Paper Group ANR 791
Machine learning methods for histopathological image analysis. Language Use Matters: Analysis of the Linguistic Structure of Question Texts Can Characterize Answerability in Quora. Hierarchical Temporal Representation in Linear Reservoir Computing. Transfer learning for diagnosis of congenital abnormalities of the kidney and urinary tract in childr …
Machine learning methods for histopathological image analysis
| Title | Machine learning methods for histopathological image analysis |
| Authors | Daisuke Komura, Shumpei Ishikawa |
| Abstract | Abundant accumulation of digital histopathological images has led to the increased demand for their analysis, such as computer-aided diagnosis using machine learning techniques. However, digital pathological images and related tasks have some issues to be considered. In this mini-review, we introduce the application of digital pathological image analysis using machine learning algorithms, address some problems specific to such analysis, and propose possible solutions. |
| Tasks | |
| Published | 2017-09-04 |
| URL | http://arxiv.org/abs/1709.00786v2 |
| http://arxiv.org/pdf/1709.00786v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-methods-for |
| Repo | |
| Framework | |
Language Use Matters: Analysis of the Linguistic Structure of Question Texts Can Characterize Answerability in Quora
| Title | Language Use Matters: Analysis of the Linguistic Structure of Question Texts Can Characterize Answerability in Quora |
| Authors | Suman Kalyan Maity, Aman Kharb, Animesh Mukherjee |
| Abstract | Quora is one of the most popular community Q&A sites of recent times. However, many question posts on this Q&A site often do not get answered. In this paper, we quantify various linguistic activities that discriminates an answered question from an unanswered one. Our central finding is that the way users use language while writing the question text can be a very effective means to characterize answerability. This characterization helps us to predict early if a question remaining unanswered for a specific time period t will eventually be answered or not and achieve an accuracy of 76.26% (t = 1 month) and 68.33% (t = 3 months). Notably, features representing the language use patterns of the users are most discriminative and alone account for an accuracy of 74.18%. We also compare our method with some of the similar works (Dror et al., Yang et al.) achieving a maximum improvement of ~39% in terms of accuracy. |
| Tasks | |
| Published | 2017-03-11 |
| URL | http://arxiv.org/abs/1703.04001v1 |
| http://arxiv.org/pdf/1703.04001v1.pdf | |
| PWC | https://paperswithcode.com/paper/language-use-matters-analysis-of-the |
| Repo | |
| Framework | |
Hierarchical Temporal Representation in Linear Reservoir Computing
| Title | Hierarchical Temporal Representation in Linear Reservoir Computing |
| Authors | Claudio Gallicchio, Alessio Micheli, Luca Pedrelli |
| Abstract | Recently, studies on deep Reservoir Computing (RC) highlighted the role of layering in deep recurrent neural networks (RNNs). In this paper, the use of linear recurrent units allows us to bring more evidence on the intrinsic hierarchical temporal representation in deep RNNs through frequency analysis applied to the state signals. The potentiality of our approach is assessed on the class of Multiple Superimposed Oscillator tasks. Furthermore, our investigation provides useful insights to open a discussion on the main aspects that characterize the deep learning framework in the temporal domain. |
| Tasks | |
| Published | 2017-05-16 |
| URL | http://arxiv.org/abs/1705.05782v5 |
| http://arxiv.org/pdf/1705.05782v5.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-temporal-representation-in |
| Repo | |
| Framework | |
Transfer learning for diagnosis of congenital abnormalities of the kidney and urinary tract in children based on Ultrasound imaging data
| Title | Transfer learning for diagnosis of congenital abnormalities of the kidney and urinary tract in children based on Ultrasound imaging data |
| Authors | Qiang Zheng, Gregory Tasian, Yong Fan |
| Abstract | Classification of ultrasound (US) kidney images for diagnosis of congenital abnormalities of the kidney and urinary tract (CAKUT) in children is a challenging task. It is desirable to improve existing pattern classification models that are built upon conventional image features. In this study, we propose a transfer learning-based method to extract imaging features from US kidney images in order to improve the CAKUT diagnosis in children. Particularly, a pre-trained deep learning model (imagenet-caffe-alex) is adopted for transfer learning-based feature extraction from 3-channel feature maps computed from US images, including original images, gradient features, and distanced transform features. Support vector machine classifiers are then built upon different sets of features, including the transfer learning features, conventional imaging features, and their combination. Experimental results have demonstrated that the combination of transfer learning features and conventional imaging features yielded the best classification performance for distinguishing CAKUT patients from normal controls based on their US kidney images. |
