Paper Group ANR 220
Classical Statistics and Statistical Learning in Imaging Neuroscience. Syntactic Enhancement to VSIMM for Roadmap Based Anomalous Trajectory Detection: A Natural Language Processing Approach. Cutting out the middleman: measuring nuclear area in histopathology slides without segmentation. A Tour of TensorFlow. End-to-End Localization and Ranking for …
Classical Statistics and Statistical Learning in Imaging Neuroscience
| Title | Classical Statistics and Statistical Learning in Imaging Neuroscience |
| Authors | Danilo Bzdok |
| Abstract | Neuroimaging research has predominantly drawn conclusions based on classical statistics, including null-hypothesis testing, t-tests, and ANOVA. Throughout recent years, statistical learning methods enjoy increasing popularity, including cross-validation, pattern classification, and sparsity-inducing regression. These two methodological families used for neuroimaging data analysis can be viewed as two extremes of a continuum. Yet, they originated from different historical contexts, build on different theories, rest on different assumptions, evaluate different outcome metrics, and permit different conclusions. This paper portrays commonalities and differences between classical statistics and statistical learning with their relation to neuroimaging research. The conceptual implications are illustrated in three common analysis scenarios. It is thus tried to resolve possible confusion between classical hypothesis testing and data-guided model estimation by discussing their ramifications for the neuroimaging access to neurobiology. |
| Tasks | |
| Published | 2016-03-06 |
| URL | http://arxiv.org/abs/1603.01857v2 |
| http://arxiv.org/pdf/1603.01857v2.pdf | |
| PWC | https://paperswithcode.com/paper/classical-statistics-and-statistical-learning |
| Repo | |
| Framework | |
Syntactic Enhancement to VSIMM for Roadmap Based Anomalous Trajectory Detection: A Natural Language Processing Approach
| Title | Syntactic Enhancement to VSIMM for Roadmap Based Anomalous Trajectory Detection: A Natural Language Processing Approach |
| Authors | Vikram Krishnamurthy, Sijia Gao |
| Abstract | The aim of syntactic tracking is to classify spatio-temporal patterns of a target’s motion using natural language processing models. In this paper, we generalize earlier work by considering a constrained stochastic context free grammar (CSCFG) for modeling patterns confined to a roadmap. The constrained grammar facilitates modeling specific directions and road names in a roadmap. We present a novel particle filtering algorithm that exploits the CSCFG model for estimating the target’s patterns. This meta-level algorithm operates in conjunction with a base-level tracking algorithm. Extensive numerical results using simulated ground moving target indicator (GMTI) radar measurements show substantial improvement in target tracking accuracy. |
| Tasks | |
| Published | 2016-11-10 |
| URL | http://arxiv.org/abs/1611.03466v3 |
| http://arxiv.org/pdf/1611.03466v3.pdf | |
| PWC | https://paperswithcode.com/paper/syntactic-enhancement-to-vsimm-for-roadmap |
| Repo | |
| Framework | |
Cutting out the middleman: measuring nuclear area in histopathology slides without segmentation
| Title | Cutting out the middleman: measuring nuclear area in histopathology slides without segmentation |
| Authors | Mitko Veta, Paul J. van Diest, Josien P. W. Pluim |
| Abstract | The size of nuclei in histological preparations from excised breast tumors is predictive of patient outcome (large nuclei indicate poor outcome). Pathologists take into account nuclear size when performing breast cancer grading. In addition, the mean nuclear area (MNA) has been shown to have independent prognostic value. The straightforward approach to measuring nuclear size is by performing nuclei segmentation. We hypothesize that given an image of a tumor region with known nuclei locations, the area of the individual nuclei and region statistics such as the MNA can be reliably computed directly from the image data by employing a machine learning model, without the intermediate step of nuclei segmentation. Towards this goal, we train a deep convolutional neural network model that is applied locally at each nucleus location, and can reliably measure the area of the individual nuclei and the MNA. Furthermore, we show how such an approach can be extended to perform combined nuclei detection and measurement, which is reminiscent of granulometry. |
| Tasks | |
| Published | 2016-06-20 |
| URL | http://arxiv.org/abs/1606.06127v1 |
| http://arxiv.org/pdf/1606.06127v1.pdf | |
| PWC | https://paperswithcode.com/paper/cutting-out-the-middleman-measuring-nuclear |
| Repo | |
| Framework | |
A Tour of TensorFlow
| Title | A Tour of TensorFlow |
| Authors | Peter Goldsborough |
| Abstract | Deep learning is a branch of artificial intelligence employing deep neural network architectures that has significantly advanced the state-of-the-art in computer vision, speech recognition, natural language processing and other domains. In November 2015, Google released $\textit{TensorFlow}$, an open source deep learning software library for defining, training and deploying machine learning models. In this paper, we review TensorFlow and put it in context of modern deep learning concepts and software. We discuss its basic computational paradigms and distributed execution model, its programming interface as well as accompanying visualization toolkits. We then compare TensorFlow to alternative libraries such as Theano, Torch or Caffe on a qualitative as well as quantitative basis and finally comment on observed use-cases of TensorFlow in academia and industry. |
