May 6, 2019

2750 words 13 mins read

Paper Group ANR 170

Domain based classification. 2D Discrete Fourier Transform with Simultaneous Edge Artifact Removal for Real-Time Applications. Predicting Branch Visits and Credit Card Up-selling using Temporal Banking Data. On the equivalence between Kolmogorov-Smirnov and ROC curve metrics for binary classification. Automatic discovery of discriminative parts as …

Domain based classification


Title	Domain based classification
Authors	Robert P. W. Duin, Elzbieta Pekalska
Abstract	The majority of traditional classification ru les minimizing the expected probability of error (0-1 loss) are inappropriate if the class probability distributions are ill-defined or impossible to estimate. We argue that in such cases class domains should be used instead of class distributions or densities to construct a reliable decision function. Proposals are presented for some evaluation criteria and classifier learning schemes, illustrated by an example.
Tasks
Published	2016-01-18
URL	http://arxiv.org/abs/1601.04530v2
PDF	http://arxiv.org/pdf/1601.04530v2.pdf
PWC	https://paperswithcode.com/paper/domain-based-classification
Repo
Framework

2D Discrete Fourier Transform with Simultaneous Edge Artifact Removal for Real-Time Applications


Title	2D Discrete Fourier Transform with Simultaneous Edge Artifact Removal for Real-Time Applications
Authors	Faisal Mahmood, Märt Toots, Lars-Göran Öfverstedt, Ulf Skoglund
Abstract	Two-Dimensional (2D) Discrete Fourier Transform (DFT) is a basic and computationally intensive algorithm, with a vast variety of applications. 2D images are, in general, non-periodic, but are assumed to be periodic while calculating their DFTs. This leads to cross-shaped artifacts in the frequency domain due to spectral leakage. These artifacts can have critical consequences if the DFTs are being used for further processing. In this paper we present a novel FPGA-based design to calculate high-throughput 2D DFTs with simultaneous edge artifact removal. Standard approaches for removing these artifacts using apodization functions or mirroring, either involve removing critical frequencies or a surge in computation by increasing image size. We use a periodic-plus-smooth decomposition based artifact removal algorithm optimized for FPGA implementation, while still achieving real-time ($\ge$23 frames per second) performance for a 512$\times$512 size image stream. Our optimization approach leads to a significant decrease in external memory utilization thereby avoiding memory conflicts and simplifies the design. We have tested our design on a PXIe based Xilinx Kintex 7 FPGA system communicating with a host PC which gives us the advantage to further expand the design for industrial applications.
Tasks
Published	2016-03-16
URL	http://arxiv.org/abs/1603.05154v1
PDF	http://arxiv.org/pdf/1603.05154v1.pdf
PWC	https://paperswithcode.com/paper/2d-discrete-fourier-transform-with
Repo
Framework

Predicting Branch Visits and Credit Card Up-selling using Temporal Banking Data


Title	Predicting Branch Visits and Credit Card Up-selling using Temporal Banking Data
Authors	Sandra Mitrović, Gaurav Singh
Abstract	There is an abundance of temporal and non-temporal data in banking (and other industries), but such temporal activity data can not be used directly with classical machine learning models. In this work, we perform extensive feature extraction from the temporal user activity data in an attempt to predict user visits to different branches and credit card up-selling utilizing user information and the corresponding activity data, as part of \emph{ECML/PKDD Discovery Challenge 2016 on Bank Card Usage Analysis}. Our solution ranked \nth{4} for \emph{Task 1} and achieved an AUC of \textbf{$0.7056$} for \emph{Task 2} on public leaderboard.
Tasks
Published	2016-07-20
URL	http://arxiv.org/abs/1607.06123v2
PDF	http://arxiv.org/pdf/1607.06123v2.pdf
PWC	https://paperswithcode.com/paper/predicting-branch-visits-and-credit-card-up
Repo
Framework

On the equivalence between Kolmogorov-Smirnov and ROC curve metrics for binary classification


