October 16, 2019

3336 words 16 mins read

Paper Group ANR 992

RGB image-based data analysis via discrete Morse theory and persistent homology. Toward Scale-Invariance and Position-Sensitive Region Proposal Networks. Time Series Classification to Improve Poultry Welfare. EEG machine learning with Higuchi fractal dimension and Sample Entropy as features for successful detection of depression. Efficient Multi-Do …

RGB image-based data analysis via discrete Morse theory and persistent homology


Title	RGB image-based data analysis via discrete Morse theory and persistent homology
Authors	Chuan Du, Christopher Szul, Adarsh Manawa, Nima Rasekh, Rosemary Guzman, Ruth Davidson
Abstract	Understanding and comparing images for the purposes of data analysis is currently a very computationally demanding task. A group at Australian National University (ANU) recently developed open-source code that can detect fundamental topological features of a grayscale image in a computationally feasible manner. This is made possible by the fact that computers store grayscale images as cubical cellular complexes. These complexes can be studied using the techniques of discrete Morse theory. We expand the functionality of the ANU code by introducing methods and software for analyzing images encoded in red, green, and blue (RGB), because this image encoding is very popular for publicly available data. Our methods allow the extraction of key topological information from RGB images via informative persistence diagrams by introducing novel methods for transforming RGB-to-grayscale. This paradigm allows us to perform data analysis directly on RGB images representing water scarcity variability as well as crime variability. We introduce software enabling a a user to predict future image properties, towards the eventual aim of more rapid image-based data behavior prediction.
Tasks
Published	2018-01-09
URL	http://arxiv.org/abs/1801.09530v1
PDF	http://arxiv.org/pdf/1801.09530v1.pdf
PWC	https://paperswithcode.com/paper/rgb-image-based-data-analysis-via-discrete
Repo
Framework

Toward Scale-Invariance and Position-Sensitive Region Proposal Networks


Title	Toward Scale-Invariance and Position-Sensitive Region Proposal Networks
Authors	Hsueh-Fu Lu, Xiaofei Du, Ping-Lin Chang
Abstract	Accurately localising object proposals is an important precondition for high detection rate for the state-of-the-art object detection frameworks. The accuracy of an object detection method has been shown highly related to the average recall (AR) of the proposals. In this work, we propose an advanced object proposal network in favour of translation-invariance for objectness classification, translation-variance for bounding box regression, large effective receptive fields for capturing global context and scale-invariance for dealing with a range of object sizes from extremely small to large. The design of the network architecture aims to be simple while being effective and with real time performance. Without bells and whistles the proposed object proposal network significantly improves the AR at 1,000 proposals by $35%$ and $45%$ on PASCAL VOC and COCO dataset respectively and has a fast inference time of 44.8 ms for input image size of $640^{2}$. Empirical studies have also shown that the proposed method is class-agnostic to be generalised for general object proposal.
Tasks	Object Detection
Published	2018-07-25
URL	http://arxiv.org/abs/1807.09528v1
PDF	http://arxiv.org/pdf/1807.09528v1.pdf
PWC	https://paperswithcode.com/paper/toward-scale-invariance-and-position
Repo
Framework

Time Series Classification to Improve Poultry Welfare


Title	Time Series Classification to Improve Poultry Welfare
Authors	Alireza Abdoli, Amy C. Murillo, Chin-Chia M. Yeh, Alec C. Gerry, Eamonn J. Keogh
Abstract	Poultry farms are an important contributor to the human food chain. Worldwide, humankind keeps an enormous number of domesticated birds (e.g. chickens) for their eggs and their meat, providing rich sources of low-fat protein. However, around the world, there have been growing concerns about the quality of life for the livestock in poultry farms; and increasingly vocal demands for improved standards of animal welfare. Recent advances in sensing technologies and machine learning allow the possibility of automatically assessing the health of some individual birds, and employing the lessons learned to improve the welfare for all birds. This task superficially appears to be easy, given the dramatic progress in recent years in classifying human behaviors, and given that human behaviors are presumably more complex. However, as we shall demonstrate, classifying chicken behaviors poses several unique challenges, chief among which is creating a generalizable dictionary of behaviors from sparse and noisy data. In this work we introduce a novel time series dictionary learning algorithm that can robustly learn from weakly labeled data sources.
Tasks	Dictionary Learning, Time Series, Time Series Classification
Published	2018-11-07
URL	http://arxiv.org/abs/1811.03149v1
PDF	http://arxiv.org/pdf/1811.03149v1.pdf
PWC	https://paperswithcode.com/paper/time-series-classification-to-improve-poultry
Repo
Framework

