October 18, 2019

2894 words 14 mins read

Paper Group ANR 554

Transfer Topic Labeling with Domain-Specific Knowledge Base: An Analysis of UK House of Commons Speeches 1935-2014. Sleep-wake classification via quantifying heart rate variability by convolutional neural network. The Effect of Network Width on the Performance of Large-batch Training. CapProNet: Deep Feature Learning via Orthogonal Projections onto …

Transfer Topic Labeling with Domain-Specific Knowledge Base: An Analysis of UK House of Commons Speeches 1935-2014


Title	Transfer Topic Labeling with Domain-Specific Knowledge Base: An Analysis of UK House of Commons Speeches 1935-2014
Authors	Alexander Herzog, Peter John, Slava Jankin Mikhaylov
Abstract	Topic models are widely used in natural language processing, allowing researchers to estimate the underlying themes in a collection of documents. Most topic models use unsupervised methods and hence require the additional step of attaching meaningful labels to estimated topics. This process of manual labeling is not scalable and suffers from human bias. We present a semi-automatic transfer topic labeling method that seeks to remedy these problems. Domain-specific codebooks form the knowledge-base for automated topic labeling. We demonstrate our approach with a dynamic topic model analysis of the complete corpus of UK House of Commons speeches 1935-2014, using the coding instructions of the Comparative Agendas Project to label topics. We show that our method works well for a majority of the topics we estimate; but we also find that institution-specific topics, in particular on subnational governance, require manual input. We validate our results using human expert coding.
Tasks	Topic Models
Published	2018-06-03
URL	http://arxiv.org/abs/1806.00793v2
PDF	http://arxiv.org/pdf/1806.00793v2.pdf
PWC	https://paperswithcode.com/paper/transfer-topic-labeling-with-domain-specific
Repo
Framework

Sleep-wake classification via quantifying heart rate variability by convolutional neural network


Title	Sleep-wake classification via quantifying heart rate variability by convolutional neural network
Authors	John Malik, Yu-Lun Lo, Hau-tieng Wu
Abstract	Fluctuations in heart rate are intimately tied to changes in the physiological state of the organism. We examine and exploit this relationship by classifying a human subject’s wake/sleep status using his instantaneous heart rate (IHR) series. We use a convolutional neural network (CNN) to build features from the IHR series extracted from a whole-night electrocardiogram (ECG) and predict every 30 seconds whether the subject is awake or asleep. Our training database consists of 56 normal subjects, and we consider three different databases for validation; one is private, and two are public with different races and apnea severities. On our private database of 27 subjects, our accuracy, sensitivity, specificity, and AUC values for predicting the wake stage are 83.1%, 52.4%, 89.4%, and 0.83, respectively. Validation performance is similar on our two public databases. When we use the photoplethysmography instead of the ECG to obtain the IHR series, the performance is also comparable. A robustness check is carried out to confirm the obtained performance statistics. This result advocates for an effective and scalable method for recognizing changes in physiological state using non-invasive heart rate monitoring. The CNN model adaptively quantifies IHR fluctuation as well as its location in time and is suitable for differentiating between the wake and sleep stages.
Tasks	Heart Rate Variability
Published	2018-08-01
URL	http://arxiv.org/abs/1808.00142v1
PDF	http://arxiv.org/pdf/1808.00142v1.pdf
PWC	https://paperswithcode.com/paper/sleep-wake-classification-via-quantifying
Repo
Framework