Title	On the equivalence between Kolmogorov-Smirnov and ROC curve metrics for binary classification
Authors	Paulo J. L. Adeodato, Sílvio B. Melo
Abstract	Binary decisions are very common in artificial intelligence. Applying a threshold on the continuous score gives the human decider the power to control the operating point to separate the two classes. The classifier,s discriminating power is measured along the continuous range of the score by the Area Under the ROC curve (AUC_ROC) in most application fields. Only finances uses the poor single point metric maximum Kolmogorov-Smirnov (KS) distance. This paper proposes the Area Under the KS curve (AUC_KS) for performance assessment and proves AUC_ROC = 0.5 + AUC_KS, as a simpler way to calculate the AUC_ROC. That is even more important for ROC averaging in ensembles of classifiers or n fold cross-validation. The proof is geometrically inspired on rotating all KS curve to make it lie on the top of the ROC chance diagonal. On the practical side, the independent variable on the abscissa on the KS curve simplifies the calculation of the AUC_ROC. On the theoretical side, this research gives insights on probabilistic interpretations of classifiers assessment and integrates the existing body of knowledge of the information theoretical ROC approach with the proposed statistical approach based on the thoroughly known KS distribution.
Tasks
Published	2016-06-01
URL	http://arxiv.org/abs/1606.00496v1
PDF	http://arxiv.org/pdf/1606.00496v1.pdf
PWC	https://paperswithcode.com/paper/on-the-equivalence-between-kolmogorov-smirnov
Repo
Framework

Automatic discovery of discriminative parts as a quadratic assignment problem


Title	Automatic discovery of discriminative parts as a quadratic assignment problem
Authors	Ronan Sicre, Julien Rabin, Yannis Avrithis, Teddy Furon, Frederic Jurie
Abstract	Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built. This paper addresses the question of how to automatically learn such parts from a set of labeled training images. The training of parts is cast as a quadratic assignment problem in which optimal correspondences between image regions and parts are automatically learned. The paper analyses different assignment strategies and thoroughly evaluates them on two public datasets: Willow actions and MIT 67 scenes. State-of-the art results are obtained on these datasets.
Tasks	Image Classification
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04413v1
PDF	http://arxiv.org/pdf/1611.04413v1.pdf
PWC	https://paperswithcode.com/paper/automatic-discovery-of-discriminative-parts
Repo
Framework

Clustering by connection center evolution


Title	Clustering by connection center evolution
Authors	Xiurui Geng, Hairong Tang
Abstract	The determination of cluster centers generally depends on the scale that we use to analyze the data to be clustered. Inappropriate scale usually leads to unreasonable cluster centers and thus unreasonable results. In this study, we first consider the similarity of elements in the data as the connectivity of nodes in an undirected graph, then present the concept of a connection center and regard it as the cluster center of the data. Based on this definition, the determination of cluster centers and the assignment of class are very simple, natural and effective. One more crucial finding is that the cluster centers of different scales can be obtained easily by the different powers of a similarity matrix and the change of power from small to large leads to the dynamic evolution of cluster centers from local (microscopic) to global (microscopic). Further, in this process of evolution, the number of categories changes discontinuously, which means that the presented method can automatically skip the unreasonable number of clusters, suggest appropriate observation scales and provide corresponding cluster results.
Tasks
Published	2016-10-19
URL	http://arxiv.org/abs/1610.05956v1
PDF	http://arxiv.org/pdf/1610.05956v1.pdf
PWC	https://paperswithcode.com/paper/clustering-by-connection-center-evolution
Repo
Framework

On The Stability of Video Detection and Tracking


Title	On The Stability of Video Detection and Tracking
Authors	Hong Zhang, Naiyan Wang
Abstract	In this paper, we study an important yet less explored aspect in video detection and tracking – stability. Surprisingly, there is no prior work that tried to study it. As a result, we start our work by proposing a novel evaluation metric for video detection which considers both stability and accuracy. For accuracy, we extend the existing accuracy metric mean Average Precision (mAP). For stability, we decompose it into three terms: fragment error, center position error, scale and ratio error. Each error represents one aspect of stability. Furthermore, we demonstrate that the stability metric has low correlation with accuracy metric. Thus, it indeed captures a different perspective of quality. Lastly, based on this metric, we evaluate several existing methods for video detection and show how they affect accuracy and stability. We believe our work can provide guidance and solid baselines for future researches in the related areas.
Tasks
Published	2016-11-20
URL	http://arxiv.org/abs/1611.06467v2
PDF	http://arxiv.org/pdf/1611.06467v2.pdf
PWC	https://paperswithcode.com/paper/on-the-stability-of-video-detection-and
Repo
Framework

Gaussian Process Kernels for Popular State-Space Time Series Models


Title	Gaussian Process Kernels for Popular State-Space Time Series Models
Authors	Alexander Grigorievskiy, Juha Karhunen
Abstract	In this paper we investigate a link between state- space models and Gaussian Processes (GP) for time series modeling and forecasting. In particular, several widely used state- space models are transformed into continuous time form and corresponding Gaussian Process kernels are derived. Experimen- tal results demonstrate that the derived GP kernels are correct and appropriate for Gaussian Process Regression. An experiment with a real world dataset shows that the modeling is identical with state-space models and with the proposed GP kernels. The considered connection allows the researchers to look at their models from a different angle and facilitate sharing ideas between these two different modeling approaches.
Tasks	Gaussian Processes, Time Series
Published	2016-10-25
URL	http://arxiv.org/abs/1610.08074v1
PDF	http://arxiv.org/pdf/1610.08074v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-process-kernels-for-popular-state
Repo
Framework

