May 5, 2019

3267 words 16 mins read

Paper Group ANR 448

A Mathematical Framework for Feature Selection from Real-World Data with Non-Linear Observations. Measuring Asymmetric Opinions on Online Social Interrelationship with Language and Network Features. Applying Artifical Neural Networks To Predict Nominal Vehicle Performance. Unsupervised Regenerative Learning of Hierarchical Features in Spiking Deep …

A Mathematical Framework for Feature Selection from Real-World Data with Non-Linear Observations


Title	A Mathematical Framework for Feature Selection from Real-World Data with Non-Linear Observations
Authors	Martin Genzel, Gitta Kutyniok
Abstract	In this paper, we study the challenge of feature selection based on a relatively small collection of sample pairs ${(x_i, y_i)}{1 \leq i \leq m}$. The observations $y_i \in \mathbb{R}$ are thereby supposed to follow a noisy single-index model, depending on a certain set of signal variables. A major difficulty is that these variables usually cannot be observed directly, but rather arise as hidden factors in the actual data vectors $x_i \in \mathbb{R}^d$ (feature variables). We will prove that a successful variable selection is still possible in this setup, even when the applied estimator does not have any knowledge of the underlying model parameters and only takes the ‘raw’ samples ${(x_i, y_i)}{1 \leq i \leq m}$ as input. The model assumptions of our results will be fairly general, allowing for non-linear observations, arbitrary convex signal structures as well as strictly convex loss functions. This is particularly appealing for practical purposes, since in many applications, already standard methods, e.g., the Lasso or logistic regression, yield surprisingly good outcomes. Apart from a general discussion of the practical scope of our theoretical findings, we will also derive a rigorous guarantee for a specific real-world problem, namely sparse feature extraction from (proteomics-based) mass spectrometry data.
Tasks	Feature Selection
Published	2016-08-31
URL	http://arxiv.org/abs/1608.08852v1
PDF	http://arxiv.org/pdf/1608.08852v1.pdf
PWC	https://paperswithcode.com/paper/a-mathematical-framework-for-feature
Repo
Framework


Title	Measuring Asymmetric Opinions on Online Social Interrelationship with Language and Network Features
Authors	Bo Wang, Yanshu Yu, Yuan Wang
Abstract	Instead of studying the properties of social relationship from an objective view, in this paper, we focus on individuals’ subjective and asymmetric opinions on their interrelationships. Inspired by the theories from sociolinguistics, we investigate two individuals’ opinions on their interrelationship with their interactive language features. Eliminating the difference of personal language style, we clarify that the asymmetry of interactive language feature values can indicate individuals’ asymmetric opinions on their interrelationship. We also discuss how the degree of opinions’ asymmetry is related to the individuals’ personality traits. Furthermore, to measure the individuals’ asymmetric opinions on interrelationship concretely, we develop a novel model synthetizing interactive language and social network features. The experimental results with Enron email dataset provide multiple evidences of the asymmetric opinions on interrelationship, and also verify the effectiveness of the proposed model in measuring the degree of opinions’ asymmetry.
Tasks
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00456v2
PDF	http://arxiv.org/pdf/1611.00456v2.pdf
PWC	https://paperswithcode.com/paper/measuring-asymmetric-opinions-on-online
Repo
Framework

Applying Artifical Neural Networks To Predict Nominal Vehicle Performance


Title	Applying Artifical Neural Networks To Predict Nominal Vehicle Performance
Authors	Adam J. Last
Abstract	This paper investigates the use of artificial neural networks (ANNs) to replace traditional algorithms and manual review for identifying anomalies in vehicle run data. The specific data used for this study is from undersea vehicle qualification tests. Such data is highly non-linear, therefore traditional algorithms are not adequate and manual review is time consuming. By using ANNs to predict nominal vehicle performance based solely on information available pre-run, vehicle deviation from expected performance can be automatically identified in the post-run data. Such capability is only now becoming available due to the rapid increase in understanding of ANN framework and available computing power in the past decade. The ANN trained for the purpose of this investigation is relatively simple, to keep the computing requirements within the parameters of a modern desktop PC. This ANN showed potential in predicting vehicle performance, particularly during transient events within the run data. However, there were also several performance cases, such as steady state operation and cases which did not have sufficient training data, where the ANN showed deficiencies. It is expected that as computational power becomes more readily available, ANN understanding matures, and more training data is acquired from real world tests, the performance predictions of the ANN will surpass traditional algorithms and manual human review.
Tasks
Published	2016-03-16
URL	http://arxiv.org/abs/1603.05189v1
PDF	http://arxiv.org/pdf/1603.05189v1.pdf
PWC	https://paperswithcode.com/paper/applying-artifical-neural-networks-to-predict
Repo
Framework