The Effect of Network Width on the Performance of Large-batch Training


Title	The Effect of Network Width on the Performance of Large-batch Training
Authors	Lingjiao Chen, Hongyi Wang, Jinman Zhao, Dimitris Papailiopoulos, Paraschos Koutris
Abstract	Distributed implementations of mini-batch stochastic gradient descent (SGD) suffer from communication overheads, attributed to the high frequency of gradient updates inherent in small-batch training. Training with large batches can reduce these overheads; however, large batches can affect the convergence properties and generalization performance of SGD. In this work, we take a first step towards analyzing how the structure (width and depth) of a neural network affects the performance of large-batch training. We present new theoretical results which suggest that–for a fixed number of parameters–wider networks are more amenable to fast large-batch training compared to deeper ones. We provide extensive experiments on residual and fully-connected neural networks which suggest that wider networks can be trained using larger batches without incurring a convergence slow-down, unlike their deeper variants.
Tasks
Published	2018-06-11
URL	http://arxiv.org/abs/1806.03791v1
PDF	http://arxiv.org/pdf/1806.03791v1.pdf
PWC	https://paperswithcode.com/paper/the-effect-of-network-width-on-the
Repo
Framework

CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces


Title	CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces
Authors	Liheng Zhang, Marzieh Edraki, Guo-Jun Qi
Abstract	In this paper, we formalize the idea behind capsule nets of using a capsule vector rather than a neuron activation to predict the label of samples. To this end, we propose to learn a group of capsule subspaces onto which an input feature vector is projected. Then the lengths of resultant capsules are used to score the probability of belonging to different classes. We train such a Capsule Projection Network (CapProNet) by learning an orthogonal projection matrix for each capsule subspace, and show that each capsule subspace is updated until it contains input feature vectors corresponding to the associated class. We will also show that the capsule projection can be viewed as normalizing the multiple columns of the weight matrix simultaneously to form an orthogonal basis, which makes it more effective in incorporating novel components of input features to update capsule representations. In other words, the capsule projection can be viewed as a multi-dimensional weight normalization in capsule subspaces, where the conventional weight normalization is simply a special case of the capsule projection onto 1D lines. Only a small negligible computing overhead is incurred to train the network in low-dimensional capsule subspaces or through an alternative hyper-power iteration to estimate the normalization matrix. Experiment results on image datasets show the presented model can greatly improve the performance of the state-of-the-art ResNet backbones by $10-20%$ and that of the Densenet by $5-7%$ respectively at the same level of computing and memory expenses. The CapProNet establishes the competitive state-of-the-art performance for the family of capsule nets by significantly reducing test errors on the benchmark datasets.
Tasks
Published	2018-05-19
URL	http://arxiv.org/abs/1805.07621v2
PDF	http://arxiv.org/pdf/1805.07621v2.pdf
PWC	https://paperswithcode.com/paper/cappronet-deep-feature-learning-via
Repo
Framework

Online optimal exact identification of a quantum change point


Title	Online optimal exact identification of a quantum change point
Authors	Gael Sentís, Esteban Martínez-Vargas, Ramon Muñoz-Tapia
Abstract	We consider online detection strategies for identifying a change point in a stream of quantum particles allegedly prepared in identical states. We show that the identification of the change point can be done without error via sequential local measurements while attaining the optimal performance bound set by quantum mechanics. In this way, we establish the task of exactly identifying a quantum change point as an instance where local protocols are as powerful as global ones. The optimal online detection strategy requires only one bit of memory between subsequent measurements, and it is amenable to experimental realization with current technology.
Tasks
Published	2018-02-01
URL	http://arxiv.org/abs/1802.00280v2
PDF	http://arxiv.org/pdf/1802.00280v2.pdf
PWC	https://paperswithcode.com/paper/online-optimal-exact-identification-of-a
Repo
Framework

A Novel Blaschke Unwinding Adaptive Fourier Decomposition based Signal Compression Algorithm with Application on ECG Signals


