October 19, 2019

3268 words 16 mins read

Paper Group ANR 400

Paper Group ANR 400

Unsupervised Image to Sequence Translation with Canvas-Drawer Networks. Beyond Bags of Words: Inferring Systemic Nets. Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network. Mobile big data analysis with machine learning. Revealing patterns in HIV viral load data and classifying pa …

Unsupervised Image to Sequence Translation with Canvas-Drawer Networks

Title Unsupervised Image to Sequence Translation with Canvas-Drawer Networks
Authors Kevin Frans, Chin-Yi Cheng
Abstract Encoding images as a series of high-level constructs, such as brush strokes or discrete shapes, can often be key to both human and machine understanding. In many cases, however, data is only available in pixel form. We present a method for generating images directly in a high-level domain (e.g. brush strokes), without the need for real pairwise data. Specifically, we train a “canvas” network to imitate the mapping of high-level constructs to pixels, followed by a high-level “drawing” network which is optimized through this mapping towards solving a desired image recreation or translation task. We successfully discover sequential vector representations of symbols, large sketches, and 3D objects, utilizing only pixel data. We display applications of our method in image segmentation, and present several ablation studies comparing various configurations.
Tasks Semantic Segmentation
Published 2018-09-21
URL http://arxiv.org/abs/1809.08340v2
PDF http://arxiv.org/pdf/1809.08340v2.pdf
PWC https://paperswithcode.com/paper/unsupervised-image-to-sequence-translation
Repo
Framework

Beyond Bags of Words: Inferring Systemic Nets

Title Beyond Bags of Words: Inferring Systemic Nets
Authors D. B. Skillicorn, N. Alsadhan
Abstract Textual analytics based on representations of documents as bags of words have been reasonably successful. However, analysis that requires deeper insight into language, into author properties, or into the contexts in which documents were created requires a richer representation. Systemic nets are one such representation. They have not been extensively used because they required human effort to construct. We show that systemic nets can be algorithmically inferred from corpora, that the resulting nets are plausible, and that they can provide practical benefits for knowledge discovery problems. This opens up a new class of practical analysis techniques for textual analytics.
Tasks
Published 2018-06-13
URL http://arxiv.org/abs/1806.05231v1
PDF http://arxiv.org/pdf/1806.05231v1.pdf
PWC https://paperswithcode.com/paper/beyond-bags-of-words-inferring-systemic-nets
Repo
Framework

Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network

Title Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network
Authors Xinhai Liu, Zhizhong Han, Yu-Shen Liu, Matthias Zwicker
Abstract Exploring contextual information in the local region is important for shape understanding and analysis. Existing studies often employ hand-crafted or explicit ways to encode contextual information of local regions. However, it is hard to capture fine-grained contextual information in hand-crafted or explicit manners, such as the correlation between different areas in a local region, which limits the discriminative ability of learned features. To resolve this issue, we propose a novel deep learning model for 3D point clouds, named Point2Sequence, to learn 3D shape features by capturing fine-grained contextual information in a novel implicit way. Point2Sequence employs a novel sequence learning model for point clouds to capture the correlations by aggregating multi-scale areas of each local region with attention. Specifically, Point2Sequence first learns the feature of each area scale in a local region. Then, it captures the correlation between area scales in the process of aggregating all area scales using a recurrent neural network (RNN) based encoder-decoder structure, where an attention mechanism is proposed to highlight the importance of different area scales. Experimental results show that Point2Sequence achieves state-of-the-art performance in shape classification and segmentation tasks.
Tasks Shape Representation Of 3D Point Clouds
Published 2018-11-06
URL http://arxiv.org/abs/1811.02565v2
PDF http://arxiv.org/pdf/1811.02565v2.pdf
PWC https://paperswithcode.com/paper/point2sequence-learning-the-shape
Repo
Framework

