October 18, 2019

3045 words 15 mins read

Paper Group ANR 499

EEG-based Communication with a Predictive Text Algorithm. Bayesian deep neural networks for low-cost neurophysiological markers of Alzheimer’s disease severity. SWDE : A Sub-Word And Document Embedding Based Engine for Clickbait Detection. When Politicians Talk About Politics: Identifying Political Tweets of Brazilian Congressmen. Reward Learning f …

EEG-based Communication with a Predictive Text Algorithm


Title	EEG-based Communication with a Predictive Text Algorithm
Authors	Daniel Omeiza, Kayode Adewole, Daniel Nkemelu
Abstract	Several changes occur in the brain in response to voluntary and involuntary activities performed by a person. The ability to retrieve data from the brain within a time space provides basis for in-depth analyses that offer insight on what changes occur in the brain during its decision making processes. In this work, we present the technical description and software implementation of an electroencephalographic (EEG) based intelligent communication system. We use EEG dry sensors to read brain waves data in real-time with which we compute the likelihood that a voluntary eye blink has been made by a person and use the decision to trigger buttons on a user interface in order to produce text using a modification of the T9 algorithm. Our results indicate that EEG-based technology can be effectively applied in facilitating speech for people with severe speech and muscular disabilities, providing a foundation for future work in the area.
Tasks	Decision Making, EEG
Published	2018-12-14
URL	https://arxiv.org/abs/1812.05945v3
PDF	https://arxiv.org/pdf/1812.05945v3.pdf
PWC	https://paperswithcode.com/paper/eeg-based-communication-with-a-predictive
Repo
Framework

Bayesian deep neural networks for low-cost neurophysiological markers of Alzheimer’s disease severity


Title	Bayesian deep neural networks for low-cost neurophysiological markers of Alzheimer’s disease severity
Authors	Wolfgang Fruehwirt, Adam D. Cobb, Martin Mairhofer, Leonard Weydemann, Heinrich Garn, Reinhold Schmidt, Thomas Benke, Peter Dal-Bianco, Gerhard Ransmayr, Markus Waser, Dieter Grossegger, Pengfei Zhang, Georg Dorffner, Stephen Roberts
Abstract	As societies around the world are ageing, the number of Alzheimer’s disease (AD) patients is rapidly increasing. To date, no low-cost, non-invasive biomarkers have been established to advance the objectivization of AD diagnosis and progression assessment. Here, we utilize Bayesian neural networks to develop a multivariate predictor for AD severity using a wide range of quantitative EEG (QEEG) markers. The Bayesian treatment of neural networks both automatically controls model complexity and provides a predictive distribution over the target function, giving uncertainty bounds for our regression task. It is therefore well suited to clinical neuroscience, where data sets are typically sparse and practitioners require a precise assessment of the predictive uncertainty. We use data of one of the largest prospective AD EEG trials ever conducted to demonstrate the potential of Bayesian deep learning in this domain, while comparing two distinct Bayesian neural network approaches, i.e., Monte Carlo dropout and Hamiltonian Monte Carlo.
Tasks	EEG
Published	2018-12-12
URL	http://arxiv.org/abs/1812.04994v2
PDF	http://arxiv.org/pdf/1812.04994v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-deep-neural-networks-for-low-cost
Repo
Framework