Title	A Novel Blaschke Unwinding Adaptive Fourier Decomposition based Signal Compression Algorithm with Application on ECG Signals
Authors	Chunyu Tan, Liming Zhang, Hau-tieng Wu
Abstract	This paper presents a novel signal compression algorithm based on the Blaschke unwinding adaptive Fourier decomposition (AFD). The Blaschke unwinding AFD is a newly developed signal decomposition theory. It utilizes the Nevanlinna factorization and the maximal selection principle in each decomposition step, and achieves a faster convergence rate with higher fidelity. The proposed compression algorithm is applied to the electrocardiogram signal. To assess the performance of the proposed compression algorithm, in addition to the generic assessment criteria, we consider the less discussed criteria related to the clinical needs – for the heart rate variability analysis purpose, how accurate the R peak information is preserved is evaluated. The experiments are conducted on the MIT-BIH arrhythmia benchmark database. The results show that the proposed algorithm performs better than other state-of-the-art approaches. Meanwhile, it also well preserves the R peak information.
Tasks	Heart Rate Variability
Published	2018-03-17
URL	http://arxiv.org/abs/1803.06441v1
PDF	http://arxiv.org/pdf/1803.06441v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-blaschke-unwinding-adaptive-fourier
Repo
Framework

The AGINAO Self-Programming Engine


Title	The AGINAO Self-Programming Engine
Authors	Wojciech Skaba
Abstract	The AGINAO is a project to create a human-level artificial general intelligence system (HL AGI) embodied in the Aldebaran Robotics’ NAO humanoid robot. The dynamical and open-ended cognitive engine of the robot is represented by an embedded and multi-threaded control program, that is self-crafted rather than hand-crafted, and is executed on a simulated Universal Turing Machine (UTM). The actual structure of the cognitive engine emerges as a result of placing the robot in a natural preschool-like environment and running a core start-up system that executes self-programming of the cognitive layer on top of the core layer. The data from the robot’s sensory devices supplies the training samples for the machine learning methods, while the commands sent to actuators enable testing hypotheses and getting a feedback. The individual self-created subroutines are supposed to reflect the patterns and concepts of the real world, while the overall program structure reflects the spatial and temporal hierarchy of the world dependencies. This paper focuses on the details of the self-programming approach, limiting the discussion of the applied cognitive architecture to a necessary minimum.
Tasks
Published	2018-04-10
URL	http://arxiv.org/abs/1804.03437v1
PDF	http://arxiv.org/pdf/1804.03437v1.pdf
PWC	https://paperswithcode.com/paper/the-aginao-self-programming-engine
Repo
Framework

Multilevel MIMO Detection with Deep Learning


Title	Multilevel MIMO Detection with Deep Learning
Authors	Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, Loïc Brunel
Abstract	A quasi-static flat multiple-antenna channel is considered. We show how real multilevel modulation symbols can be detected via deep neural networks. A multi-plateau sigmoid function is introduced. Then, after showing the DNN architecture for detection, we propose a twin-network neural structure. Batch size and training statistics for efficient learning are investigated. Near-Maximum-Likelihood performance with a relatively reasonable number of parameters is achieved.
Tasks
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01571v2
PDF	http://arxiv.org/pdf/1812.01571v2.pdf
PWC	https://paperswithcode.com/paper/multilevel-mimo-detection-with-deep-learning
Repo
Framework

Domain Adaptation for Statistical Machine Translation


Title	Domain Adaptation for Statistical Machine Translation
Authors	Longyue Wang
Abstract	Statistical machine translation (SMT) systems perform poorly when it is applied to new target domains. Our goal is to explore domain adaptation approaches and techniques for improving the translation quality of domain-specific SMT systems. However, translating texts from a specific domain (e.g., medicine) is full of challenges. The first challenge is ambiguity. Words or phrases contain different meanings in different contexts. The second one is language style due to the fact that texts from different genres are always presented in different syntax, length and structural organization. The third one is the out-of-vocabulary words (OOVs) problem. In-domain training data are often scarce with low terminology coverage. In this thesis, we explore the state-of-the-art domain adaptation approaches and propose effective solutions to address those problems.
Tasks	Domain Adaptation, Machine Translation
Published	2018-04-05
URL	http://arxiv.org/abs/1804.01760v1
PDF	http://arxiv.org/pdf/1804.01760v1.pdf
PWC	https://paperswithcode.com/paper/domain-adaptation-for-statistical-machine
Repo
Framework