Long-Term Trends in the Public Perception of Artificial Intelligence


Title	Long-Term Trends in the Public Perception of Artificial Intelligence
Authors	Ethan Fast, Eric Horvitz
Abstract	Analyses of text corpora over time can reveal trends in beliefs, interest, and sentiment about a topic. We focus on views expressed about artificial intelligence (AI) in the New York Times over a 30-year period. General interest, awareness, and discussion about AI has waxed and waned since the field was founded in 1956. We present a set of measures that captures levels of engagement, measures of pessimism and optimism, the prevalence of specific hopes and concerns, and topics that are linked to discussions about AI over decades. We find that discussion of AI has increased sharply since 2009, and that these discussions have been consistently more optimistic than pessimistic. However, when we examine specific concerns, we find that worries of loss of control of AI, ethical concerns for AI, and the negative impact of AI on work have grown in recent years. We also find that hopes for AI in healthcare and education have increased over time.
Tasks
Published	2016-09-16
URL	http://arxiv.org/abs/1609.04904v2
PDF	http://arxiv.org/pdf/1609.04904v2.pdf
PWC	https://paperswithcode.com/paper/long-term-trends-in-the-public-perception-of
Repo
Framework

Human Body Orientation Estimation using Convolutional Neural Network


Title	Human Body Orientation Estimation using Convolutional Neural Network
Authors	Jinyoung Choi, Beom-Jin Lee, Byoung-Tak Zhang
Abstract	Personal robots are expected to interact with the user by recognizing the user’s face. However, in most of the service robot applications, the user needs to move himself/herself to allow the robot to see him/her face to face. To overcome such limitations, a method for estimating human body orientation is required. Previous studies used various components such as feature extractors and classification models to classify the orientation which resulted in low performance. For a more robust and accurate approach, we propose the light weight convolutional neural networks, an end to end system, for estimating human body orientation. Our body orientation estimation model achieved 81.58% and 94% accuracy with the benchmark dataset and our own dataset respectively. The proposed method can be used in a wide range of service robot applications which depend on the ability to estimate human body orientation. To show its usefulness in service robot applications, we designed a simple robot application which allows the robot to move towards the user’s frontal plane. With this, we demonstrated an improved face detection rate.
Tasks	Face Detection
Published	2016-09-07
URL	http://arxiv.org/abs/1609.01984v1
PDF	http://arxiv.org/pdf/1609.01984v1.pdf
PWC	https://paperswithcode.com/paper/human-body-orientation-estimation-using
Repo
Framework

Improving Trajectory Modelling for DNN-based Speech Synthesis by using Stacked Bottleneck Features and Minimum Generation Error Training


Title	Improving Trajectory Modelling for DNN-based Speech Synthesis by using Stacked Bottleneck Features and Minimum Generation Error Training
Authors	Zhizheng Wu, Simon King
Abstract	We propose two novel techniques — stacking bottleneck features and minimum generation error training criterion — to improve the performance of deep neural network (DNN)-based speech synthesis. The techniques address the related issues of frame-by-frame independence and ignorance of the relationship between static and dynamic features, within current typical DNN-based synthesis frameworks. Stacking bottleneck features, which are an acoustically–informed linguistic representation, provides an efficient way to include more detailed linguistic context at the input. The minimum generation error training criterion minimises overall output trajectory error across an utterance, rather than minimising the error per frame independently, and thus takes into account the interaction between static and dynamic features. The two techniques can be easily combined to further improve performance. We present both objective and subjective results that demonstrate the effectiveness of the proposed techniques. The subjective results show that combining the two techniques leads to significantly more natural synthetic speech than from conventional DNN or long short-term memory (LSTM) recurrent neural network (RNN) systems.
Tasks	Speech Synthesis
Published	2016-02-22
URL	http://arxiv.org/abs/1602.06727v3
PDF	http://arxiv.org/pdf/1602.06727v3.pdf
PWC	https://paperswithcode.com/paper/improving-trajectory-modelling-for-dnn-based
Repo
Framework

LSTM Deep Neural Networks Postfiltering for Improving the Quality of Synthetic Voices