EEG machine learning with Higuchi fractal dimension and Sample Entropy as features for successful detection of depression


Title	EEG machine learning with Higuchi fractal dimension and Sample Entropy as features for successful detection of depression
Authors	Milena Cukic, David Pokrajac, Miodrag Stokic, slobodan Simic, Vlada Radivojevic, Milos Ljubisavljevic
Abstract	Reliable diagnosis of depressive disorder is essential for both optimal treatment and prevention of fatal outcomes. In this study, we aimed to elucidate the effectiveness of two non-linear measures, Higuchi Fractal Dimension (HFD) and Sample Entropy (SampEn), in detecting depressive disorders when applied on EEG. HFD and SampEn of EEG signals were used as features for seven machine learning algorithms including Multilayer Perceptron, Logistic Regression, Support Vector Machines with the linear and polynomial kernel, Decision Tree, Random Forest, and Naive Bayes classifier, discriminating EEG between healthy control subjects and patients diagnosed with depression. We confirmed earlier observations that both non-linear measures can discriminate EEG signals of patients from healthy control subjects. The results suggest that good classification is possible even with a small number of principal components. Average accuracy among classifiers ranged from 90.24% to 97.56%. Among the two measures, SampEn had better performance. Using HFD and SampEn and a variety of machine learning techniques we can accurately discriminate patients diagnosed with depression vs controls which can serve as a highly sensitive, clinically relevant marker for the diagnosis of depressive disorders.
Tasks	EEG
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05985v1
PDF	http://arxiv.org/pdf/1803.05985v1.pdf
PWC	https://paperswithcode.com/paper/eeg-machine-learning-with-higuchi-fractal
Repo
Framework

Efficient Multi-Domain Dictionary Learning with GANs


Title	Efficient Multi-Domain Dictionary Learning with GANs
Authors	Cho Ying Wu, Ulrich Neumann
Abstract	In this paper, we propose the multi-domain dictionary learn- ing (MDDL) to make dictionary learning-based classification more robust to data representing in different domains. We use adversarial neural networks to generate data in different styles, and collect all the generated data into a miscellaneous dictionary. To tackle the dictionary learning with many sam- ples, we compute the weighting matrix that compress the mis- cellaneous dictionary from multi-sample per class to single sample per class. We show that the time complexity solv- ing the proposed MDDL with weighting matrix is the same as solving the dictionary with single sample per class. More- over, since the weighting matrix could help the solver rely more on the training data, which possibly lie in the same do- main with the testing data, the classification could be more accurate.
Tasks	Dictionary Learning
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00274v1
PDF	http://arxiv.org/pdf/1811.00274v1.pdf
PWC	https://paperswithcode.com/paper/efficient-multi-domain-dictionary-learning
Repo
Framework

Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural language Processing


Title	Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural language Processing
Authors	K M Annervaz, Somnath Basu Roy Chowdhury, Ambedkar Dukkipati
Abstract	Machine Learning has been the quintessential solution for many AI problems, but learning is still heavily dependent on the specific training data. Some learning models can be incorporated with a prior knowledge in the Bayesian set up, but these learning models do not have the ability to access any organised world knowledge on demand. In this work, we propose to enhance learning models with world knowledge in the form of Knowledge Graph (KG) fact triples for Natural Language Processing (NLP) tasks. Our aim is to develop a deep learning model that can extract relevant prior support facts from knowledge graphs depending on the task using attention mechanism. We introduce a convolution-based model for learning representations of knowledge graph entity and relation clusters in order to reduce the attention space. We show that the proposed method is highly scalable to the amount of prior information that has to be processed and can be applied to any generic NLP task. Using this method we show significant improvement in performance for text classification with News20, DBPedia datasets and natural language inference with Stanford Natural Language Inference (SNLI) dataset. We also demonstrate that a deep learning model can be trained well with substantially less amount of labeled training data, when it has access to organised world knowledge in the form of knowledge graph.
Tasks	Knowledge Graphs, Natural Language Inference, Text Classification
Published	2018-02-16
URL	http://arxiv.org/abs/1802.05930v2
PDF	http://arxiv.org/pdf/1802.05930v2.pdf
PWC	https://paperswithcode.com/paper/learning-beyond-datasets-knowledge-graph
Repo
Framework