Mobile big data analysis with machine learning

Title Mobile big data analysis with machine learning
Authors Jiyang Xie, Zeyu Song, Yupeng Li, Zhanyu Ma
Abstract This paper investigates to identify the requirement and the development of machine learning-based mobile big data analysis through discussing the insights of challenges in the mobile big data (MBD). Furthermore, it reviews the state-of-the-art applications of data analysis in the area of MBD. Firstly, we introduce the development of MBD. Secondly, the frequently adopted methods of data analysis are reviewed. Three typical applications of MBD analysis, namely wireless channel modeling, human online and offline behavior analysis, and speech recognition in the internet of vehicles, are introduced respectively. Finally, we summarize the main challenges and future development directions of mobile big data analysis.
Tasks Speech Recognition
Published 2018-08-02
URL https://arxiv.org/abs/1808.00803v2
PDF https://arxiv.org/pdf/1808.00803v2.pdf
PWC https://paperswithcode.com/paper/mobile-big-data-analysis-with-machine
Repo
Framework

Revealing patterns in HIV viral load data and classifying patients via a novel machine learning cluster summarization method

Title Revealing patterns in HIV viral load data and classifying patients via a novel machine learning cluster summarization method
Authors Samir Farooq, Samuel J. Weisenthal, Melissa Trayhan, Robert J. White, Kristen Bush, Peter R. Mariuz, Martin S. Zand
Abstract HIV RNA viral load (VL) is an important outcome variable in studies of HIV infected persons. There exists only a handful of methods which classify patients by viral load patterns. Most methods place limits on the use of viral load measurements, are often specific to a particular study design, and do not account for complex, temporal variation. To address this issue, we propose a set of four unambiguous computable characteristics (features) of time-varying HIV viral load patterns, along with a novel centroid-based classification algorithm, which we use to classify a population of 1,576 HIV positive clinic patients into one of five different viral load patterns (clusters) often found in the literature: durably suppressed viral load (DSVL), sustained low viral load (SLVL), sustained high viral load (SHVL), high viral load suppression (HVLS), and rebounding viral load (RVL). The centroid algorithm summarizes these clusters in terms of their centroids and radii. We show that this allows new viral load patterns to be assigned pattern membership based on the distance from the centroid relative to its radius, which we term radial normalization classification. This method has the benefit of providing an objective and quantitative method to assign viral load pattern membership with a concise and interpretable model that aids clinical decision making. This method also facilitates meta-analyses by providing computably distinct HIV categories. Finally we propose that this novel centroid algorithm could also be useful in the areas of cluster comparison for outcomes research and data reduction in machine learning.
Tasks Decision Making
Published 2018-04-25
URL http://arxiv.org/abs/1804.11195v1
PDF http://arxiv.org/pdf/1804.11195v1.pdf
PWC https://paperswithcode.com/paper/revealing-patterns-in-hiv-viral-load-data-and
Repo
Framework

Improving Medical Short Text Classification with Semantic Expansion Using Word-Cluster Embedding

Title Improving Medical Short Text Classification with Semantic Expansion Using Word-Cluster Embedding
Authors Ying Shen, Qiang Zhang, Jin Zhang, Jiyue Huang, Yuming Lu, Kai Lei
Abstract Automatic text classification (TC) research can be used for real-world problems such as the classification of in-patient discharge summaries and medical text reports, which is beneficial to make medical documents more understandable to doctors. However, in electronic medical records (EMR), the texts containing sentences are shorter than that in general domain, which leads to the lack of semantic features and the ambiguity of semantic. To tackle this challenge, we propose to add word-cluster embedding to deep neural network for improving short text classification. Concretely, we first use hierarchical agglomerative clustering to cluster the word vectors in the semantic space. Then we calculate the cluster center vector which represents the implicit topic information of words in the cluster. Finally, we expand word vector with cluster center vector, and implement classifiers using CNN and LSTM respectively. To evaluate the performance of our proposed method, we conduct experiments on public data sets TREC and the medical short sentences data sets which is constructed and released by us. The experimental results demonstrate that our proposed method outperforms state-of-the-art baselines in short sentence classification on both medical domain and general domain.
Tasks Sentence Classification, Text Classification
Published 2018-12-05
URL http://arxiv.org/abs/1812.01885v1
PDF http://arxiv.org/pdf/1812.01885v1.pdf
PWC https://paperswithcode.com/paper/improving-medical-short-text-classification
Repo
Framework

From FATS to feets: Further improvements to an astronomical feature extraction tool based on machine learning

