the emerging deep reinforcement learning (DRL) framework. Specifically, we propose an end-to-end cooling control algorithm (CCA) that is based on the actor-critic framework and an off-policy offline version of the deep deterministic policy gradient (DDPG) algorithm. In the proposed CCA, an evaluation network is trained to predict an energy cost counter penalized by the cooling status of the DC room, and a policy network is trained to predict optimized control settings when gave the current load and weather information. The proposed algorithm is evaluated on the EnergyPlus simulation platform and on a real data trace collected from the National Super Computing Centre (NSCC) of Singapore. Our results show that the proposed CCA can achieve about 11% cooling cost saving on the simulation platform compared with a manually configured baseline control algorithm. In the trace-based study, we propose a de-underestimation validation mechanism as we cannot directly test the algorithm on a real DC. Even though with DUE the results are conservative, we can still achieve about 15% cooling energy saving on the NSCC data trace if we set the inlet temperature threshold at 26.6 degree Celsius. |
| Tasks | |
| Published | 2017-09-15 |
| URL | http://arxiv.org/abs/1709.05077v4 |
| http://arxiv.org/pdf/1709.05077v4.pdf | |
| PWC | https://paperswithcode.com/paper/transforming-cooling-optimization-for-green |
| Repo | |
| Framework | |
Dual-reference Face Retrieval
| Title | Dual-reference Face Retrieval |
| Authors | BingZhang Hu, Feng Zheng, Ling Shao |
| Abstract | Face retrieval has received much attention over the past few decades, and many efforts have been made in retrieving face images against pose, illumination, and expression variations. However, the conventional works fail to meet the requirements of a potential and novel task — retrieving a person’s face image at a specific age, especially when the specific ‘age’ is not given as a numeral, i.e. ‘retrieving someone’s image at the similar age period shown by another person’s image’. To tackle this problem, we propose a dual reference face retrieval framework in this paper, where the system takes two inputs: an identity reference image which indicates the target identity and an age reference image which reflects the target age. In our framework, the raw images are first projected on a joint manifold, which preserves both the age and identity locality. Then two similarity metrics of age and identity are exploited and optimized by utilizing our proposed quartet-based model. The experiments show promising results, outperforming hierarchical methods. |
| Tasks | |
| Published | 2017-06-02 |
| URL | http://arxiv.org/abs/1706.00631v2 |
| http://arxiv.org/pdf/1706.00631v2.pdf | |
| PWC | https://paperswithcode.com/paper/dual-reference-face-retrieval |
| Repo | |
| Framework | |
Towards High Performance Video Object Detection
| Title | Towards High Performance Video Object Detection |
| Authors | Xizhou Zhu, Jifeng Dai, Lu Yuan, Yichen Wei |
| Abstract | There has been significant progresses for image object detection in recent years. Nevertheless, video object detection has received little attention, although it is more challenging and more important in practical scenarios. Built upon the recent works, this work proposes a unified approach based on the principle of multi-frame end-to-end learning of features and cross-frame motion. Our approach extends prior works with three new techniques and steadily pushes forward the performance envelope (speed-accuracy tradeoff), towards high performance video object detection. |
| Tasks | Object Detection, Video Object Detection |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1711.11577v1 |
| http://arxiv.org/pdf/1711.11577v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-high-performance-video-object-1 |
| Repo | |
| Framework | |
A note on the uniqueness of models in social abstract argumentation
| Title | A note on the uniqueness of models in social abstract argumentation |
| Authors | Leila Amgoud, Elise Bonzon, Marco Correia, Jorge Cruz, Jérôme Delobelle, Sébastien Konieczny, João Leite, Alexis Martin, Nicolas Maudet, Srdjan Vesic |
| Abstract | Social abstract argumentation is a principled way to assign values to conflicting (weighted) arguments. In this note we discuss the important property of the uniqueness of the model. |
| Tasks | Abstract Argumentation |
| Published | 2017-05-09 |
| URL | http://arxiv.org/abs/1705.03381v1 |
| http://arxiv.org/pdf/1705.03381v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-note-on-the-uniqueness-of-models-in-social |
| Repo | |
| Framework | |
Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networks
| Title | Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networks |
| Authors | Pichao Wang, Wanqing Li, Zhimin Gao, Yuyao Zhang, Chang Tang, Philip Ogunbona |