| Tasks | Speech Recognition |
| Published | 2016-10-01 |
| URL | http://arxiv.org/abs/1610.01178v1 |
| http://arxiv.org/pdf/1610.01178v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-tour-of-tensorflow |
| Repo | |
| Framework | |
End-to-End Localization and Ranking for Relative Attributes
| Title | End-to-End Localization and Ranking for Relative Attributes |
| Authors | Krishna Kumar Singh, Yong Jae Lee |
| Abstract | We propose an end-to-end deep convolutional network to simultaneously localize and rank relative visual attributes, given only weakly-supervised pairwise image comparisons. Unlike previous methods, our network jointly learns the attribute’s features, localization, and ranker. The localization module of our network discovers the most informative image region for the attribute, which is then used by the ranking module to learn a ranking model of the attribute. Our end-to-end framework also significantly speeds up processing and is much faster than previous methods. We show state-of-the-art ranking results on various relative attribute datasets, and our qualitative localization results clearly demonstrate our network’s ability to learn meaningful image patches. |
| Tasks | |
| Published | 2016-08-09 |
| URL | http://arxiv.org/abs/1608.02676v1 |
| http://arxiv.org/pdf/1608.02676v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-localization-and-ranking-for |
| Repo | |
| Framework | |
Syntactic Phylogenetic Trees
| Title | Syntactic Phylogenetic Trees |
| Authors | Kevin Shu, Sharjeel Aziz, Vy-Luan Huynh, David Warrick, Matilde Marcolli |
| Abstract | In this paper we identify several serious problems that arise in the use of syntactic data from the SSWL database for the purpose of computational phylogenetic reconstruction. We show that the most naive approach fails to produce reliable linguistic phylogenetic trees. We identify some of the sources of the observed problems and we discuss how they may be, at least partly, corrected by using additional information, such as prior subdivision into language families and subfamilies, and a better use of the information about ancient languages. We also describe how the use of phylogenetic algebraic geometry can help in estimating to what extent the probability distribution at the leaves of the phylogenetic tree obtained from the SSWL data can be considered reliable, by testing it on phylogenetic trees established by other forms of linguistic analysis. In simple examples, we find that, after restricting to smaller language subfamilies and considering only those SSWL parameters that are fully mapped for the whole subfamily, the SSWL data match extremely well reliable phylogenetic trees, according to the evaluation of phylogenetic invariants. This is a promising sign for the use of SSWL data for linguistic phylogenetics. |
| Tasks | |
| Published | 2016-07-10 |
| URL | http://arxiv.org/abs/1607.02791v1 |
| http://arxiv.org/pdf/1607.02791v1.pdf | |
| PWC | https://paperswithcode.com/paper/syntactic-phylogenetic-trees |
| Repo | |
| Framework | |
Learning Bounded Treewidth Bayesian Networks with Thousands of Variables
| Title | Learning Bounded Treewidth Bayesian Networks with Thousands of Variables |
| Authors | Mauro Scanagatta, Giorgio Corani, Cassio P. de Campos, Marco Zaffalon |
| Abstract | We present a method for learning treewidth-bounded Bayesian networks from data sets containing thousands of variables. Bounding the treewidth of a Bayesian greatly reduces the complexity of inferences. Yet, being a global property of the graph, it considerably increases the difficulty of the learning process. We propose a novel algorithm for this task, able to scale to large domains and large treewidths. Our novel approach consistently outperforms the state of the art on data sets with up to ten thousand variables. |
| Tasks | |
| Published | 2016-05-11 |
| URL | http://arxiv.org/abs/1605.03392v1 |
| http://arxiv.org/pdf/1605.03392v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-bounded-treewidth-bayesian-networks |
| Repo | |
| Framework | |
Named Entity Recognition for Novel Types by Transfer Learning
| Title | Named Entity Recognition for Novel Types by Transfer Learning |
| Authors | Lizhen Qu, Gabriela Ferraro, Liyuan Zhou, Weiwei Hou, Timothy Baldwin |
| Abstract | In named entity recognition, we often don’t have a large in-domain training corpus or a knowledge base with adequate coverage to train a model directly. In this paper, we propose a method where, given training data in a related domain with similar (but not identical) named entity (NE) types and a small amount of in-domain training data, we use transfer learning to learn a domain-specific NE model. That is, the novelty in the task setup is that we assume not just domain mismatch, but also label mismatch. |
| Tasks | Named Entity Recognition, Transfer Learning |