Title From FATS to feets: Further improvements to an astronomical feature extraction tool based on machine learning
Authors J. B. Cabral, B. Sánchez, F. Ramos, S. Gurovich, P. Granitto, J. Vanderplas
Abstract Machine learning algorithms are highly useful for the classification of time series data in astronomy in this era of peta-scale public survey data releases. These methods can facilitate the discovery of new unknown events in most astrophysical areas, as well as improving the analysis of samples of known phenomena. Machine learning algorithms use features extracted from collected data as input predictive variables. A public tool called Feature Analysis for Time Series (FATS) has proved an excellent workhorse for feature extraction, particularly light curve classification for variable objects. In this study, we present a major improvement to FATS, which corrects inconvenient design choices, minor details, and documentation for the re-engineering process. This improvement comprises a new Python package called “feets”, which is important for future code-refactoring for astronomical software tools.
Tasks Time Series
Published 2018-09-06
URL http://arxiv.org/abs/1809.02154v1
PDF http://arxiv.org/pdf/1809.02154v1.pdf
PWC https://paperswithcode.com/paper/from-fats-to-feets-further-improvements-to-an
Repo
Framework

Top-down Attention Recurrent VLAD Encoding for Action Recognition in Videos

Title Top-down Attention Recurrent VLAD Encoding for Action Recognition in Videos
Authors Swathikiran Sudhakaran, Oswald Lanz
Abstract Most recent approaches for action recognition from video leverage deep architectures to encode the video clip into a fixed length representation vector that is then used for classification. For this to be successful, the network must be capable of suppressing irrelevant scene background and extract the representation from the most discriminative part of the video. Our contribution builds on the observation that spatio-temporal patterns characterizing actions in videos are highly correlated with objects and their location in the video. We propose Top-down Attention Action VLAD (TA-VLAD), a deep recurrent architecture with built-in spatial attention that performs temporally aggregated VLAD encoding for action recognition from videos. We adopt a top-down approach of attention, by using class specific activation maps obtained from a deep CNN pre-trained for image classification, to weight appearance features before encoding them into a fixed-length video descriptor using Gated Recurrent Units. Our method achieves state of the art recognition accuracy on HMDB51 and UCF101 benchmarks.
Tasks Action Recognition In Videos, Image Classification, Temporal Action Localization
Published 2018-08-29
URL http://arxiv.org/abs/1808.09892v1
PDF http://arxiv.org/pdf/1808.09892v1.pdf
PWC https://paperswithcode.com/paper/top-down-attention-recurrent-vlad-encoding
Repo
Framework
Title Teacher Guided Architecture Search
Authors Pouya Bashivan, Mark Tensen, James J DiCarlo
Abstract Much of the recent improvement in neural networks for computer vision has resulted from discovery of new networks architectures. Most prior work has used the performance of candidate models following limited training to automatically guide the search in a feasible way. Could further gains in computational efficiency be achieved by guiding the search via measurements of a high performing network with unknown detailed architecture (e.g. the primate visual system)? As one step toward this goal, we use representational similarity analysis to evaluate the similarity of internal activations of candidate networks with those of a (fixed, high performing) teacher network. We show that adopting this evaluation metric could produce up to an order of magnitude in search efficiency over performance-guided methods. Our approach finds a convolutional cell structure with similar performance as was previously found using other methods but at a total computational cost that is two orders of magnitude lower than Neural Architecture Search (NAS) and more than four times lower than progressive neural architecture search (PNAS). We further show that measurements from only ~300 neurons from primate visual system provides enough signal to find a network with an Imagenet top-1 error that is significantly lower than that achieved by performance-guided architecture search alone. These results suggest that representational matching can be used to accelerate network architecture search in cases where one has access to some or all of the internal representations of a teacher network of interest, such as the brain’s sensory processing networks.
Tasks Neural Architecture Search
Published 2018-08-04
URL https://arxiv.org/abs/1808.01405v3
PDF https://arxiv.org/pdf/1808.01405v3.pdf
PWC https://paperswithcode.com/paper/teacher-guided-architecture-search
Repo
Framework

On the convergence of optimistic policy iteration for stochastic shortest path problem