Characterizing Implicit Bias in Terms of Optimization Geometry


Title	Characterizing Implicit Bias in Terms of Optimization Geometry
Authors	Suriya Gunasekar, Jason Lee, Daniel Soudry, Nathan Srebro
Abstract	We study the implicit bias of generic optimization methods, such as mirror descent, natural gradient descent, and steepest descent with respect to different potentials and norms, when optimizing underdetermined linear regression or separable linear classification problems. We explore the question of whether the specific global minimum (among the many possible global minima) reached by an algorithm can be characterized in terms of the potential or norm of the optimization geometry, and independently of hyperparameter choices such as step-size and momentum.
Tasks
Published	2018-02-22
URL	http://arxiv.org/abs/1802.08246v2
PDF	http://arxiv.org/pdf/1802.08246v2.pdf
PWC	https://paperswithcode.com/paper/characterizing-implicit-bias-in-terms-of
Repo
Framework

Domain Modelling in Computational Persuasion for Behaviour Change in Healthcare


Title	Domain Modelling in Computational Persuasion for Behaviour Change in Healthcare
Authors	Lisa Chalaguine, Emmanuel Hadoux, Fiona Hamilton, Andrew Hayward, Anthony Hunter, Sylwia Polberg, Henry W. W. Potts
Abstract	The aim of behaviour change is to help people to change aspects of their behaviour for the better (e.g., to decrease calorie intake, to drink in moderation, to take more exercise, to complete a course of antibiotics once started, etc.). In current persuasion technology for behaviour change, the emphasis is on helping people to explore their issues (e.g., through questionnaires or game playing) or to remember to follow a behaviour change plan (e.g., diaries and email reminders). However, recent developments in computational persuasion are leading to an argument-centric approach to persuasion that can potentially be harnessed in behaviour change applications. In this paper, we review developments in computational persuasion, and then focus on domain modelling as a key component. We present a multi-dimensional approach to domain modelling. At the core of this proposal is an ontology which provides a representation of key factors, in particular kinds of belief, which we have identified in the behaviour change literature as being important in diverse behaviour change initiatives. Our proposal for domain modelling is intended to facilitate the acquisition and representation of the arguments that can be used in persuasion dialogues, together with meta-level information about them which can be used by the persuader to make strategic choices of argument to present.
Tasks
Published	2018-02-27
URL	http://arxiv.org/abs/1802.10054v1
PDF	http://arxiv.org/pdf/1802.10054v1.pdf
PWC	https://paperswithcode.com/paper/domain-modelling-in-computational-persuasion
Repo
Framework

Joint & Progressive Learning from High-Dimensional Data for Multi-Label Classification


Title	Joint & Progressive Learning from High-Dimensional Data for Multi-Label Classification
Authors	Danfeng Hong, Naoto Yokoya, Jian Xu, Xiaoxiang Zhu
Abstract	Despite the fact that nonlinear subspace learning techniques (e.g. manifold learning) have successfully applied to data representation, there is still room for improvement in explainability (explicit mapping), generalization (out-of-samples), and cost-effectiveness (linearization). To this end, a novel linearized subspace learning technique is developed in a joint and progressive way, called \textbf{j}oint and \textbf{p}rogressive \textbf{l}earning str\textbf{a}teg\textbf{y} (J-Play), with its application to multi-label classification. The J-Play learns high-level and semantically meaningful feature representation from high-dimensional data by 1) jointly performing multiple subspace learning and classification to find a latent subspace where samples are expected to be better classified; 2) progressively learning multi-coupled projections to linearly approach the optimal mapping bridging the original space with the most discriminative subspace; 3) locally embedding manifold structure in each learnable latent subspace. Extensive experiments are performed to demonstrate the superiority and effectiveness of the proposed method in comparison with previous state-of-the-art methods.
Tasks	Multi-Label Classification
Published	2018-08-15
URL	http://arxiv.org/abs/1808.05110v1
PDF	http://arxiv.org/pdf/1808.05110v1.pdf
PWC	https://paperswithcode.com/paper/joint-progressive-learning-from-high
Repo
Framework


