July 28, 2019

3001 words 15 mins read

Paper Group ANR 301

A Note on Community Trees in Networks. Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems. View-invariant Gait Recognition through Genetic Template Segmentation. Practical Coreset Constructions for Machine Learning. Efficient-UCBV: An Almost Optimal Algorithm using Variance Estimates. Non-parametric Est …

A Note on Community Trees in Networks


Title	A Note on Community Trees in Networks
Authors	Ruqian Chen, Yen-Chi Chen, Wei Guo, Ashis G. Banerjee
Abstract	We introduce the concept of community trees that summarizes topological structures within a network. A community tree is a tree structure representing clique communities from the clique percolation method (CPM). The community tree also generates a persistent diagram. Community trees and persistent diagrams reveal topological structures of the underlying networks and can be used as visualization tools. We study the stability of community trees and derive a quantity called the total star number (TSN) that presents an upper bound on the change of community trees. Our findings provide a topological interpretation for the stability of communities generated by the CPM.
Tasks
Published	2017-10-11
URL	http://arxiv.org/abs/1710.03924v1
PDF	http://arxiv.org/pdf/1710.03924v1.pdf
PWC	https://paperswithcode.com/paper/a-note-on-community-trees-in-networks
Repo
Framework

Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems


Title	Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems
Authors	Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao, Asli Celikyilmaz
Abstract	Language understanding is a key component in a spoken dialogue system. In this paper, we investigate how the language understanding module influences the dialogue system performance by conducting a series of systematic experiments on a task-oriented neural dialogue system in a reinforcement learning based setting. The empirical study shows that among different types of language understanding errors, slot-level errors can have more impact on the overall performance of a dialogue system compared to intent-level errors. In addition, our experiments demonstrate that the reinforcement learning based dialogue system is able to learn when and what to confirm in order to achieve better performance and greater robustness.
Tasks
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07055v1
PDF	http://arxiv.org/pdf/1703.07055v1.pdf
PWC	https://paperswithcode.com/paper/investigation-of-language-understanding
Repo
Framework

View-invariant Gait Recognition through Genetic Template Segmentation


Title	View-invariant Gait Recognition through Genetic Template Segmentation
Authors	Ebenezer Isaac, Susan Elias, Srinivasan Rajagopalan, K. S. Easwarakumar
Abstract	Template-based model-free approach provides by far the most successful solution to the gait recognition problem in literature. Recent work discusses how isolating the head and leg portion of the template increase the performance of a gait recognition system making it robust against covariates like clothing and carrying conditions. However, most involve a manual definition of the boundaries. The method we propose, the genetic template segmentation (GTS), employs the genetic algorithm to automate the boundary selection process. This method was tested on the GEI, GEnI and AEI templates. GEI seems to exhibit the best result when segmented with our approach. Experimental results depict that our approach significantly outperforms the existing implementations of view-invariant gait recognition.
Tasks	Gait Recognition
Published	2017-05-15
URL	http://arxiv.org/abs/1705.05273v3
PDF	http://arxiv.org/pdf/1705.05273v3.pdf
PWC	https://paperswithcode.com/paper/view-invariant-gait-recognition-through
Repo
Framework

Practical Coreset Constructions for Machine Learning


Title	Practical Coreset Constructions for Machine Learning
Authors	Olivier Bachem, Mario Lucic, Andreas Krause
Abstract	We investigate coresets - succinct, small summaries of large data sets - so that solutions found on the summary are provably competitive with solution found on the full data set. We provide an overview over the state-of-the-art in coreset construction for machine learning. In Section 2, we present both the intuition behind and a theoretically sound framework to construct coresets for general problems and apply it to $k$-means clustering. In Section 3 we summarize existing coreset construction algorithms for a variety of machine learning problems such as maximum likelihood estimation of mixture models, Bayesian non-parametric models, principal component analysis, regression and general empirical risk minimization.
Tasks
Published	2017-03-19
URL	http://arxiv.org/abs/1703.06476v2
PDF	http://arxiv.org/pdf/1703.06476v2.pdf
PWC	https://paperswithcode.com/paper/practical-coreset-constructions-for-machine
Repo
Framework