Title On the convergence of optimistic policy iteration for stochastic shortest path problem
Authors Yuanlong Chen
Abstract In this paper, we prove some convergence results of a special case of optimistic policy iteration algorithm for stochastic shortest path problem. We consider both Monte Carlo and $TD(\lambda)$ methods for the policy evaluation step under the condition that the termination state will eventually be reached almost surely.
Tasks
Published 2018-08-27
URL http://arxiv.org/abs/1808.08763v2
PDF http://arxiv.org/pdf/1808.08763v2.pdf
PWC https://paperswithcode.com/paper/on-the-convergence-of-optimistic-policy
Repo
Framework

Topology and Prediction Focused Research on Graph Convolutional Neural Networks

Title Topology and Prediction Focused Research on Graph Convolutional Neural Networks
Authors Matthew Baron
Abstract Important advances have been made using convolutional neural network (CNN) approaches to solve complicated problems in areas that rely on grid structured data such as image processing and object classification. Recently, research on graph convolutional neural networks (GCNN) has increased dramatically as researchers try to replicate the success of CNN for graph structured data. Unfortunately, traditional CNN methods are not readily transferable to GCNN, given the irregularity and geometric complexity of graphs. The emerging field of GCNN is further complicated by research papers that differ greatly in their scope, detail, and level of academic sophistication needed by the reader. The present paper provides a review of some basic properties of GCNN. As a guide to the interested reader, recent examples of GCNN research are then grouped according to techniques that attempt to uncover the underlying topology of the graph model and those that seek to generalize traditional CNN methods on graph data to improve prediction of class membership. Discrete Signal Processing on Graphs (DSPg) is used as a theoretical framework to better understand some of the performance gains and limitations of these recent GCNN approaches. A brief discussion of Topology Adaptive Graph Convolutional Networks (TAGCN) is presented as an approach motivated by DSPg and future research directions using this approach are briefly discussed.
Tasks Object Classification
Published 2018-08-23
URL http://arxiv.org/abs/1808.07769v1
PDF http://arxiv.org/pdf/1808.07769v1.pdf
PWC https://paperswithcode.com/paper/topology-and-prediction-focused-research-on
Repo
Framework

Fibres of Failure: Classifying errors in predictive processes

Title Fibres of Failure: Classifying errors in predictive processes
Authors Leo Carlsson, Gunnar Carlsson, Mikael Vejdemo-Johansson
Abstract We describe Fibres of Failure (FiFa), a method to classify failure modes of predictive processes using the Mapper algorithm from Topological Data Analysis. Our method uses Mapper to build a graph model of input data stratified by prediction error. Groupings found in high-error regions of the Mapper model then provide distinct failure modes of the predictive process. We demonstrate FiFa on misclassifications of MNIST images with added noise, and demonstrate two ways to use the failure mode classification: either to produce a correction layer that adjusts predictions by similarity to the failure modes; or to inspect members of the failure modes to illustrate and investigate what characterizes each failure mode.
Tasks Topological Data Analysis
Published 2018-02-09
URL http://arxiv.org/abs/1803.00384v1
PDF http://arxiv.org/pdf/1803.00384v1.pdf
PWC https://paperswithcode.com/paper/fibres-of-failure-classifying-errors-in
Repo
Framework

Example Mining for Incremental Learning in Medical Imaging

Title Example Mining for Incremental Learning in Medical Imaging
Authors Pratyush Kumar, Muktabh Mayank Srivastava
Abstract Incremental Learning is well known machine learning approach wherein the weights of the learned model are dynamically and gradually updated to generalize on new unseen data without forgetting the existing knowledge. Incremental learning proves to be time as well as resource-efficient solution for deployment of deep learning algorithms in real world as the model can automatically and dynamically adapt to new data as and when annotated data becomes available. The development and deployment of Computer Aided Diagnosis (CAD) tools in medical domain is another scenario, where incremental learning becomes very crucial as collection and annotation of a comprehensive dataset spanning over multiple pathologies and imaging machines might take years. However, not much has so far been explored in this direction. In the current work, we propose a robust and efficient method for incremental learning in medical imaging domain. Our approach makes use of Hard Example Mining technique (which is commonly used as a solution to heavy class imbalance) to automatically select a subset of dataset to fine-tune the existing network weights such that it adapts to new data while retaining existing knowledge. We develop our approach for incremental learning of our already under test model for detecting dental caries. Further, we apply our approach to one publicly available dataset and demonstrate that our approach reaches the accuracy of training on entire dataset at once, while availing the benefits of incremental learning scenario.
Tasks
Published 2018-07-24
URL http://arxiv.org/abs/1807.08942v1
PDF http://arxiv.org/pdf/1807.08942v1.pdf
PWC https://paperswithcode.com/paper/example-mining-for-incremental-learning-in
Repo
Framework