| Tasks | Transfer Learning |
| Published | 2017-12-31 |
| URL | http://arxiv.org/abs/1801.00224v1 |
| http://arxiv.org/pdf/1801.00224v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-for-diagnosis-of-congenital |
| Repo | |
| Framework | |
Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning
| Title | Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning |
| Authors | Gabriel V. de la Cruz Jr, Yunshu Du, Matthew E. Taylor |
| Abstract | Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images. A drawback of using raw images is that deep RL must learn the state feature representation from the raw images in addition to learning a policy. As a result, deep RL can require a prohibitively large amount of training time and data to reach reasonable performance, making it difficult to use deep RL in real-world applications, especially when data is expensive. In this work, we speed up training by addressing half of what deep RL is trying to solve — learning features. Our approach is to learn some of the important features by pre-training deep RL network’s hidden layers via supervised learning using a small set of human demonstrations. We empirically evaluate our approach using deep Q-network (DQN) and asynchronous advantage actor-critic (A3C) algorithms on the Atari 2600 games of Pong, Freeway, and Beamrider. Our results show that: 1) pre-training with human demonstrations in a supervised learning manner is better at discovering features relative to pre-training naively in DQN, and 2) initializing a deep RL network with a pre-trained model provides a significant improvement in training time even when pre-training from a small number of human demonstrations. |
| Tasks | Atari Games |
| Published | 2017-09-12 |
| URL | http://arxiv.org/abs/1709.04083v2 |
| http://arxiv.org/pdf/1709.04083v2.pdf | |
| PWC | https://paperswithcode.com/paper/pre-training-neural-networks-with-human |
| Repo | |
| Framework | |
BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks
| Title | BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks |
| Authors | Surat Teerapittayanon, Bradley McDanel, H. T. Kung |
| Abstract | Deep neural networks are state of the art methods for many learning tasks due to their ability to extract increasingly better features at each network layer. However, the improved performance of additional layers in a deep network comes at the cost of added latency and energy usage in feedforward inference. As networks continue to get deeper and larger, these costs become more prohibitive for real-time and energy-sensitive applications. To address this issue, we present BranchyNet, a novel deep network architecture that is augmented with additional side branch classifiers. The architecture allows prediction results for a large portion of test samples to exit the network early via these branches when samples can already be inferred with high confidence. BranchyNet exploits the observation that features learned at an early layer of a network may often be sufficient for the classification of many data points. For more difficult samples, which are expected less frequently, BranchyNet will use further or all network layers to provide the best likelihood of correct prediction. We study the BranchyNet architecture using several well-known networks (LeNet, AlexNet, ResNet) and datasets (MNIST, CIFAR10) and show that it can both improve accuracy and significantly reduce the inference time of the network. |
| Tasks | |
| Published | 2017-09-06 |
| URL | http://arxiv.org/abs/1709.01686v1 |
| http://arxiv.org/pdf/1709.01686v1.pdf | |
| PWC | https://paperswithcode.com/paper/branchynet-fast-inference-via-early-exiting |
| Repo | |
| Framework | |
Automatic Classification of Functional Gait Disorders
| Title | Automatic Classification of Functional Gait Disorders |
| Authors | Djordje Slijepcevic, Matthias Zeppelzauer, Anna-Maria Gorgas, Caterine Schwab, Michael Schüller, Arnold Baca, Christian Breiteneder, Brian Horsak |