Unsupervised Regenerative Learning of Hierarchical Features in Spiking Deep Networks for Object Recognition


Title	Unsupervised Regenerative Learning of Hierarchical Features in Spiking Deep Networks for Object Recognition
Authors	Priyadarshini Panda, Kaushik Roy
Abstract	We present a spike-based unsupervised regenerative learning scheme to train Spiking Deep Networks (SpikeCNN) for object recognition problems using biologically realistic leaky integrate-and-fire neurons. The training methodology is based on the Auto-Encoder learning model wherein the hierarchical network is trained layer wise using the encoder-decoder principle. Regenerative learning uses spike-timing information and inherent latencies to update the weights and learn representative levels for each convolutional layer in an unsupervised manner. The features learnt from the final layer in the hierarchy are then fed to an output layer. The output layer is trained with supervision by showing a fraction of the labeled training dataset and performs the overall classification of the input. Our proposed methodology yields 0.92%/29.84% classification error on MNIST/CIFAR10 datasets which is comparable with state-of-the-art results. The proposed methodology also introduces sparsity in the hierarchical feature representations on account of event-based coding resulting in computationally efficient learning.
Tasks	Object Recognition
Published	2016-02-03
URL	http://arxiv.org/abs/1602.01510v1
PDF	http://arxiv.org/pdf/1602.01510v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-regenerative-learning-of
Repo
Framework

Robust 3D Hand Pose Estimation in Single Depth Images: from Single-View CNN to Multi-View CNNs


Title	Robust 3D Hand Pose Estimation in Single Depth Images: from Single-View CNN to Multi-View CNNs
Authors	Liuhao Ge, Hui Liang, Junsong Yuan, Daniel Thalmann
Abstract	Articulated hand pose estimation plays an important role in human-computer interaction. Despite the recent progress, the accuracy of existing methods is still not satisfactory, partially due to the difficulty of embedded high-dimensional and non-linear regression problem. Different from the existing discriminative methods that regress for the hand pose with a single depth image, we propose to first project the query depth image onto three orthogonal planes and utilize these multi-view projections to regress for 2D heat-maps which estimate the joint positions on each plane. These multi-view heat-maps are then fused to produce final 3D hand pose estimation with learned pose priors. Experiments show that the proposed method largely outperforms state-of-the-art on a challenging dataset. Moreover, a cross-dataset experiment also demonstrates the good generalization ability of the proposed method.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2016-06-23
URL	http://arxiv.org/abs/1606.07253v3
PDF	http://arxiv.org/pdf/1606.07253v3.pdf
PWC	https://paperswithcode.com/paper/robust-3d-hand-pose-estimation-in-single
Repo
Framework

Comparing Time and Frequency Domain for Audio Event Recognition Using Deep Learning


Title	Comparing Time and Frequency Domain for Audio Event Recognition Using Deep Learning
Authors	Lars Hertel, Huy Phan, Alfred Mertins
Abstract	Recognizing acoustic events is an intricate problem for a machine and an emerging field of research. Deep neural networks achieve convincing results and are currently the state-of-the-art approach for many tasks. One advantage is their implicit feature learning, opposite to an explicit feature extraction of the input signal. In this work, we analyzed whether more discriminative features can be learned from either the time-domain or the frequency-domain representation of the audio signal. For this purpose, we trained multiple deep networks with different architectures on the Freiburg-106 and ESC-10 datasets. Our results show that feature learning from the frequency domain is superior to the time domain. Moreover, additionally using convolution and pooling layers, to explore local structures of the audio signal, significantly improves the recognition performance and achieves state-of-the-art results.
Tasks
Published	2016-03-18
URL	http://arxiv.org/abs/1603.05824v1
PDF	http://arxiv.org/pdf/1603.05824v1.pdf
PWC	https://paperswithcode.com/paper/comparing-time-and-frequency-domain-for-audio
Repo
Framework