ConvSRC: SmartPhone based Periocular Recognition using Deep Convolutional Neural Network and Sparsity Augmented Collaborative Representation

Title ConvSRC: SmartPhone based Periocular Recognition using Deep Convolutional Neural Network and Sparsity Augmented Collaborative Representation
Authors Amani Alahmadi, Muhammad Hussain, Hatim Aboalsamh, Mansour Zuair
Abstract Smartphone based periocular recognition has gained significant attention from biometric research community because of the limitations of biometric modalities like face, iris etc. Most of the existing methods for periocular recognition employ hand-crafted features. Recently, learning based image representation techniques like deep Convolutional Neural Network (CNN) have shown outstanding performance in many visual recognition tasks. CNN needs a huge volume of data for its learning, but for periocular recognition only limited amount of data is available. The solution is to use CNN pre-trained on the dataset from the related domain, in this case the challenge is to extract efficiently the discriminative features. Using a pertained CNN model (VGG-Net), we propose a simple, efficient and compact image representation technique that takes into account the wealth of information and sparsity existing in the activations of the convolutional layers and employs principle component analysis. For recognition, we use an efficient and robust Sparse Augmented Collaborative Representation based Classification (SA-CRC) technique. For thorough evaluation of ConvSRC (the proposed system), experiments were carried out on the VISOB challenging database which was presented for periocular recognition competition in ICIP2016. The obtained results show the superiority of ConvSRC over the state-of-the-art methods; it obtains a GMR of more than 99% at FMR = 10-3 and outperforms the first winner of ICIP2016 challenge by 10%.
Tasks
Published 2018-01-16
URL http://arxiv.org/abs/1801.05449v1
PDF http://arxiv.org/pdf/1801.05449v1.pdf
PWC https://paperswithcode.com/paper/convsrc-smartphone-based-periocular
Repo
Framework

Find the dimension that counts: Fast dimension estimation and Krylov PCA

Title Find the dimension that counts: Fast dimension estimation and Krylov PCA
Authors Shashanka Ubaru, Abd-Krim Seghouane, Yousef Saad
Abstract High dimensional data and systems with many degrees of freedom are often characterized by covariance matrices. In this paper, we consider the problem of simultaneously estimating the dimension of the principal (dominant) subspace of these covariance matrices and obtaining an approximation to the subspace. This problem arises in the popular principal component analysis (PCA), and in many applications of machine learning, data analysis, signal and image processing, and others. We first present a novel method for estimating the dimension of the principal subspace. We then show how this method can be coupled with a Krylov subspace method to simultaneously estimate the dimension and obtain an approximation to the subspace. The dimension estimation is achieved at no additional cost. The proposed method operates on a model selection framework, where the novel selection criterion is derived based on random matrix perturbation theory ideas. We present theoretical analyses which (a) show that the proposed method achieves strong consistency (i.e., yields optimal solution as the number of data-points $n\rightarrow \infty$), and (b) analyze conditions for exact dimension estimation in the finite $n$ case. Using recent results, we show that our algorithm also yields near optimal PCA. The proposed method avoids forming the sample covariance matrix (associated with the data) explicitly and computing the complete eigen-decomposition. Therefore, the method is inexpensive, which is particularly advantageous in modern data applications where the covariance matrices can be very large. Numerical experiments illustrate the performance of the proposed method in various applications.
Tasks Model Selection
Published 2018-10-08
URL http://arxiv.org/abs/1810.03733v1
PDF http://arxiv.org/pdf/1810.03733v1.pdf
PWC https://paperswithcode.com/paper/find-the-dimension-that-counts-fast-dimension
Repo
Framework
comments powered by Disqus