SWDE : A Sub-Word And Document Embedding Based Engine for Clickbait Detection


Title	SWDE : A Sub-Word And Document Embedding Based Engine for Clickbait Detection
Authors	Vaibhav Kumar, Mrinal Dhar, Dhruv Khattar, Yash Kumar Lal, Abhimanshu Mishra, Manish Shrivastava, Vasudeva Varma
Abstract	In order to expand their reach and increase website ad revenue, media outlets have started using clickbait techniques to lure readers to click on articles on their digital platform. Having successfully enticed the user to open the article, the article fails to satiate his curiosity serving only to boost click-through rates. Initial methods for this task were dependent on feature engineering, which varies with each dataset. Industry systems have relied on an exhaustive set of rules to get the job done. Neural networks have barely been explored to perform this task. We propose a novel approach considering different textual embeddings of a news headline and the related article. We generate sub-word level embeddings of the title using Convolutional Neural Networks and use them to train a bidirectional LSTM architecture. An attention layer allows for calculation of significance of each term towards the nature of the post. We also generate Doc2Vec embeddings of the title and article text and model how they interact, following which it is concatenated with the output of the previous component. Finally, this representation is passed through a neural network to obtain a score for the headline. We test our model over 2538 posts (having trained it on 17000 records) and achieve an accuracy of 83.49% outscoring previous state-of-the-art approaches.
Tasks	Clickbait Detection, Document Embedding, Feature Engineering
Published	2018-08-02
URL	http://arxiv.org/abs/1808.00957v1
PDF	http://arxiv.org/pdf/1808.00957v1.pdf
PWC	https://paperswithcode.com/paper/swde-a-sub-word-and-document-embedding-based
Repo
Framework

When Politicians Talk About Politics: Identifying Political Tweets of Brazilian Congressmen


Title	When Politicians Talk About Politics: Identifying Political Tweets of Brazilian Congressmen
Authors	Lucas S. Oliveira, Pedro O. S. Vaz de Melo, Marcelo S. Amaral, José Antônio. G. Pinho
Abstract	Since June 2013, when Brazil faced the largest and most significant mass protests in a generation, a political crisis is in course. In midst of this crisis, Brazilian politicians use social media to communicate with the electorate in order to retain or to grow their political capital. The problem is that many controversial topics are in course and deputies may prefer to avoid such themes in their messages. To characterize this behavior, we propose a method to accurately identify political and non-political tweets independently of the deputy who posted it and of the time it was posted. Moreover, we collected tweets of all congressmen who were active on Twitter and worked in the Brazilian parliament from October 2013 to October 2017. To evaluate our method, we used word clouds and a topic model to identify the main political and non-political latent topics in parliamentarian tweets. Both results indicate that our proposal is able to accurately distinguish political from non-political tweets. Moreover, our analyses revealed a striking fact: more than half of the messages posted by Brazilian deputies are non-political.
Tasks
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01589v1
PDF	http://arxiv.org/pdf/1805.01589v1.pdf
PWC	https://paperswithcode.com/paper/when-politicians-talk-about-politics
Repo
Framework

Reward Learning from Narrated Demonstrations


Title	Reward Learning from Narrated Demonstrations
Authors	Hsiao-Yu Fish Tung, Adam W. Harley, Liang-Kang Huang, Katerina Fragkiadaki
Abstract	Humans effortlessly “program” one another by communicating goals and desires in natural language. In contrast, humans program robotic behaviours by indicating desired object locations and poses to be achieved, by providing RGB images of goal configurations, or supplying a demonstration to be imitated. None of these methods generalize across environment variations, and they convey the goal in awkward technical terms. This work proposes joint learning of natural language grounding and instructable behavioural policies reinforced by perceptual detectors of natural language expressions, grounded to the sensory inputs of the robotic agent. Our supervision is narrated visual demonstrations(NVD), which are visual demonstrations paired with verbal narration (as opposed to being silent). We introduce a dataset of NVD where teachers perform activities while describing them in detail. We map the teachers’ descriptions to perceptual reward detectors, and use them to train corresponding behavioural policies in simulation.We empirically show that our instructable agents (i) learn visual reward detectors using a small number of examples by exploiting hard negative mined configurations from demonstration dynamics, (ii) develop pick-and place policies using learned visual reward detectors, (iii) benefit from object-factorized state representations that mimic the syntactic structure of natural language goal expressions, and (iv) can execute behaviours that involve novel objects in novel locations at test time, instructed by natural language.
Tasks
Published	2018-04-27
URL	http://arxiv.org/abs/1804.10692v1
PDF	http://arxiv.org/pdf/1804.10692v1.pdf
PWC	https://paperswithcode.com/paper/reward-learning-from-narrated-demonstrations
Repo
Framework