Distributed Supervised Learning using Neural Networks


Title	Distributed Supervised Learning using Neural Networks
Authors	Simone Scardapane
Abstract	Distributed learning is the problem of inferring a function in the case where training data is distributed among multiple geographically separated sources. Particularly, the focus is on designing learning strategies with low computational requirements, in which communication is restricted only to neighboring agents, with no reliance on a centralized authority. In this thesis, we analyze multiple distributed protocols for a large number of neural network architectures. The first part of the thesis is devoted to a definition of the problem, followed by an extensive overview of the state-of-the-art. Next, we introduce different strategies for a relatively simple class of single layer neural networks, where a linear output layer is preceded by a nonlinear layer, whose weights are stochastically assigned in the beginning of the learning process. We consider both batch and sequential learning, with horizontally and vertically partitioned data. In the third part, we consider instead the more complex problem of semi-supervised distributed learning, where each agent is provided with an additional set of unlabeled training samples. We propose two different algorithms based on diffusion processes for linear support vector machines and kernel ridge regression. Subsequently, the fourth part extends the discussion to learning with time-varying data (e.g. time-series) using recurrent neural networks. We consider two different families of networks, namely echo state networks (extending the algorithms introduced in the second part), and spline adaptive filters. Overall, the algorithms presented throughout the thesis cover a wide range of possible practical applications, and lead the way to numerous future extensions, which are briefly summarized in the conclusive chapter.
Tasks	Time Series
Published	2016-07-21
URL	http://arxiv.org/abs/1607.06364v1
PDF	http://arxiv.org/pdf/1607.06364v1.pdf
PWC	https://paperswithcode.com/paper/distributed-supervised-learning-using-neural
Repo
Framework

End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks


Title	End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks
Authors	Peter Ondruska, Julie Dequaire, Dominic Zeng Wang, Ingmar Posner
Abstract	In this work we present a novel end-to-end framework for tracking and classifying a robot’s surroundings in complex, dynamic and only partially observable real-world environments. The approach deploys a recurrent neural network to filter an input stream of raw laser measurements in order to directly infer object locations, along with their identity in both visible and occluded areas. To achieve this we first train the network using unsupervised Deep Tracking, a recently proposed theoretical framework for end-to-end space occupancy prediction. We show that by learning to track on a large amount of unsupervised data, the network creates a rich internal representation of its environment which we in turn exploit through the principle of inductive transfer of knowledge to perform the task of it’s semantic classification. As a result, we show that only a small amount of labelled data suffices to steer the network towards mastering this additional task. Furthermore we propose a novel recurrent neural network architecture specifically tailored to tracking and semantic classification in real-world robotics applications. We demonstrate the tracking and classification performance of the method on real-world data collected at a busy road junction. Our evaluation shows that the proposed end-to-end framework compares favourably to a state-of-the-art, model-free tracking solution and that it outperforms a conventional one-shot training scheme for semantic classification.
Tasks	Semantic Segmentation
Published	2016-04-18
URL	http://arxiv.org/abs/1604.05091v2
PDF	http://arxiv.org/pdf/1604.05091v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-tracking-and-semantic-segmentation
Repo
Framework

Sentence Ordering and Coherence Modeling using Recurrent Neural Networks


Title	Sentence Ordering and Coherence Modeling using Recurrent Neural Networks
Authors	Lajanugen Logeswaran, Honglak Lee, Dragomir Radev
Abstract	Modeling the structure of coherent texts is a key NLP problem. The task of coherently organizing a given set of sentences has been commonly used to build and evaluate models that understand such structure. We propose an end-to-end unsupervised deep learning approach based on the set-to-sequence framework to address this problem. Our model strongly outperforms prior methods in the order discrimination task and a novel task of ordering abstracts from scientific articles. Furthermore, our work shows that useful text representations can be obtained by learning to order sentences. Visualizing the learned sentence representations shows that the model captures high-level logical structure in paragraphs. Our representations perform comparably to state-of-the-art pre-training methods on sentence similarity and paraphrase detection tasks.
Tasks	Sentence Ordering
Published	2016-11-08
URL	http://arxiv.org/abs/1611.02654v2
PDF	http://arxiv.org/pdf/1611.02654v2.pdf
PWC	https://paperswithcode.com/paper/sentence-ordering-and-coherence-modeling
Repo
Framework

Proceedings of the The First Workshop on Verification and Validation of Cyber-Physical Systems