Efficient-UCBV: An Almost Optimal Algorithm using Variance Estimates


Title	Efficient-UCBV: An Almost Optimal Algorithm using Variance Estimates
Authors	Subhojyoti Mukherjee, K. P. Naveen, Nandan Sudarsanam, Balaraman Ravindran
Abstract	We propose a novel variant of the UCB algorithm (referred to as Efficient-UCB-Variance (EUCBV)) for minimizing cumulative regret in the stochastic multi-armed bandit (MAB) setting. EUCBV incorporates the arm elimination strategy proposed in UCB-Improved \citep{auer2010ucb}, while taking into account the variance estimates to compute the arms’ confidence bounds, similar to UCBV \citep{audibert2009exploration}. Through a theoretical analysis we establish that EUCBV incurs a \emph{gap-dependent} regret bound of {\scriptsize $O\left( \dfrac{K\sigma^2_{\max} \log (T\Delta^2 /K)}{\Delta}\right)$} after $T$ trials, where $\Delta$ is the minimal gap between optimal and sub-optimal arms; the above bound is an improvement over that of existing state-of-the-art UCB algorithms (such as UCB1, UCB-Improved, UCBV, MOSS). Further, EUCBV incurs a \emph{gap-independent} regret bound of {\scriptsize $O\left(\sqrt{KT}\right)$} which is an improvement over that of UCB1, UCBV and UCB-Improved, while being comparable with that of MOSS and OCUCB. Through an extensive numerical study we show that EUCBV significantly outperforms the popular UCB variants (like MOSS, OCUCB, etc.) as well as Thompson sampling and Bayes-UCB algorithms.
Tasks
Published	2017-11-09
URL	http://arxiv.org/abs/1711.03591v1
PDF	http://arxiv.org/pdf/1711.03591v1.pdf
PWC	https://paperswithcode.com/paper/efficient-ucbv-an-almost-optimal-algorithm
Repo
Framework

Non-parametric Estimation of Stochastic Differential Equations with Sparse Gaussian Processes


Title	Non-parametric Estimation of Stochastic Differential Equations with Sparse Gaussian Processes
Authors	Constantino A. García, Abraham Otero, Paulo Félix, Jesús Presedo, David G. Márquez
Abstract	The application of Stochastic Differential Equations (SDEs) to the analysis of temporal data has attracted increasing attention, due to their ability to describe complex dynamics with physically interpretable equations. In this paper, we introduce a non-parametric method for estimating the drift and diffusion terms of SDEs from a densely observed discrete time series. The use of Gaussian processes as priors permits working directly in a function-space view and thus the inference takes place directly in this space. To cope with the computational complexity that requires the use of Gaussian processes, a sparse Gaussian process approximation is provided. This approximation permits the efficient computation of predictions for the drift and diffusion terms by using a distribution over a small subset of pseudo-samples. The proposed method has been validated using both simulated data and real data from economy and paleoclimatology. The application of the method to real data demonstrates its ability to capture the behaviour of complex systems.
Tasks	Gaussian Processes, Time Series
Published	2017-04-14
URL	http://arxiv.org/abs/1704.04375v2
PDF	http://arxiv.org/pdf/1704.04375v2.pdf
PWC	https://paperswithcode.com/paper/non-parametric-estimation-of-stochastic
Repo
Framework

Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features


Title	Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features
Authors	Jeremy Kawahara, Ghassan Hamarneh
Abstract	The presence of certain clinical dermoscopic features within a skin lesion may indicate melanoma, and automatically detecting these features may lead to more quantitative and reproducible diagnoses. We reformulate the task of classifying clinical dermoscopic features within superpixels as a segmentation problem, and propose a fully convolutional neural network to detect clinical dermoscopic features from dermoscopy skin lesion images. Our neural network architecture uses interpolated feature maps from several intermediate network layers, and addresses imbalanced labels by minimizing a negative multi-label Dice-F$_1$ score, where the score is computed across the mini-batch for each label. Our approach ranked first place in the 2017 ISIC-ISBI Part 2: Dermoscopic Feature Classification Task challenge over both the provided validation and test datasets, achieving a 0.895% area under the receiver operator characteristic curve score. We show how simple baseline models can outrank state-of-the-art approaches when using the official metrics of the challenge, and propose to use a fuzzy Jaccard Index that ignores the empty set (i.e., masks devoid of positive pixels) when ranking models. Our results suggest that (i) the classification of clinical dermoscopic features can be effectively approached as a segmentation problem, and (ii) the current metrics used to rank models may not well capture the efficacy of the model. We plan to make our trained model and code publicly available.
Tasks	Image Classification, Semantic Segmentation
Published	2017-03-14
URL	http://arxiv.org/abs/1703.04559v2
PDF	http://arxiv.org/pdf/1703.04559v2.pdf
PWC	https://paperswithcode.com/paper/fully-convolutional-networks-to-detect
Repo
Framework

Detecting Policy Preferences and Dynamics in the UN General Debate with Neural Word Embeddings


Title	Detecting Policy Preferences and Dynamics in the UN General Debate with Neural Word Embeddings
Authors	Stefano Gurciullo, Slava Mikhaylov
Abstract	Foreign policy analysis has been struggling to find ways to measure policy preferences and paradigm shifts in international political systems. This paper presents a novel, potential solution to this challenge, through the application of a neural word embedding (Word2vec) model on a dataset featuring speeches by heads of state or government in the United Nations General Debate. The paper provides three key contributions based on the output of the Word2vec model. First, it presents a set of policy attention indices, synthesizing the semantic proximity of political speeches to specific policy themes. Second, it introduces country-specific semantic centrality indices, based on topological analyses of countries’ semantic positions with respect to each other. Third, it tests the hypothesis that there exists a statistical relation between the semantic content of political speeches and UN voting behavior, falsifying it and suggesting that political speeches contain information of different nature then the one behind voting outcomes. The paper concludes with a discussion of the practical use of its results and consequences for foreign policy analysis, public accountability, and transparency.
Tasks	Word Embeddings
Published	2017-07-11
URL	http://arxiv.org/abs/1707.03490v1
PDF	http://arxiv.org/pdf/1707.03490v1.pdf
PWC	https://paperswithcode.com/paper/detecting-policy-preferences-and-dynamics-in
Repo
Framework

On the Use of Default Parameter Settings in the Empirical Evaluation of Classification Algorithms


Title	On the Use of Default Parameter Settings in the Empirical Evaluation of Classification Algorithms
Authors	Anthony Bagnall, Gavin C. Cawley
Abstract	We demonstrate that, for a range of state-of-the-art machine learning algorithms, the differences in generalisation performance obtained using default parameter settings and using parameters tuned via cross-validation can be similar in magnitude to the differences in performance observed between state-of-the-art and uncompetitive learning systems. This means that fair and rigorous evaluation of new learning algorithms requires performance comparison against benchmark methods with best-practice model selection procedures, rather than using default parameter settings. We investigate the sensitivity of three key machine learning algorithms (support vector machine, random forest and rotation forest) to their default parameter settings, and provide guidance on determining sensible default parameter values for implementations of these algorithms. We also conduct an experimental comparison of these three algorithms on 121 classification problems and find that, perhaps surprisingly, rotation forest is significantly more accurate on average than both random forest and a support vector machine.
Tasks	Model Selection
Published	2017-03-20
URL	http://arxiv.org/abs/1703.06777v1
PDF	http://arxiv.org/pdf/1703.06777v1.pdf
PWC	https://paperswithcode.com/paper/on-the-use-of-default-parameter-settings-in
Repo
Framework

Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks


Title	Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks
Authors	Xianxu Hou, Guoping Qiu
Abstract	In this paper, we introduce deep learning technology to tackle two traditional low-level image processing problems, companding and inverse halftoning. We make two main contributions. First, to the best knowledge of the authors, this is the first work that has successfully developed deep learning based solutions to these two traditional low-level image processing problems. This not only introduces new methods to tackle well-known image processing problems but also demonstrates the power of deep learning in solving traditional signal processing problems. Second, we have developed an effective deep learning algorithm based on insights into the properties of visual quality of images and the internal representation properties of a deep convolutional neural network (CNN). We train a deep CNN as a nonlinear transformation function to map a low bit depth image to higher bit depth or from a halftone image to a continuous tone image. We also employ another pretrained deep CNN as a feature extractor to derive visually important features to construct the objective function for the training of the mapping CNN. We present experimental results to demonstrate the effectiveness of the new deep learning based solutions.
Tasks
Published	2017-07-01
URL	http://arxiv.org/abs/1707.00116v2
PDF	http://arxiv.org/pdf/1707.00116v2.pdf
PWC	https://paperswithcode.com/paper/image-companding-and-inverse-halftoning-using
Repo
Framework

A Generalised Seizure Prediction with Convolutional Neural Networks for Intracranial and Scalp Electroencephalogram Data Analysis


Title	A Generalised Seizure Prediction with Convolutional Neural Networks for Intracranial and Scalp Electroencephalogram Data Analysis
Authors	Nhan Duy Truong, Anh Duy Nguyen, Levin Kuhlmann, Mohammad Reza Bonyadi, Jiawei Yang, Omid Kavehei
Abstract	Seizure prediction has attracted a growing attention as one of the most challenging predictive data analysis efforts in order to improve the life of patients living with drug-resistant epilepsy and tonic seizures. Many outstanding works have been reporting great results in providing a sensible indirect (warning systems) or direct (interactive neural-stimulation) control over refractory seizures, some of which achieved high performance. However, many works put heavily handcraft feature extraction and/or carefully tailored feature engineering to each patient to achieve very high sensitivity and low false prediction rate for a particular dataset. This limits the benefit of their approaches if a different dataset is used. In this paper we apply Convolutional Neural Networks (CNNs) on different intracranial and scalp electroencephalogram (EEG) datasets and proposed a generalized retrospective and patient-specific seizure prediction method. We use Short-Time Fourier Transform (STFT) on 30-second EEG windows with 50% overlapping to extract information in both frequency and time domains. A standardization step is then applied on STFT components across the whole frequency range to prevent high frequencies features being influenced by those at lower frequencies. A convolutional neural network model is used for both feature extraction and classification to separate preictal segments from interictal ones. The proposed approach achieves sensitivity of 81.4%, 81.2%, 82.3% and false prediction rate (FPR) of 0.06/h, 0.16/h, 0.22/h on Freiburg Hospital intracranial EEG (iEEG) dataset, Children’s Hospital of Boston-MIT scalp EEG (sEEG) dataset, and Kaggle American Epilepsy Society Seizure Prediction Challenge’s dataset, respectively. Our prediction method is also statistically better than an unspecific random predictor for most of patients in all three datasets.
Tasks	EEG, Feature Engineering, Seizure prediction
Published	2017-07-06
URL	http://arxiv.org/abs/1707.01976v2
PDF	http://arxiv.org/pdf/1707.01976v2.pdf
PWC	https://paperswithcode.com/paper/a-generalised-seizure-prediction-with
Repo
Framework

Learning Spontaneity to Improve Emotion Recognition In Speech


Title	Learning Spontaneity to Improve Emotion Recognition In Speech
Authors	Karttikeya Mangalam, Tanaya Guha
Abstract	We investigate the effect and usefulness of spontaneity (i.e. whether a given speech is spontaneous or not) in speech in the context of emotion recognition. We hypothesize that emotional content in speech is interrelated with its spontaneity, and use spontaneity classification as an auxiliary task to the problem of emotion recognition. We propose two supervised learning settings that utilize spontaneity to improve speech emotion recognition: a hierarchical model that performs spontaneity detection before performing emotion recognition, and a multitask learning model that jointly learns to recognize both spontaneity and emotion. Through various experiments on the well known IEMOCAP database, we show that by using spontaneity detection as an additional task, significant improvement can be achieved over emotion recognition systems that are unaware of spontaneity. We achieve state-of-the-art emotion recognition accuracy (4-class, 69.1%) on the IEMOCAP database outperforming several relevant and competitive baselines.
Tasks	Emotion Recognition, Speech Emotion Recognition
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04753v3
PDF	http://arxiv.org/pdf/1712.04753v3.pdf
PWC	https://paperswithcode.com/paper/learning-spontaneity-to-improve-emotion
Repo
Framework