| Abstract | This article proposes a comprehensive investigation of the automatic classification of functional gait disorders based solely on ground reaction force (GRF) measurements. The aim of the study is twofold: (1) to investigate the suitability of stateof-the-art GRF parameterization techniques (representations) for the discrimination of functional gait disorders; and (2) to provide a first performance baseline for the automated classification of functional gait disorders for a large-scale dataset. The utilized database comprises GRF measurements from 279 patients with gait disorders (GDs) and data from 161 healthy controls (N). Patients were manually classified into four classes with different functional impairments associated with the “hip”, “knee”, “ankle”, and “calcaneus”. Different parameterizations are investigated: GRF parameters, global principal component analysis (PCA)-based representations and a combined representation applying PCA on GRF parameters. The discriminative power of each parameterization for different classes is investigated by linear discriminant analysis (LDA). Based on this analysis, two classification experiments are pursued: (1) distinction between healthy and impaired gait (N vs. GD) and (2) multi-class classification between healthy gait and all four GD classes. Experiments show promising results and reveal among others that several factors, such as imbalanced class cardinalities and varying numbers of measurement sessions per patient have a strong impact on the classification accuracy and therefore need to be taken into account. The results represent a promising first step towards the automated classification of gait disorders and a first performance baseline for future developments in this direction. |
| Tasks | |
| Published | 2017-12-18 |
| URL | http://arxiv.org/abs/1712.06405v2 |
| http://arxiv.org/pdf/1712.06405v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-classification-of-functional-gait |
| Repo | |
| Framework | |
Automating Image Analysis by Annotating Landmarks with Deep Neural Networks
| Title | Automating Image Analysis by Annotating Landmarks with Deep Neural Networks |
| Authors | Mikhail Breslav, Tyson L. Hedrick, Stan Sclaroff, Margrit Betke |
| Abstract | Image and video analysis is often a crucial step in the study of animal behavior and kinematics. Often these analyses require that the position of one or more animal landmarks are annotated (marked) in numerous images. The process of annotating landmarks can require a significant amount of time and tedious labor, which motivates the need for algorithms that can automatically annotate landmarks. In the community of scientists that use image and video analysis to study the 3D flight of animals, there has been a trend of developing more automated approaches for annotating landmarks, yet they fall short of being generally applicable. Inspired by the success of Deep Neural Networks (DNNs) on many problems in the field of computer vision, we investigate how suitable DNNs are for accurate and automatic annotation of landmarks in video datasets representative of those collected by scientists studying animals. Our work shows, through extensive experimentation on videos of hawkmoths, that DNNs are suitable for automatic and accurate landmark localization. In particular, we show that one of our proposed DNNs is more accurate than the current best algorithm for automatic localization of landmarks on hawkmoth videos. Moreover, we demonstrate how these annotations can be used to quantitatively analyze the 3D flight of a hawkmoth. To facilitate the use of DNNs by scientists from many different fields, we provide a self contained explanation of what DNNs are, how they work, and how to apply them to other datasets using the freely available library Caffe and supplemental code that we provide. |
| Tasks | |
| Published | 2017-02-02 |
| URL | http://arxiv.org/abs/1702.00583v1 |
| http://arxiv.org/pdf/1702.00583v1.pdf | |
| PWC | https://paperswithcode.com/paper/automating-image-analysis-by-annotating |
| Repo | |
| Framework | |
Sparse Hierachical Extrapolated Parametric Methods for Cortical Data Analysis
| Title | Sparse Hierachical Extrapolated Parametric Methods for Cortical Data Analysis |
| Authors | Nicolas Honnorat, Christos Davatzikos |
| Abstract | Many neuroimaging studies focus on the cortex, in order to benefit from better signal to noise ratios and reduced computational burden. Cortical data are usually projected onto a reference mesh, where subsequent analyses are carried out. Several multiscale approaches have been proposed for analyzing these surface data, such as spherical harmonics and graph wavelets. As far as we know, however, the hierarchical structure of the template icosahedral meshes used by most neuroimaging software has never been exploited for cortical data factorization. In this paper, we demonstrate how the structure of the ubiquitous icosahedral meshes can be exploited by data factorization methods such as sparse dictionary learning, and we assess the optimization speed-up offered by extrapolation methods in this context. By testing different sparsity-inducing norms, extrapolation methods, and factorization schemes, we compare the performances of eleven methods for analyzing four datasets: two structural and two functional MRI datasets obtained by processing the data publicly available for the hundred unrelated subjects of the Human Connectome Project. Our results demonstrate that, depending on the level of details requested, a speedup of several orders of magnitudes can be obtained. |