Title	Proceedings of the The First Workshop on Verification and Validation of Cyber-Physical Systems
Authors	Mehdi Kargahi, Ashutosh Trivedi
Abstract	The first International Workshop on Verification and Validation of Cyber-Physical Systems (V2CPS-16) was held in conjunction with the 12th International Conference on integration of Formal Methods (iFM 2016) in Reykjavik, Iceland. The purpose of V2CPS-16 was to bring together researchers and experts of the fields of formal verification and cyber-physical systems (CPS) to cover the theme of this workshop, namely a wide spectrum of verification and validation methods including (but not limited to) control, simulation, formal methods, etc. A CPS is an integration of networked computational and physical processes with meaningful inter-effects; the former monitors, controls, and affects the latter, while the latter also impacts the former. CPSs have applications in a wide-range of systems spanning robotics, transportation, communication, infrastructure, energy, and manufacturing. Many safety-critical systems such as chemical processes, medical devices, aircraft flight control, and automotive systems, are indeed CPS. The advanced capabilities of CPS require complex software and synthesis algorithms, which are hard to verify. In fact, many problems in this area are undecidable. Thus, a major step is to find particular abstractions of such systems which might be algorithmically verifiable regarding specific properties of such systems, describing the partial/overall behaviors of CPSs.
Tasks
Published	2016-12-13
URL	http://arxiv.org/abs/1612.04023v1
PDF	http://arxiv.org/pdf/1612.04023v1.pdf
PWC	https://paperswithcode.com/paper/proceedings-of-the-the-first-workshop-on
Repo
Framework

Can we unify monocular detectors for autonomous driving by using the pixel-wise semantic segmentation of CNNs?


Title	Can we unify monocular detectors for autonomous driving by using the pixel-wise semantic segmentation of CNNs?
Authors	Eduardo Romera, Luis M. Bergasa, Roberto Arroyo
Abstract	Autonomous driving is a challenging topic that requires complex solutions in perception tasks such as recognition of road, lanes, traffic signs or lights, vehicles and pedestrians. Through years of research, computer vision has grown capable of tackling these tasks with monocular detectors that can provide remarkable detection rates with relatively low processing times. However, the recent appearance of Convolutional Neural Networks (CNNs) has revolutionized the computer vision field and has made possible approaches to perform full pixel-wise semantic segmentation in times close to real time (even on hardware that can be carried on a vehicle). In this paper, we propose to use full image segmentation as an approach to simplify and unify most of the detection tasks required in the perception module of an autonomous vehicle, analyzing major concerns such as computation time and detection performance.
Tasks	Autonomous Driving, Semantic Segmentation
Published	2016-07-04
URL	http://arxiv.org/abs/1607.00971v1
PDF	http://arxiv.org/pdf/1607.00971v1.pdf
PWC	https://paperswithcode.com/paper/can-we-unify-monocular-detectors-for
Repo
Framework

Lazily Adapted Constant Kinky Inference for Nonparametric Regression and Model-Reference Adaptive Control


Title	Lazily Adapted Constant Kinky Inference for Nonparametric Regression and Model-Reference Adaptive Control
Authors	Jan-Peter Calliess
Abstract	Techniques known as Nonlinear Set Membership prediction, Lipschitz Interpolation or Kinky Inference are approaches to machine learning that utilise presupposed Lipschitz properties to compute inferences over unobserved function values. Provided a bound on the true best Lipschitz constant of the target function is known a priori they offer convergence guarantees as well as bounds around the predictions. Considering a more general setting that builds on Hoelder continuity relative to pseudo-metrics, we propose an online method for estimating the Hoelder constant online from function value observations that possibly are corrupted by bounded observational errors. Utilising this to compute adaptive parameters within a kinky inference rule gives rise to a nonparametric machine learning method, for which we establish strong universal approximation guarantees. That is, we show that our prediction rule can learn any continuous function in the limit of increasingly dense data to within a worst-case error bound that depends on the level of observational uncertainty. We apply our method in the context of nonparametric model-reference adaptive control (MRAC). Across a range of simulated aircraft roll-dynamics and performance metrics our approach outperforms recently proposed alternatives that were based on Gaussian processes and RBF-neural networks. For discrete-time systems, we provide guarantees on the tracking success of our learning-based controllers both for the batch and the online learning setting.
Tasks	Gaussian Processes
Published	2016-12-31
URL	http://arxiv.org/abs/1701.00178v2
PDF	http://arxiv.org/pdf/1701.00178v2.pdf
PWC	https://paperswithcode.com/paper/lazily-adapted-constant-kinky-inference-for
Repo
Framework