| Published | 2016-10-31 |
| URL | http://arxiv.org/abs/1610.09914v1 |
| http://arxiv.org/pdf/1610.09914v1.pdf | |
| PWC | https://paperswithcode.com/paper/named-entity-recognition-for-novel-types-by |
| Repo | |
| Framework | |
Multiple scan data association by convex variational inference
| Title | Multiple scan data association by convex variational inference |
| Authors | Jason L. Williams, Roslyn A. Lau |
| Abstract | Data association, the reasoning over correspondence between targets and measurements, is a problem of fundamental importance in target tracking. Recently, belief propagation (BP) has emerged as a promising method for estimating the marginal probabilities of measurement to target association, providing fast, accurate estimates. The excellent performance of BP in the particular formulation used may be attributed to the convexity of the underlying free energy which it implicitly optimises. This paper studies multiple scan data association problems, i.e., problems that reason over correspondence between targets and several sets of measurements, which may correspond to different sensors or different time steps. We find that the multiple scan extension of the single scan BP formulation is non-convex and demonstrate the undesirable behaviour that can result. A convex free energy is constructed using the recently proposed fractional free energy (FFE). A convergent, BP-like algorithm is provided for the single scan FFE, and employed in optimising the multiple scan free energy using primal-dual coordinate ascent. Finally, based on a variational interpretation of joint probabilistic data association (JPDA), we develop a sequential variant of the algorithm that is similar to JPDA, but retains consistency constraints from prior scans. The performance of the proposed methods is demonstrated on a bearings only target localisation problem. |
| Tasks | |
| Published | 2016-07-27 |
| URL | http://arxiv.org/abs/1607.07942v2 |
| http://arxiv.org/pdf/1607.07942v2.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-scan-data-association-by-convex |
| Repo | |
| Framework | |
Improving Twitter Sentiment Classification via Multi-Level Sentiment-Enriched Word Embeddings
| Title | Improving Twitter Sentiment Classification via Multi-Level Sentiment-Enriched Word Embeddings |
| Authors | Shufeng Xiong |
| Abstract | Most of existing work learn sentiment-specific word representation for improving Twitter sentiment classification, which encoded both n-gram and distant supervised tweet sentiment information in learning process. They assume all words within a tweet have the same sentiment polarity as the whole tweet, which ignores the word its own sentiment polarity. To address this problem, we propose to learn sentiment-specific word embedding by exploiting both lexicon resource and distant supervised information. We develop a multi-level sentiment-enriched word embedding learning method, which uses parallel asymmetric neural network to model n-gram, word level sentiment and tweet level sentiment in learning process. Experiments on standard benchmarks show our approach outperforms state-of-the-art methods. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2016-11-01 |
| URL | http://arxiv.org/abs/1611.00126v1 |
| http://arxiv.org/pdf/1611.00126v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-twitter-sentiment-classification |
| Repo | |
| Framework | |
Latent Attention For If-Then Program Synthesis
| Title | Latent Attention For If-Then Program Synthesis |
| Authors | Xinyun Chen, Chang Liu, Richard Shin, Dawn Song, Mingcheng Chen |
| Abstract | Automatic translation from natural language descriptions into programs is a longstanding challenging problem. In this work, we consider a simple yet important sub-problem: translation from textual descriptions to If-Then programs. We devise a novel neural network architecture for this task which we train end-to-end. Specifically, we introduce Latent Attention, which computes multiplicative weights for the words in the description in a two-stage process with the goal of better leveraging the natural language structures that indicate the relevant parts for predicting program elements. Our architecture reduces the error rate by 28.57% compared to prior art. We also propose a one-shot learning scenario of If-Then program synthesis and simulate it with our existing dataset. We demonstrate a variation on the training procedure for this scenario that outperforms the original procedure, significantly closing the gap to the model trained with all data. |
| Tasks | One-Shot Learning, Program Synthesis |
| Published | 2016-11-07 |
| URL | http://arxiv.org/abs/1611.01867v1 |
| http://arxiv.org/pdf/1611.01867v1.pdf | |
| PWC | https://paperswithcode.com/paper/latent-attention-for-if-then-program |
| Repo | |
| Framework | |
Zero-Shot Hashing via Transferring Supervised Knowledge
| Title | Zero-Shot Hashing via Transferring Supervised Knowledge |
| Authors | Yang Yang, Weilun Chen, Yadan Luo, Fumin Shen, Jie Shao, Heng Tao Shen |