Research on several key technologies in practical speech emotion recognition


Title	Research on several key technologies in practical speech emotion recognition
Authors	Chengwei Huang
Abstract	In this dissertation the practical speech emotion recognition technology is studied, including several cognitive related emotion types, namely fidgetiness, confidence and tiredness. The high quality of naturalistic emotional speech data is the basis of this research. The following techniques are used for inducing practical emotional speech: cognitive task, computer game, noise stimulation, sleep deprivation and movie clips. A practical speech emotion recognition system is studied based on Gaussian mixture model. A two-class classifier set is adopted for performance improvement under the small sample case. Considering the context information in continuous emotional speech, a Gaussian mixture model embedded with Markov networks is proposed. A further study is carried out for system robustness analysis. First, noise reduction algorithm based on auditory masking properties is fist introduced to the practical speech emotion recognition. Second, to deal with the complicated unknown emotion types under real situation, an emotion recognition method with rejection ability is proposed, which enhanced the system compatibility against unknown emotion samples. Third, coping with the difficulties brought by a large number of unknown speakers, an emotional feature normalization method based on speaker-sensitive feature clustering is proposed. Fourth, by adding the electrocardiogram channel, a bi-modal emotion recognition system based on speech signals and electrocardiogram signals is first introduced. The speech emotion recognition methods studied in this dissertation may be extended into the cross-language speech emotion recognition and the whispered speech emotion recognition.
Tasks	Emotion Recognition, Speech Emotion Recognition
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09364v1
PDF	http://arxiv.org/pdf/1709.09364v1.pdf
PWC	https://paperswithcode.com/paper/research-on-several-key-technologies-in
Repo
Framework

Size-Independent Sample Complexity of Neural Networks


Title	Size-Independent Sample Complexity of Neural Networks
Authors	Noah Golowich, Alexander Rakhlin, Ohad Shamir
Abstract	We study the sample complexity of learning neural networks, by providing new bounds on their Rademacher complexity assuming norm constraints on the parameter matrix of each layer. Compared to previous work, these complexity bounds have improved dependence on the network depth, and under some additional assumptions, are fully independent of the network size (both depth and width). These results are derived using some novel techniques, which may be of independent interest.
Tasks
Published	2017-12-18
URL	https://arxiv.org/abs/1712.06541v5
PDF	https://arxiv.org/pdf/1712.06541v5.pdf
PWC	https://paperswithcode.com/paper/size-independent-sample-complexity-of-neural
Repo
Framework

Learning how to learn: an adaptive dialogue agent for incrementally learning visually grounded word meanings


Title	Learning how to learn: an adaptive dialogue agent for incrementally learning visually grounded word meanings
Authors	Yanchao Yu, Arash Eshghi, Oliver Lemon
Abstract	We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data. Within a life-long interactive learning period, the agent, trained using Reinforcement Learning (RL), must be able to handle natural conversations with human users and achieve good learning performance (accuracy) while minimising human effort in the learning process. We train and evaluate this system in interaction with a simulated human tutor, which is built on the BURCHAK corpus – a Human-Human Dialogue dataset for the visual learning task. The results show that: 1) The learned policy can coherently interact with the simulated user to achieve the goal of the task (i.e. learning visual attributes of objects, e.g. colour and shape); and 2) it finds a better trade-off between classifier accuracy and tutoring costs than hand-crafted rule-based policies, including ones with dynamic policies.
Tasks
Published	2017-09-29
URL	http://arxiv.org/abs/1709.10423v1
PDF	http://arxiv.org/pdf/1709.10423v1.pdf
PWC	https://paperswithcode.com/paper/learning-how-to-learn-an-adaptive-dialogue
Repo
Framework