| Tasks | Dictionary Learning |
| Published | 2017-04-27 |
| URL | http://arxiv.org/abs/1704.08631v1 |
| http://arxiv.org/pdf/1704.08631v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-hierachical-extrapolated-parametric |
| Repo | |
| Framework | |
Video Representation Learning and Latent Concept Mining for Large-scale Multi-label Video Classification
| Title | Video Representation Learning and Latent Concept Mining for Large-scale Multi-label Video Classification |
| Authors | Po-Yao Huang, Ye Yuan, Zhenzhong Lan, Lu Jiang, Alexander G. Hauptmann |
| Abstract | We report on CMU Informedia Lab’s system used in Google’s YouTube 8 Million Video Understanding Challenge. In this multi-label video classification task, our pipeline achieved 84.675% and 84.662% GAP on our evaluation split and the official test set. We attribute the good performance to three components: 1) Refined video representation learning with residual links and hypercolumns 2) Latent concept mining which captures interactions among concepts. 3) Learning with temporal segments and weighted multi-model ensemble. We conduct experiments to validate and analyze the contribution of our models. We also share some unsuccessful trials leveraging conventional approaches such as recurrent neural networks for video representation learning for this large-scale video dataset. All the codes to reproduce our results are publicly available at https://github.com/Martini09/informedia-yt8m-release. |
| Tasks | Representation Learning, Video Classification, Video Understanding |
| Published | 2017-07-05 |
| URL | http://arxiv.org/abs/1707.01408v3 |
| http://arxiv.org/pdf/1707.01408v3.pdf | |
| PWC | https://paperswithcode.com/paper/video-representation-learning-and-latent |
| Repo | |
| Framework | |
Asking Too Much? The Rhetorical Role of Questions in Political Discourse
| Title | Asking Too Much? The Rhetorical Role of Questions in Political Discourse |
| Authors | Justine Zhang, Arthur Spirling, Cristian Danescu-Niculescu-Mizil |
| Abstract | Questions play a prominent role in social interactions, performing rhetorical functions that go beyond that of simple informational exchange. The surface form of a question can signal the intention and background of the person asking it, as well as the nature of their relation with the interlocutor. While the informational nature of questions has been extensively examined in the context of question-answering applications, their rhetorical aspects have been largely understudied. In this work we introduce an unsupervised methodology for extracting surface motifs that recur in questions, and for grouping them according to their latent rhetorical role. By applying this framework to the setting of question sessions in the UK parliament, we show that the resulting typology encodes key aspects of the political discourse—such as the bifurcation in questioning behavior between government and opposition parties—and reveals new insights into the effects of a legislator’s tenure and political career ambitions. |
| Tasks | Question Answering |
| Published | 2017-08-07 |
| URL | http://arxiv.org/abs/1708.02254v1 |
| http://arxiv.org/pdf/1708.02254v1.pdf | |
| PWC | https://paperswithcode.com/paper/asking-too-much-the-rhetorical-role-of |
| Repo | |
| Framework | |
Towards an automated method based on Iterated Local Search optimization for tuning the parameters of Support Vector Machines
| Title | Towards an automated method based on Iterated Local Search optimization for tuning the parameters of Support Vector Machines |
| Authors | Sergio Consoli, Jacek Kustra, Pieter Vos, Monique Hendriks, Dimitrios Mavroeidis |
| Abstract | We provide preliminary details and formulation of an optimization strategy under current development that is able to automatically tune the parameters of a Support Vector Machine over new datasets. The optimization strategy is a heuristic based on Iterated Local Search, a modification of classic hill climbing which iterates calls to a local search routine. |
| Tasks | |
| Published | 2017-07-11 |
| URL | http://arxiv.org/abs/1707.03191v1 |