A Method for Robust Online Classification using Dictionary Learning: Development and Assessment for Monitoring Manual Material Handling Activities Using Wearable Sensors


Title	A Method for Robust Online Classification using Dictionary Learning: Development and Assessment for Monitoring Manual Material Handling Activities Using Wearable Sensors
Authors	Babak Barazandeh, Mohammadhussein Rafieisakhaei, Sunwook Kim, Zhenyu, Kong, Maury A. Nussbaum
Abstract	Classification methods based on sparse estimation have drawn much attention recently, due to their effectiveness in processing high-dimensional data such as images. In this paper, a method to improve the performance of a sparse representation classification (SRC) approach is proposed; it is then applied to the problem of online process monitoring of human workers, specifically manual material handling (MMH) operations monitored using wearable sensors (involving 111 sensor channels). Our proposed method optimizes the design matrix (aka dictionary) in the linear model used for SRC, minimizing its ill-posedness to achieve a sparse solution. This procedure is based on the idea of dictionary learning (DL): we optimize the design matrix formed by training datasets to minimize both redundancy and coherency as well as reducing the size of these datasets. Use of such optimized training data can subsequently improve classification accuracy and help decrease the computational time needed for the SRC; it is thus more applicable for online process monitoring. Performance of the proposed methodology is demonstrated using wearable sensor data obtained from manual material handling experiments, and is found to be superior to those of benchmark methods in terms of accuracy, while also requiring computational time appropriate for MMH online monitoring.
Tasks	Dictionary Learning
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09447v1
PDF	http://arxiv.org/pdf/1810.09447v1.pdf
PWC	https://paperswithcode.com/paper/a-method-for-robust-online-classification
Repo
Framework

Extracting Action Sequences from Texts Based on Deep Reinforcement Learning


Title	Extracting Action Sequences from Texts Based on Deep Reinforcement Learning
Authors	Wenfeng Feng, Hankz Hankui Zhuo, Subbarao Kambhampati
Abstract	Extracting action sequences from natural language texts is challenging, as it requires commonsense inferences based on world knowledge. Although there has been work on extracting action scripts, instructions, navigation actions, etc., they require that either the set of candidate actions be provided in advance, or that action descriptions are restricted to a specific form, e.g., description templates. In this paper, we aim to extract action sequences from texts in free natural language, i.e., without any restricted templates, provided the candidate set of actions is unknown. We propose to extract action sequences from texts based on the deep reinforcement learning framework. Specifically, we view “selecting” or “eliminating” words from texts as “actions”, and the texts associated with actions as “states”. We then build Q-networks to learn the policy of extracting actions and extract plans from the labeled texts. We demonstrate the effectiveness of our approach on several datasets with comparison to state-of-the-art approaches, including online experiments interacting with humans.
Tasks
Published	2018-03-07
URL	http://arxiv.org/abs/1803.02632v2
PDF	http://arxiv.org/pdf/1803.02632v2.pdf
PWC	https://paperswithcode.com/paper/extracting-action-sequences-from-texts-based
Repo
Framework

Sparse-View CT Reconstruction via Convolutional Sparse Coding


Title	Sparse-View CT Reconstruction via Convolutional Sparse Coding
Authors	Peng Bao, Wenjun Xia, Kang Yang, Jiliu Zhou, Yi Zhang
Abstract	Traditional dictionary learning based CT reconstruction methods are patch-based and the features learned with these methods often contain shifted versions of the same features. To deal with these problems, the convolutional sparse coding (CSC) has been proposed and introduced into various applications. In this paper, inspired by the successful applications of CSC in the field of signal processing, we propose a novel sparse-view CT reconstruction method based on CSC with gradient regularization on feature maps. By directly working on whole image, which need not to divide the image into overlapped patches like dictionary learning based methods, the proposed method can maintain more details and avoid the artifacts caused by patch aggregation. Experimental results demonstrate that the proposed method has better performance than several existing algorithms in both qualitative and quantitative aspects.
Tasks	Dictionary Learning
Published	2018-10-15
URL	http://arxiv.org/abs/1810.06228v1
PDF	http://arxiv.org/pdf/1810.06228v1.pdf
PWC	https://paperswithcode.com/paper/sparse-view-ct-reconstruction-via
Repo
Framework