Using Neural Network for Identifying Clickbaits in Online News Media


Title	Using Neural Network for Identifying Clickbaits in Online News Media
Authors	Amin Omidvar, Hui Jiang, Aijun An
Abstract	Online news media sometimes use misleading headlines to lure users to open the news article. These catchy headlines that attract users but disappointed them at the end, are called Clickbaits. Because of the importance of automatic clickbait detection in online medias, lots of machine learning methods were proposed and employed to find the clickbait headlines. In this research, a model using deep learning methods is proposed to find the clickbaits in Clickbait Challenge 2017’s dataset. The proposed model gained the first rank in the Clickbait Challenge 2017 in terms of Mean Squared Error. Also, data analytics and visualization techniques are employed to explore and discover the provided dataset to get more insight from the data.
Tasks	Clickbait Detection
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07713v1
PDF	http://arxiv.org/pdf/1806.07713v1.pdf
PWC	https://paperswithcode.com/paper/using-neural-network-for-identifying
Repo
Framework

Inner Space Preserving Generative Pose Machine


Title	Inner Space Preserving Generative Pose Machine
Authors	Shuangjun Liu, Sarah Ostadabbas
Abstract	Image-based generative methods, such as generative adversarial networks (GANs) have already been able to generate realistic images with much context control, specially when they are conditioned. However, most successful frameworks share a common procedure which performs an image-to-image translation with pose of figures in the image untouched. When the objective is reposing a figure in an image while preserving the rest of the image, the state-of-the-art mainly assumes a single rigid body with simple background and limited pose shift, which can hardly be extended to the images under normal settings. In this paper, we introduce an image “inner space” preserving model that assigns an interpretable low-dimensional pose descriptor (LDPD) to an articulated figure in the image. Figure reposing is then generated by passing the LDPD and the original image through multi-stage augmented hourglass networks in a conditional GAN structure, called inner space preserving generative pose machine (ISP-GPM). We evaluated ISP-GPM on reposing human figures, which are highly articulated with versatile variations. Test of a state-of-the-art pose estimator on our reposed dataset gave an accuracy over 80% on PCK0.5 metric. The results also elucidated that our ISP-GPM is able to preserve the background with high accuracy while reasonably recovering the area blocked by the figure to be reposed.
Tasks	Image-to-Image Translation
Published	2018-08-06
URL	http://arxiv.org/abs/1808.02104v1
PDF	http://arxiv.org/pdf/1808.02104v1.pdf
PWC	https://paperswithcode.com/paper/inner-space-preserving-generative-pose
Repo
Framework

StationPlot: A New Non-stationarity Quantification Tool for Detection of Epileptic Seizures


Title	StationPlot: A New Non-stationarity Quantification Tool for Detection of Epileptic Seizures
Authors	Sawon Pratiher, Subhankar Chattoraj, Rajdeep Mukherjee
Abstract	A novel non-stationarity visualization tool known as StationPlot is developed for deciphering the chaotic behavior of a dynamical time series. A family of analytic measures enumerating geometrical aspects of the non-stationarity & degree of variability is formulated by convex hull geometry (CHG) on StationPlot. In the Euclidean space, both trend-stationary (TS) & difference-stationary (DS) perturbations are comprehended by the asymmetric structure of StationPlot’s region of interest (ROI). The proposed method is experimentally validated using EEG signals, where it comprehend the relative temporal evolution of neural dynamics & its non-stationary morphology, thereby exemplifying its diagnostic competence for seizure activity (SA) detection. Experimental results & analysis-of-Variance (ANOVA) on the extracted CHG features demonstrates better classification performances as compared to the existing shallow feature based state-of-the-art & validates its efficacy as geometry-rich discriminative descriptors for signal processing applications.
Tasks	EEG, Seizure Detection, Time Series
Published	2018-11-10
URL	http://arxiv.org/abs/1811.04230v1
PDF	http://arxiv.org/pdf/1811.04230v1.pdf
PWC	https://paperswithcode.com/paper/stationplot-a-new-non-stationarity
Repo
Framework