Title	Personalized Dynamics Models for Adaptive Assistive Navigation Systems
Authors	Eshed Ohn-Bar, Kris Kitani, Chieko Asakawa
Abstract	Consider an assistive system that guides visually impaired users through speech and haptic feedback to their destination. Existing robotic and ubiquitous navigation technologies (e.g., portable, ground, or wearable systems) often operate in a generic, user-agnostic manner. However, to minimize confusion and navigation errors, our real-world analysis reveals a crucial need to adapt the instructional guidance across different end-users with diverse mobility skills. To address this practical issue in scalable system design, we propose a novel model-based reinforcement learning framework for personalizing the system-user interaction experience. When incrementally adapting the system to new users, we propose to use a weighted experts model for addressing data-efficiency limitations in transfer learning with deep models. A real-world dataset of navigation by blind users is used to show that the proposed approach allows for (1) more accurate long-term human behavior prediction (up to 20 seconds into the future) through improved reasoning over personal mobility characteristics, interaction with surrounding obstacles, and the current navigation goal, and (2) quick adaptation at the onset of learning, when data is limited.
Tasks	Transfer Learning
Published	2018-04-11
URL	http://arxiv.org/abs/1804.04118v2
PDF	http://arxiv.org/pdf/1804.04118v2.pdf
PWC	https://paperswithcode.com/paper/personalized-dynamics-models-for-adaptive
Repo
Framework

Iterative Crowd Counting


Title	Iterative Crowd Counting
Authors	Viresh Ranjan, Hieu Le, Minh Hoai
Abstract	In this work, we tackle the problem of crowd counting in images. We present a Convolutional Neural Network (CNN) based density estimation approach to solve this problem. Predicting a high resolution density map in one go is a challenging task. Hence, we present a two branch CNN architecture for generating high resolution density maps, where the first branch generates a low resolution density map, and the second branch incorporates the low resolution prediction and feature maps from the first branch to generate a high resolution density map. We also propose a multi-stage extension of our approach where each stage in the pipeline utilizes the predictions from all the previous stages. Empirical comparison with the previous state-of-the-art crowd counting methods shows that our method achieves the lowest mean absolute error on three challenging crowd counting benchmarks: Shanghaitech, WorldExpo’10, and UCF datasets.
Tasks	Crowd Counting, Density Estimation
Published	2018-07-26
URL	http://arxiv.org/abs/1807.09959v1
PDF	http://arxiv.org/pdf/1807.09959v1.pdf
PWC	https://paperswithcode.com/paper/iterative-crowd-counting
Repo
Framework

Geodesic Clustering in Deep Generative Models


Title	Geodesic Clustering in Deep Generative Models
Authors	Tao Yang, Georgios Arvanitidis, Dongmei Fu, Xiaogang Li, Søren Hauberg
Abstract	Deep generative models are tremendously successful in learning low-dimensional latent representations that well-describe the data. These representations, however, tend to much distort relationships between points, i.e. pairwise distances tend to not reflect semantic similarities well. This renders unsupervised tasks, such as clustering, difficult when working with the latent representations. We demonstrate that taking the geometry of the generative model into account is sufficient to make simple clustering algorithms work well over latent representations. Leaning on the recent finding that deep generative models constitute stochastically immersed Riemannian manifolds, we propose an efficient algorithm for computing geodesics (shortest paths) and computing distances in the latent space, while taking its distortion into account. We further propose a new architecture for modeling uncertainty in variational autoencoders, which is essential for understanding the geometry of deep generative models. Experiments show that the geodesic distance is very likely to reflect the internal structure of the data.
Tasks
Published	2018-09-13
URL	http://arxiv.org/abs/1809.04747v1
PDF	http://arxiv.org/pdf/1809.04747v1.pdf
PWC	https://paperswithcode.com/paper/geodesic-clustering-in-deep-generative-models
Repo
Framework