A Survey of FPGA Based Deep Learning Accelerators: Challenges and Opportunities


Title	A Survey of FPGA Based Deep Learning Accelerators: Challenges and Opportunities
Authors	Teng Wang, Chao Wang, Xuehai Zhou, Huaping Chen
Abstract	With the rapid development of in-depth learning, neural network and deep learning algorithms have been widely used in various fields, e.g., image, video and voice processing. However, the neural network model is getting larger and larger, which is expressed in the calculation of model parameters. Although a wealth of existing efforts on GPU platforms currently used by researchers for improving computing performance, dedicated hardware solutions are essential and emerging to provide advantages over pure software solutions. In this paper, we systematically investigate the neural network accelerator based on FPGA. Specifically, we respectively review the accelerators designed for specific problems, specific algorithms, algorithm features, and general templates. We also compared the design and implementation of the accelerator based on FPGA under different devices and network models and compared it with the versions of CPU and GPU. Finally, we present to discuss the advantages and disadvantages of accelerators on FPGA platforms and to further explore the opportunities for future research.
Tasks
Published	2018-12-25
URL	https://arxiv.org/abs/1901.04988v2
PDF	https://arxiv.org/pdf/1901.04988v2.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-fpga-based-deep-learning
Repo
Framework

Classifying Multi-channel UWB SAR Imagery via Tensor Sparsity Learning Techniques


Title	Classifying Multi-channel UWB SAR Imagery via Tensor Sparsity Learning Techniques
Authors	Tiep Vu, Lam Nguyen, Vishal Monga
Abstract	Using low-frequency (UHF to L-band) ultra-wideband (UWB) synthetic aperture radar (SAR) technology for detecting buried and obscured targets, e.g. bomb or mine, has been successfully demonstrated recently. Despite promising recent progress, a significant open challenge is to distinguish obscured targets from other (natural and manmade) clutter sources in the scene. The problem becomes exacerbated in the presence of noisy responses from rough ground surfaces. In this paper, we present three novel sparsity-driven techniques, which not only exploit the subtle features of raw captured data but also take advantage of the polarization diversity and the aspect angle dependence information from multi-channel SAR data. First, the traditional sparse representation-based classification (SRC) is generalized to exploit shared information of classes and various sparsity structures of tensor coefficients for multi-channel data. Corresponding tensor dictionary learning models are consequently proposed to enhance classification accuracy. Lastly, a new tensor sparsity model is proposed to model responses from multiple consecutive looks of objects, which is a unique characteristic of the dataset we consider. Extensive experimental results on a high-fidelity electromagnetic simulated dataset and radar data collected from the U.S. Army Research Laboratory side-looking SAR demonstrate the advantages of proposed tensor sparsity models.
Tasks	Dictionary Learning, Sparse Representation-based Classification
Published	2018-10-04
URL	http://arxiv.org/abs/1810.02812v1
PDF	http://arxiv.org/pdf/1810.02812v1.pdf
PWC	https://paperswithcode.com/paper/classifying-multi-channel-uwb-sar-imagery-via
Repo
Framework

Posterior Concentration for Sparse Deep Learning


Title	Posterior Concentration for Sparse Deep Learning
Authors	Nicholas Polson, Veronika Rockova
Abstract	Spike-and-Slab Deep Learning (SS-DL) is a fully Bayesian alternative to Dropout for improving generalizability of deep ReLU networks. This new type of regularization enables provable recovery of smooth input-output maps with unknown levels of smoothness. Indeed, we show that the posterior distribution concentrates at the near minimax rate for $\alpha$-H"older smooth maps, performing as well as if we knew the smoothness level $\alpha$ ahead of time. Our result sheds light on architecture design for deep neural networks, namely the choice of depth, width and sparsity level. These network attributes typically depend on unknown smoothness in order to be optimal. We obviate this constraint with the fully Bayes construction. As an aside, we show that SS-DL does not overfit in the sense that the posterior concentrates on smaller networks with fewer (up to the optimal number of) nodes and links. Our results provide new theoretical justifications for deep ReLU networks from a Bayesian point of view.
Tasks
Published	2018-03-24
URL	http://arxiv.org/abs/1803.09138v1
PDF	http://arxiv.org/pdf/1803.09138v1.pdf
PWC	https://paperswithcode.com/paper/posterior-concentration-for-sparse-deep
Repo
Framework