| Abstract | Scene flow describes the motion of 3D objects in real world and potentially could be the basis of a good feature for 3D action recognition. However, its use for action recognition, especially in the context of convolutional neural networks (ConvNets), has not been previously studied. In this paper, we propose the extraction and use of scene flow for action recognition from RGB-D data. Previous works have considered the depth and RGB modalities as separate channels and extract features for later fusion. We take a different approach and consider the modalities as one entity, thus allowing feature extraction for action recognition at the beginning. Two key questions about the use of scene flow for action recognition are addressed: how to organize the scene flow vectors and how to represent the long term dynamics of videos based on scene flow. In order to calculate the scene flow correctly on the available datasets, we propose an effective self-calibration method to align the RGB and depth data spatially without knowledge of the camera parameters. Based on the scene flow vectors, we propose a new representation, namely, Scene Flow to Action Map (SFAM), that describes several long term spatio-temporal dynamics for action recognition. We adopt a channel transform kernel to transform the scene flow vectors to an optimal color space analogous to RGB. This transformation takes better advantage of the trained ConvNets models over ImageNet. Experimental results indicate that this new representation can surpass the performance of state-of-the-art methods on two large public datasets. |
| Tasks | 3D Human Action Recognition, Calibration, Temporal Action Localization |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1702.08652v3 |
| http://arxiv.org/pdf/1702.08652v3.pdf | |
| PWC | https://paperswithcode.com/paper/scene-flow-to-action-map-a-new-representation |
| Repo | |
| Framework | |
Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks
| Title | Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks |
| Authors | Ziming Zhang, Matthew Brand |
| Abstract | By lifting the ReLU function into a higher dimensional space, we develop a smooth multi-convex formulation for training feed-forward deep neural networks (DNNs). This allows us to develop a block coordinate descent (BCD) training algorithm consisting of a sequence of numerically well-behaved convex optimizations. Using ideas from proximal point methods in convex analysis, we prove that this BCD algorithm will converge globally to a stationary point with R-linear convergence rate of order one. In experiments with the MNIST database, DNNs trained with this BCD algorithm consistently yielded better test-set error rates than identical DNN architectures trained via all the stochastic gradient descent (SGD) variants in the Caffe toolbox. |
| Tasks | |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1711.07354v1 |
| http://arxiv.org/pdf/1711.07354v1.pdf | |
| PWC | https://paperswithcode.com/paper/convergent-block-coordinate-descent-for |
| Repo | |
| Framework | |
SpectralLeader: Online Spectral Learning for Single Topic Models
| Title | SpectralLeader: Online Spectral Learning for Single Topic Models |
| Authors | Tong Yu, Branislav Kveton, Zheng Wen, Hung Bui, Ole J. Mengshoel |
| Abstract | We study the problem of learning a latent variable model from a stream of data. Latent variable models are popular in practice because they can explain observed data in terms of unobserved concepts. These models have been traditionally studied in the offline setting. In the online setting, on the other hand, the online EM is arguably the most popular algorithm for learning latent variable models. Although the online EM is computationally efficient, it typically converges to a local optimum. In this work, we develop a new online learning algorithm for latent variable models, which we call SpectralLeader. SpectralLeader always converges to the global optimum, and we derive a sublinear upper bound on its $n$-step regret in the bag-of-words model. In both synthetic and real-world experiments, we show that SpectralLeader performs similarly to or better than the online EM with tuned hyper-parameters. |
| Tasks | Latent Variable Models, Topic Models |
| Published | 2017-09-21 |
| URL | http://arxiv.org/abs/1709.07172v4 |
| http://arxiv.org/pdf/1709.07172v4.pdf | |
| PWC | https://paperswithcode.com/paper/spectralleader-online-spectral-learning-for |
| Repo | |
| Framework | |
Asymptotic Bayesian Generalization Error in Latent Dirichlet Allocation and Stochastic Matrix Factorization
| Title | Asymptotic Bayesian Generalization Error in Latent Dirichlet Allocation and Stochastic Matrix Factorization |
| Authors | Naoki Hayashi, Sumio Watanabe |
| Abstract | Latent Dirichlet allocation (LDA) is useful in document analysis, image processing, and many information systems; however, its generalization performance has been left unknown because it is a singular learning machine to which regular statistical theory can not be applied. Stochastic matrix factorization (SMF) is a restricted matrix factorization in which matrix factors are stochastic; the column of the matrix is in a simplex. SMF is being applied to image recognition and text mining. We can understand SMF as a statistical model by which a stochastic matrix of given data is represented by a product of two stochastic matrices, whose generalization performance has also been left unknown because of non-regularity. In this paper, by using an algebraic and geometric method, we show the analytic equivalence of LDA and SMF, both of which have the same real log canonical threshold (RLCT), resulting in that they asymptotically have the same Bayesian generalization error and the same log marginal likelihood. Moreover, we derive the upper bound of the RLCT and prove that it is smaller than the dimension of the parameter divided by two, hence the Bayesian generalization errors of them are smaller than those of regular statistical models. |
| Tasks | Bayesian Inference, Topic Models |
| Published | 2017-09-13 |
| URL | https://arxiv.org/abs/1709.04212v8 |
| https://arxiv.org/pdf/1709.04212v8.pdf | |
| PWC | https://paperswithcode.com/paper/asymptotic-bayesian-generalization-error-in |
| Repo | |
| Framework | |