Matrix Factorization-Based Clustering Of Image Features For Bandwidth-Constrained Information Retrieval


Title	Matrix Factorization-Based Clustering Of Image Features For Bandwidth-Constrained Information Retrieval
Authors	Jacob Chakareski, Immanuel Manohar, Shantanu Rane
Abstract	We consider the problem of accurately and efficiently querying a remote server to retrieve information about images captured by a mobile device. In addition to reduced transmission overhead and computational complexity, the retrieval protocol should be robust to variations in the image acquisition process, such as translation, rotation, scaling, and sensor-related differences. We propose to extract scale-invariant image features and then perform clustering to reduce the number of features needed for image matching. Principal Component Analysis (PCA) and Non-negative Matrix Factorization (NMF) are investigated as candidate clustering approaches. The image matching complexity at the database server is quadratic in the (small) number of clusters, not in the (very large) number of image features. We employ an image-dependent information content metric to approximate the model order, i.e., the number of clusters, needed for accurate matching, which is preferable to setting the model order using trial and error. We show how to combine the hypotheses provided by PCA and NMF factor loadings, thereby obtaining more accurate retrieval than using either approach alone. In experiments on a database of urban images, we obtain a top-1 retrieval accuracy of 89% and a top-3 accuracy of 92.5%.
Tasks	Information Retrieval
Published	2016-05-07
URL	http://arxiv.org/abs/1605.02140v1
PDF	http://arxiv.org/pdf/1605.02140v1.pdf
PWC	https://paperswithcode.com/paper/matrix-factorization-based-clustering-of
Repo
Framework

Analysis of Nonstationary Time Series Using Locally Coupled Gaussian Processes


Title	Analysis of Nonstationary Time Series Using Locally Coupled Gaussian Processes
Authors	Luca Ambrogioni, Eric Maris
Abstract	The analysis of nonstationary time series is of great importance in many scientific fields such as physics and neuroscience. In recent years, Gaussian process regression has attracted substantial attention as a robust and powerful method for analyzing time series. In this paper, we introduce a new framework for analyzing nonstationary time series using locally stationary Gaussian process analysis with parameters that are coupled through a hidden Markov model. The main advantage of this framework is that arbitrary complex nonstationary covariance functions can be obtained by combining simpler stationary building blocks whose hidden parameters can be estimated in closed-form. We demonstrate the flexibility of the method by analyzing two examples of synthetic nonstationary signals: oscillations with time varying frequency and time series with two dynamical states. Finally, we report an example application on real magnetoencephalographic measurements of brain activity.
Tasks	Gaussian Processes, Time Series
Published	2016-10-31
URL	http://arxiv.org/abs/1610.09838v1
PDF	http://arxiv.org/pdf/1610.09838v1.pdf
PWC	https://paperswithcode.com/paper/analysis-of-nonstationary-time-series-using
Repo
Framework

An Effective and Efficient Approach for Clusterability Evaluation


Title	An Effective and Efficient Approach for Clusterability Evaluation
Authors	Margareta Ackerman, Andreas Adolfsson, Naomi Brownstein
Abstract	Clustering is an essential data mining tool that aims to discover inherent cluster structure in data. As such, the study of clusterability, which evaluates whether data possesses such structure, is an integral part of cluster analysis. Yet, despite their central role in the theory and application of clustering, current notions of clusterability fall short in two crucial aspects that render them impractical; most are computationally infeasible and others fail to classify the structure of real datasets. In this paper, we propose a novel approach to clusterability evaluation that is both computationally efficient and successfully captures the structure of real data. Our method applies multimodality tests to the (one-dimensional) set of pairwise distances based on the original, potentially high-dimensional data. We present extensive analyses of our approach for both the Dip and Silverman multimodality tests on real data as well as 17,000 simulations, demonstrating the success of our approach as the first practical notion of clusterability.
Tasks
Published	2016-02-22
URL	http://arxiv.org/abs/1602.06687v1
PDF	http://arxiv.org/pdf/1602.06687v1.pdf
PWC	https://paperswithcode.com/paper/an-effective-and-efficient-approach-for
Repo
Framework