Title	LSTM Deep Neural Networks Postfiltering for Improving the Quality of Synthetic Voices
Authors	Marvin Coto-Jiménez, John Goddard-Close
Abstract	Recent developments in speech synthesis have produced systems capable of outcome intelligible speech, but now researchers strive to create models that more accurately mimic human voices. One such development is the incorporation of multiple linguistic styles in various languages and accents. HMM-based Speech Synthesis is of great interest to many researchers, due to its ability to produce sophisticated features with small footprint. Despite such progress, its quality has not yet reached the level of the predominant unit-selection approaches that choose and concatenate recordings of real speech. Recent efforts have been made in the direction of improving these systems. In this paper we present the application of Long-Short Term Memory Deep Neural Networks as a Postfiltering step of HMM-based speech synthesis, in order to obtain closer spectral characteristics to those of natural speech. The results show how HMM-voices could be improved using this approach.
Tasks	Speech Synthesis
Published	2016-02-08
URL	http://arxiv.org/abs/1602.02656v1
PDF	http://arxiv.org/pdf/1602.02656v1.pdf
PWC	https://paperswithcode.com/paper/lstm-deep-neural-networks-postfiltering-for
Repo
Framework

Text comparison using word vector representations and dimensionality reduction


Title	Text comparison using word vector representations and dimensionality reduction
Authors	Hendrik Heuer
Abstract	This paper describes a technique to compare large text sources using word vector representations (word2vec) and dimensionality reduction (t-SNE) and how it can be implemented using Python. The technique provides a bird’s-eye view of text sources, e.g. text summaries and their source material, and enables users to explore text sources like a geographical map. Word vector representations capture many linguistic properties such as gender, tense, plurality and even semantic concepts like “capital city of”. Using dimensionality reduction, a 2D map can be computed where semantically similar words are close to each other. The technique uses the word2vec model from the gensim Python library and t-SNE from scikit-learn.
Tasks	Dimensionality Reduction
Published	2016-07-02
URL	http://arxiv.org/abs/1607.00534v1
PDF	http://arxiv.org/pdf/1607.00534v1.pdf
PWC	https://paperswithcode.com/paper/text-comparison-using-word-vector
Repo
Framework

Recurrent Neural Network Postfilters for Statistical Parametric Speech Synthesis


Title	Recurrent Neural Network Postfilters for Statistical Parametric Speech Synthesis
Authors	Prasanna Kumar Muthukumar, Alan W Black
Abstract	In the last two years, there have been numerous papers that have looked into using Deep Neural Networks to replace the acoustic model in traditional statistical parametric speech synthesis. However, far less attention has been paid to approaches like DNN-based postfiltering where DNNs work in conjunction with traditional acoustic models. In this paper, we investigate the use of Recurrent Neural Networks as a potential postfilter for synthesis. We explore the possibility of replacing existing postfilters, as well as highlight the ease with which arbitrary new features can be added as input to the postfilter. We also tried a novel approach of jointly training the Classification And Regression Tree and the postfilter, rather than the traditional approach of training them independently.
Tasks	Speech Synthesis
Published	2016-01-26
URL	http://arxiv.org/abs/1601.07215v1
PDF	http://arxiv.org/pdf/1601.07215v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-neural-network-postfilters-for
Repo
Framework

Advancing Memristive Analog Neuromorphic Networks: Increasing Complexity, and Coping with Imperfect Hardware Components


Title	Advancing Memristive Analog Neuromorphic Networks: Increasing Complexity, and Coping with Imperfect Hardware Components
Authors	F. Merrikh Bayat, M. Prezioso, B. Chakrabarti, I. Kataeva, D. B. Strukov
Abstract	We experimentally demonstrate classification of 4x4 binary images into 4 classes, using a 3-layer mixed-signal neuromorphic network (“MLP perceptron”), based on two passive 20x20 memristive crossbar arrays, board-integrated with discrete CMOS components. The network features 10 hidden-layer and 4 output-layer analog CMOS neurons and 428 metal-oxide memristors, i.e. is almost an order of magnitude more complex than any previously reported functional memristor circuit. Moreover, the inference operation of this classifier is performed entirely in the integrated hardware. To deal with larger crossbar arrays, we have developed a semi-automatic approach to their forming and testing, and compared several memristor training schemes for coping with imperfect behavior of these devices, as well as with variability of analog CMOS neurons. The effectiveness of the proposed schemes for defect and variation tolerance was verified experimentally using the implemented network and, additionally, by modeling the operation of a larger network, with 300 hidden-layer neurons, on the MNIST benchmark. Finally, we propose a simple modification of the implemented memristor-based vector-by-matrix multiplier to allow its operation in a wider temperature range.
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.04465v1
PDF	http://arxiv.org/pdf/1611.04465v1.pdf
PWC	https://paperswithcode.com/paper/advancing-memristive-analog-neuromorphic
Repo
Framework