Virtual-to-Real: Learning to Control in Visual Semantic Segmentation


Title	Virtual-to-Real: Learning to Control in Visual Semantic Segmentation
Authors	Zhang-Wei Hong, Chen Yu-Ming, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Hsuan-Kung Yang, Brian Hsi-Lin Ho, Chih-Chieh Tu, Yueh-Chuan Chang, Tsu-Ching Hsiao, Hsin-Wei Hsiao, Sih-Pin Lai, Chun-Yi Lee
Abstract	Collecting training data from the physical world is usually time-consuming and even dangerous for fragile robots, and thus, recent advances in robot learning advocate the use of simulators as the training platform. Unfortunately, the reality gap between synthetic and real visual data prohibits direct migration of the models trained in virtual worlds to the real world. This paper proposes a modular architecture for tackling the virtual-to-real problem. The proposed architecture separates the learning model into a perception module and a control policy module, and uses semantic image segmentation as the meta representation for relating these two modules. The perception module translates the perceived RGB image to semantic image segmentation. The control policy module is implemented as a deep reinforcement learning agent, which performs actions based on the translated image segmentation. Our architecture is evaluated in an obstacle avoidance task and a target following task. Experimental results show that our architecture significantly outperforms all of the baseline methods in both virtual and real environments, and demonstrates a faster learning curve than them. We also present a detailed analysis for a variety of variant configurations, and validate the transferability of our modular architecture.
Tasks	Semantic Segmentation
Published	2018-02-01
URL	http://arxiv.org/abs/1802.00285v4
PDF	http://arxiv.org/pdf/1802.00285v4.pdf
PWC	https://paperswithcode.com/paper/virtual-to-real-learning-to-control-in-visual
Repo
Framework

Simultaneous shot inversion for nonuniform geometries using fast data interpolation


Title	Simultaneous shot inversion for nonuniform geometries using fast data interpolation
Authors	Michelle Liu, Rajiv Kumar, Eldad Haber, Aleksandr Aravkin
Abstract	Stochastic optimization is key to efficient inversion in PDE-constrained optimization. Using ‘simultaneous shots’, or random superposition of source terms, works very well in simple acquisition geometries where all sources see all receivers, but this rarely occurs in practice. We develop an approach that interpolates data to an ideal acquisition geometry while solving the inverse problem using simultaneous shots. The approach is formulated as a joint inverse problem, combining ideas from low-rank interpolation with full-waveform inversion. Results using synthetic experiments illustrate the flexibility and efficiency of the approach.
Tasks	Stochastic Optimization
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08697v1
PDF	http://arxiv.org/pdf/1804.08697v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-shot-inversion-for-nonuniform
Repo
Framework

Generating equilibrium molecules with deep neural networks


Title	Generating equilibrium molecules with deep neural networks
Authors	Niklas W. A. Gebauer, Michael Gastegger, Kristof T. Schütt
Abstract	Discovery of atomistic systems with desirable properties is a major challenge in chemistry and material science. Here we introduce a novel, autoregressive, convolutional deep neural network architecture that generates molecular equilibrium structures by sequentially placing atoms in three-dimensional space. The model estimates the joint probability over molecular configurations with tractable conditional probabilities which only depend on distances between atoms and their nuclear charges. It combines concepts from state-of-the-art atomistic neural networks with auto-regressive generative models for images and speech. We demonstrate that the architecture is capable of generating molecules close to equilibrium for constitutional isomers of C$_7$O$_2$H$_{10}$.
Tasks
Published	2018-10-26
URL	http://arxiv.org/abs/1810.11347v1
PDF	http://arxiv.org/pdf/1810.11347v1.pdf
PWC	https://paperswithcode.com/paper/generating-equilibrium-molecules-with-deep
Repo
Framework

Variational Inference: A Unified Framework of Generative Models and Some Revelations


Title	Variational Inference: A Unified Framework of Generative Models and Some Revelations
Authors	Jianlin Su
Abstract	We reinterpreting the variational inference in a new perspective. Via this way, we can easily prove that EM algorithm, VAE, GAN, AAE, ALI(BiGAN) are all special cases of variational inference. The proof also reveals the loss of standard GAN is incomplete and it explains why we need to train GAN cautiously. From that, we find out a regularization term to improve stability of GAN training.
Tasks
Published	2018-07-16
URL	http://arxiv.org/abs/1807.05936v4
PDF	http://arxiv.org/pdf/1807.05936v4.pdf
PWC	https://paperswithcode.com/paper/variational-inference-a-unified-framework-of
Repo
Framework

Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities


Title	Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities
Authors	Marinka Zitnik, Francis Nguyen, Bo Wang, Jure Leskovec, Anna Goldenberg, Michael M. Hoffman
Abstract	New technologies have enabled the investigation of biology and human health at an unprecedented scale and in multiple dimensions. These dimensions include a myriad of properties describing genome, epigenome, transcriptome, microbiome, phenotype, and lifestyle. No single data type, however, can capture the complexity of all the factors relevant to understanding a phenomenon such as a disease. Integrative methods that combine data from multiple technologies have thus emerged as critical statistical and computational approaches. The key challenge in developing such approaches is the identification of effective models to provide a comprehensive and relevant systems view. An ideal method can answer a biological or medical question, identifying important features and predicting outcomes, by harnessing heterogeneous data across several dimensions of biological variation. In this Review, we describe the principles of data integration and discuss current methods and available implementations. We provide examples of successful data integration in biology and medicine. Finally, we discuss current challenges in biomedical integrative methods and our perspective on the future development of the field.
Tasks
Published	2018-06-30
URL	http://arxiv.org/abs/1807.00123v2
PDF	http://arxiv.org/pdf/1807.00123v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-integrating-data-in
Repo
Framework

DeepTracker: Visualizing the Training Process of Convolutional Neural Networks


Title	DeepTracker: Visualizing the Training Process of Convolutional Neural Networks
Authors	Dongyu Liu, Weiwei Cui, Kai Jin, Yuxiao Guo, Huamin Qu
Abstract	Deep convolutional neural networks (CNNs) have achieved remarkable success in various fields. However, training an excellent CNN is practically a trial-and-error process that consumes a tremendous amount of time and computer resources. To accelerate the training process and reduce the number of trials, experts need to understand what has occurred in the training process and why the resulting CNN behaves as such. However, current popular training platforms, such as TensorFlow, only provide very little and general information, such as training/validation errors, which is far from enough to serve this purpose. To bridge this gap and help domain experts with their training tasks in a practical environment, we propose a visual analytics system, DeepTracker, to facilitate the exploration of the rich dynamics of CNN training processes and to identify the unusual patterns that are hidden behind the huge amount of training log. Specifically,we combine a hierarchical index mechanism and a set of hierarchical small multiples to help experts explore the entire training log from different levels of detail. We also introduce a novel cube-style visualization to reveal the complex correlations among multiple types of heterogeneous training data including neuron weights, validation images, and training iterations. Three case studies are conducted to demonstrate how DeepTracker provides its users with valuable knowledge in an industry-level CNN training process, namely in our case, training ResNet-50 on the ImageNet dataset. We show that our method can be easily applied to other state-of-the-art “very deep” CNN models.
Tasks
Published	2018-08-26
URL	http://arxiv.org/abs/1808.08531v1
PDF	http://arxiv.org/pdf/1808.08531v1.pdf
PWC	https://paperswithcode.com/paper/deeptracker-visualizing-the-training-process
Repo
Framework

Sentence Segmentation for Classical Chinese Based on LSTM with Radical Embedding


Title	Sentence Segmentation for Classical Chinese Based on LSTM with Radical Embedding
Authors	Xu Han, Hongsu Wang, Sanqian Zhang, Qunchao Fu, Jun S. Liu
Abstract	In this paper, we develop a low than character feature embedding called radical embedding, and apply it on LSTM model for sentence segmentation of pre modern Chinese texts. The datasets includes over 150 classical Chinese books from 3 different dynasties and contains different literary styles. LSTM CRF model is a state of art method for the sequence labeling problem. Our new model adds a component of radical embedding, which leads to improved performances. Experimental results based on the aforementioned Chinese books demonstrates a better accuracy than earlier methods on sentence segmentation, especial in Tang Epitaph texts.
Tasks
Published	2018-10-05
URL	http://arxiv.org/abs/1810.03479v1
PDF	http://arxiv.org/pdf/1810.03479v1.pdf
PWC	https://paperswithcode.com/paper/sentence-segmentation-for-classical-chinese
Repo
Framework