| http://arxiv.org/pdf/1707.03191v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-an-automated-method-based-on-iterated |
| Repo | |
| Framework | |
Shannon Entropy Estimation in $\infty$-Alphabets from Convergence Results
| Title | Shannon Entropy Estimation in $\infty$-Alphabets from Convergence Results |
| Authors | Jorge F. Silva |
| Abstract | The problem of Shannon entropy estimation in countable infinite alphabets is addressed from the study and use of convergence results of the entropy functional, which is known to be discontinuous with respect to the total variation distance in $\infty$-alphabets. Sufficient conditions for the convergence of the entropy are used, including scenarios with both finitely and infinitely supported assumptions on the distributions. From this new perspective, four plug-in histogram-based estimators are studied showing that convergence results are instrumental to derive new strong consistency and rate of convergences results. Different scenarios and conditions are used on both the estimators and the underlying distribution, considering for example finite and unknown supported assumptions and summable tail bounded conditions. |
| Tasks | |
| Published | 2017-08-27 |
| URL | http://arxiv.org/abs/1710.06835v2 |
| http://arxiv.org/pdf/1710.06835v2.pdf | |
| PWC | https://paperswithcode.com/paper/shannon-entropy-estimation-in-infty-alphabets |
| Repo | |
| Framework | |
The Wisdom of Polarized Crowds
| Title | The Wisdom of Polarized Crowds |
| Authors | Feng Shi, Misha Teplitskiy, Eamon Duede, James Evans |
| Abstract | As political polarization in the United States continues to rise, the question of whether polarized individuals can fruitfully cooperate becomes pressing. Although diversity of individual perspectives typically leads to superior team performance on complex tasks, strong political perspectives have been associated with conflict, misinformation and a reluctance to engage with people and perspectives beyond one’s echo chamber. It is unclear whether self-selected teams of politically diverse individuals will create higher or lower quality outcomes. In this paper, we explore the effect of team political composition on performance through analysis of millions of edits to Wikipedia’s Political, Social Issues, and Science articles. We measure editors’ political alignments by their contributions to conservative versus liberal articles. A survey of editors validates that those who primarily edit liberal articles identify more strongly with the Democratic party and those who edit conservative ones with the Republican party. Our analysis then reveals that polarized teams—those consisting of a balanced set of politically diverse editors—create articles of higher quality than politically homogeneous teams. The effect appears most strongly in Wikipedia’s Political articles, but is also observed in Social Issues and even Science articles. Analysis of article “talk pages” reveals that politically polarized teams engage in longer, more constructive, competitive, and substantively focused but linguistically diverse debates than political moderates. More intense use of Wikipedia policies by politically diverse teams suggests institutional design principles to help unleash the power of politically polarized teams. |
| Tasks | |
| Published | 2017-11-29 |
| URL | http://arxiv.org/abs/1712.06414v1 |
| http://arxiv.org/pdf/1712.06414v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-wisdom-of-polarized-crowds |
| Repo | |
| Framework | |
PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation
| Title | PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation |
| Authors | Arno Solin, Santiago Cortes, Esa Rahtu, Juho Kannala |
| Abstract | This paper presents a novel method for visual-inertial odometry. The method is based on an information fusion framework employing low-cost IMU sensors and the monocular camera in a standard smartphone. We formulate a sequential inference scheme, where the IMU drives the dynamical model and the camera frames are used in coupling trailing sequences of augmented poses. The novelty in the model is in taking into account all the cross-terms in the updates, thus propagating the inter-connected uncertainties throughout the model. Stronger coupling between the inertial and visual data sources leads to robustness against occlusion and feature-poor environments. We demonstrate results on data collected with an iPhone and provide comparisons against the Tango device and using the EuRoC data set. |
| Tasks | Visual Odometry |
| Published | 2017-08-02 |
| URL | http://arxiv.org/abs/1708.00894v2 |
| http://arxiv.org/pdf/1708.00894v2.pdf | |
| PWC | https://paperswithcode.com/paper/pivo-probabilistic-inertial-visual-odometry |
| Repo | |
| Framework | |