| Abstract | Hashing has shown its efficiency and effectiveness in facilitating large-scale multimedia applications. Supervised knowledge e.g. semantic labels or pair-wise relationship) associated to data is capable of significantly improving the quality of hash codes and hash functions. However, confronted with the rapid growth of newly-emerging concepts and multimedia data on the Web, existing supervised hashing approaches may easily suffer from the scarcity and validity of supervised information due to the expensive cost of manual labelling. In this paper, we propose a novel hashing scheme, termed \emph{zero-shot hashing} (ZSH), which compresses images of “unseen” categories to binary codes with hash functions learned from limited training data of “seen” categories. Specifically, we project independent data labels i.e. 0/1-form label vectors) into semantic embedding space, where semantic relationships among all the labels can be precisely characterized and thus seen supervised knowledge can be transferred to unseen classes. Moreover, in order to cope with the semantic shift problem, we rotate the embedded space to more suitably align the embedded semantics with the low-level visual feature space, thereby alleviating the influence of semantic gap. In the meantime, to exert positive effects on learning high-quality hash functions, we further propose to preserve local structural property and discrete nature in binary codes. Besides, we develop an efficient alternating algorithm to solve the ZSH model. Extensive experiments conducted on various real-life datasets show the superior zero-shot image retrieval performance of ZSH as compared to several state-of-the-art hashing methods. |
| Tasks | Image Retrieval |
| Published | 2016-06-16 |
| URL | http://arxiv.org/abs/1606.05032v1 |
| http://arxiv.org/pdf/1606.05032v1.pdf | |
| PWC | https://paperswithcode.com/paper/zero-shot-hashing-via-transferring-supervised |
| Repo | |
| Framework | |
Supervised Attentions for Neural Machine Translation
| Title | Supervised Attentions for Neural Machine Translation |
| Authors | Haitao Mi, Zhiguo Wang, Abe Ittycheriah |
| Abstract | In this paper, we improve the attention or alignment accuracy of neural machine translation by utilizing the alignments of training sentence pairs. We simply compute the distance between the machine attentions and the “true” alignments, and minimize this cost in the training procedure. Our experiments on large-scale Chinese-to-English task show that our model improves both translation and alignment qualities significantly over the large-vocabulary neural machine translation system, and even beats a state-of-the-art traditional syntax-based system. |
| Tasks | Machine Translation |
| Published | 2016-07-30 |
| URL | http://arxiv.org/abs/1608.00112v1 |
| http://arxiv.org/pdf/1608.00112v1.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-attentions-for-neural-machine |
| Repo | |
| Framework | |
Empirical Evaluation of Real World Tournaments
| Title | Empirical Evaluation of Real World Tournaments |
| Authors | Nicholas Mattei, Toby Walsh |
| Abstract | Computational Social Choice (ComSoc) is a rapidly developing field at the intersection of computer science, economics, social choice, and political science. The study of tournaments is fundamental to ComSoc and many results have been published about tournament solution sets and reasoning in tournaments. Theoretical results in ComSoc tend to be worst case and tell us little about performance in practice. To this end we detail some experiments on tournaments using real wold data from soccer and tennis. We make three main contributions to the understanding of tournaments using real world data from English Premier League, the German Bundesliga, and the ATP World Tour: (1) we find that the NP-hard question of finding a seeding for which a given team can win a tournament is easily solvable in real world instances, (2) using detailed and principled methodology from statistical physics we show that our real world data obeys a log-normal distribution; and (3) leveraging our log-normal distribution result and using robust statistical methods, we show that the popular Condorcet Random (CR) tournament model does not generate realistic tournament data. |
| Tasks | |
| Published | 2016-08-03 |
| URL | http://arxiv.org/abs/1608.01039v1 |
| http://arxiv.org/pdf/1608.01039v1.pdf | |
| PWC | https://paperswithcode.com/paper/empirical-evaluation-of-real-world |
| Repo | |
| Framework | |
Nonnegative Matrix Factorization Requires Irrationality
| Title | Nonnegative Matrix Factorization Requires Irrationality |
| Authors | Dmitry Chistikov, Stefan Kiefer, Ines Marušić, Mahsa Shirmohammadi, James Worrell |
| Abstract | Nonnegative matrix factorization (NMF) is the problem of decomposing a given nonnegative $n \times m$ matrix $M$ into a product of a nonnegative $n \times d$ matrix $W$ and a nonnegative $d \times m$ matrix $H$. A longstanding open question, posed by Cohen and Rothblum in 1993, is whether a rational matrix $M$ always has an NMF of minimal inner dimension $d$ whose factors $W$ and $H$ are also rational. We answer this question negatively, by exhibiting a matrix for which $W$ and $H$ require irrational entries. |
| Tasks | |
| Published | 2016-05-22 |
| URL | http://arxiv.org/abs/1605.06848v2 |
| http://arxiv.org/pdf/1605.06848v2.pdf | |
| PWC | https://paperswithcode.com/paper/nonnegative-matrix-factorization-requires |
| Repo | |
| Framework | |