Geometric Operator Convolutional Neural Network


Title	Geometric Operator Convolutional Neural Network
Authors	Yangling Ma, Yixin Luo, Zhouwang Yang
Abstract	The Convolutional Neural Network (CNN) has been successfully applied in many fields during recent decades; however it lacks the ability to utilize prior domain knowledge when dealing with many realistic problems. We present a framework called Geometric Operator Convolutional Neural Network (GO-CNN) that uses domain knowledge, wherein the kernel of the first convolutional layer is replaced with a kernel generated by a geometric operator function. This framework integrates many conventional geometric operators, which allows it to adapt to a diverse range of problems. Under certain conditions, we theoretically analyze the convergence and the bound of the generalization errors between GO-CNNs and common CNNs. Although the geometric operator convolution kernels have fewer trainable parameters than common convolution kernels, the experimental results indicate that GO-CNN performs more accurately than common CNN on CIFAR-10/100. Furthermore, GO-CNN reduces dependence on the amount of training examples and enhances adversarial stability. In the practical task of medically diagnosing bone fractures, GO-CNN obtains 3% improvement in terms of the recall.
Tasks
Published	2018-09-04
URL	http://arxiv.org/abs/1809.01016v1
PDF	http://arxiv.org/pdf/1809.01016v1.pdf
PWC	https://paperswithcode.com/paper/geometric-operator-convolutional-neural
Repo
Framework

Energy Disaggregation via Deep Temporal Dictionary Learning


Title	Energy Disaggregation via Deep Temporal Dictionary Learning
Authors	Mahdi Khodayar, Jianhui Wang, Zhaoyu Wang
Abstract	This paper addresses the energy disaggregation problem, i.e. decomposing the electricity signal of a whole home to its operating devices. First, we cast the problem as a dictionary learning (DL) problem where the key electricity patterns representing consumption behaviors are extracted for each device and stored in a dictionary matrix. The electricity signal of each device is then modeled by a linear combination of such patterns with sparse coefficients that determine the contribution of each device in the total electricity. Although popular, the classic DL approach is prone to high error in real-world applications including energy disaggregation, as it merely finds linear dictionaries. Moreover, this method lacks a recurrent structure; thus, it is unable to leverage the temporal structure of energy signals. Motivated by such shortcomings, we propose a novel optimization program where the dictionary and its sparse coefficients are optimized simultaneously with a deep neural model extracting powerful nonlinear features from the energy signals. A long short-term memory auto-encoder (LSTM-AE) is proposed with tunable time dependent states to capture the temporal behavior of energy signals for each device. We learn the dictionary in the space of temporal features captured by the LSTM-AE rather than the original space of the energy signals; hence, in contrast to the traditional DL, here, a nonlinear dictionary is learned using powerful temporal features extracted from our deep model. Real experiments on the publicly available Reference Energy Disaggregation Dataset (REDD) show significant improvement compared to the state-of-the-art methodologies in terms of the disaggregation accuracy and F-score metrics.
Tasks	Dictionary Learning
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03534v1
PDF	http://arxiv.org/pdf/1809.03534v1.pdf
PWC	https://paperswithcode.com/paper/energy-disaggregation-via-deep-temporal
Repo
Framework

Semi-supervised and Transfer learning approaches for low resource sentiment classification


Title	Semi-supervised and Transfer learning approaches for low resource sentiment classification
Authors	Rahul Gupta, Saurabh Sahu, Carol Espy-Wilson, Shrikanth Narayanan
Abstract	Sentiment classification involves quantifying the affective reaction of a human to a document, media item or an event. Although researchers have investigated several methods to reliably infer sentiment from lexical, speech and body language cues, training a model with a small set of labeled datasets is still a challenge. For instance, in expanding sentiment analysis to new languages and cultures, it may not always be possible to obtain comprehensive labeled datasets. In this paper, we investigate the application of semi-supervised and transfer learning methods to improve performances on low resource sentiment classification tasks. We experiment with extracting dense feature representations, pre-training and manifold regularization in enhancing the performance of sentiment classification systems. Our goal is a coherent implementation of these methods and we evaluate the gains achieved by these methods in matched setting involving training and testing on a single corpus setting as well as two cross corpora settings. In both the cases, our experiments demonstrate that the proposed methods can significantly enhance the model performance against a purely supervised approach, particularly in cases involving a handful of training data.
Tasks	Sentiment Analysis, Transfer Learning
Published	2018-06-07
URL	http://arxiv.org/abs/1806.02863v1
PDF	http://arxiv.org/pdf/1806.02863v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-and-transfer-learning
Repo
Framework