July 28, 2019

3197 words 16 mins read

Paper Group ANR 415

Generalization Properties of Doubly Stochastic Learning Algorithms. SceneSeer: 3D Scene Design with Natural Language. Deep Architectures for Automated Seizure Detection in Scalp EEGs. Minkowski Operations of Sets with Application to Robot Localization. An Artificial Neural Network-based Stock Trading System Using Technical Analysis and Big Data Fra …

Generalization Properties of Doubly Stochastic Learning Algorithms


Title	Generalization Properties of Doubly Stochastic Learning Algorithms
Authors	Junhong Lin, Lorenzo Rosasco
Abstract	Doubly stochastic learning algorithms are scalable kernel methods that perform very well in practice. However, their generalization properties are not well understood and their analysis is challenging since the corresponding learning sequence may not be in the hypothesis space induced by the kernel. In this paper, we provide an in-depth theoretical analysis for different variants of doubly stochastic learning algorithms within the setting of nonparametric regression in a reproducing kernel Hilbert space and considering the square loss. Particularly, we derive convergence results on the generalization error for the studied algorithms either with or without an explicit penalty term. To the best of our knowledge, the derived results for the unregularized variants are the first of this kind, while the results for the regularized variants improve those in the literature. The novelties in our proof are a sample error bound that requires controlling the trace norm of a cumulative operator, and a refined analysis of bounding initial error.
Tasks
Published	2017-07-03
URL	http://arxiv.org/abs/1707.00577v2
PDF	http://arxiv.org/pdf/1707.00577v2.pdf
PWC	https://paperswithcode.com/paper/generalization-properties-of-doubly
Repo
Framework

SceneSeer: 3D Scene Design with Natural Language


Title	SceneSeer: 3D Scene Design with Natural Language
Authors	Angel X. Chang, Mihail Eric, Manolis Savva, Christopher D. Manning
Abstract	Designing 3D scenes is currently a creative task that requires significant expertise and effort in using complex 3D design interfaces. This effortful design process starts in stark contrast to the easiness with which people can use language to describe real and imaginary environments. We present SceneSeer: an interactive text to 3D scene generation system that allows a user to design 3D scenes using natural language. A user provides input text from which we extract explicit constraints on the objects that should appear in the scene. Given these explicit constraints, the system then uses a spatial knowledge base learned from an existing database of 3D scenes and 3D object models to infer an arrangement of the objects forming a natural scene matching the input description. Using textual commands the user can then iteratively refine the created scene by adding, removing, replacing, and manipulating objects. We evaluate the quality of 3D scenes generated by SceneSeer in a perceptual evaluation experiment where we compare against manually designed scenes and simpler baselines for 3D scene generation. We demonstrate how the generated scenes can be iteratively refined through simple natural language commands.
Tasks	Scene Generation
Published	2017-02-28
URL	http://arxiv.org/abs/1703.00050v1
PDF	http://arxiv.org/pdf/1703.00050v1.pdf
PWC	https://paperswithcode.com/paper/sceneseer-3d-scene-design-with-natural
Repo
Framework

Deep Architectures for Automated Seizure Detection in Scalp EEGs


Title	Deep Architectures for Automated Seizure Detection in Scalp EEGs
Authors	Meysam Golmohammadi, Saeedeh Ziyabari, Vinit Shah, Silvia Lopez de Diego, Iyad Obeid, Joseph Picone
Abstract	Automated seizure detection using clinical electroencephalograms is a challenging machine learning problem because the multichannel signal often has an extremely low signal to noise ratio. Events of interest such as seizures are easily confused with signal artifacts (e.g, eye movements) or benign variants (e.g., slowing). Commercially available systems suffer from unacceptably high false alarm rates. Deep learning algorithms that employ high dimensional models have not previously been effective due to the lack of big data resources. In this paper, we use the TUH EEG Seizure Corpus to evaluate a variety of hybrid deep structures including Convolutional Neural Networks and Long Short-Term Memory Networks. We introduce a novel recurrent convolutional architecture that delivers 30% sensitivity at 7 false alarms per 24 hours. We have also evaluated our system on a held-out evaluation set based on the Duke University Seizure Corpus and demonstrate that performance trends are similar to the TUH EEG Seizure Corpus. This is a significant finding because the Duke corpus was collected with different instrumentation and at different hospitals. Our work shows that deep learning architectures that integrate spatial and temporal contexts are critical to achieving state of the art performance and will enable a new generation of clinically-acceptable technology.
Tasks	EEG, Seizure Detection
Published	2017-12-28
URL	http://arxiv.org/abs/1712.09776v1
PDF	http://arxiv.org/pdf/1712.09776v1.pdf
PWC	https://paperswithcode.com/paper/deep-architectures-for-automated-seizure
Repo
Framework

Minkowski Operations of Sets with Application to Robot Localization


Title	Minkowski Operations of Sets with Application to Robot Localization
Authors	Benoit Desrochers, Luc Jaulin
Abstract	This papers shows that using separators, which is a pair of two complementary contractors, we can easily and efficiently solve the localization problem of a robot with sonar measurements in an unstructured environment. We introduce separators associated with the Minkowski sum and the Minkowski difference in order to facilitate the resolution. A test-case is given in order to illustrate the principle of the approach.
Tasks
Published	2017-04-11
URL	http://arxiv.org/abs/1704.03103v1
PDF	http://arxiv.org/pdf/1704.03103v1.pdf
PWC	https://paperswithcode.com/paper/minkowski-operations-of-sets-with-application
Repo
Framework

An Artificial Neural Network-based Stock Trading System Using Technical Analysis and Big Data Framework


Title	An Artificial Neural Network-based Stock Trading System Using Technical Analysis and Big Data Framework
Authors	O. B. Sezer, M. Ozbayoglu, E. Dogdu
Abstract	In this paper, a neural network-based stock price prediction and trading system using technical analysis indicators is presented. The model developed first converts the financial time series data into a series of buy-sell-hold trigger signals using the most commonly preferred technical analysis indicators. Then, a Multilayer Perceptron (MLP) artificial neural network (ANN) model is trained in the learning stage on the daily stock prices between 1997 and 2007 for all of the Dow30 stocks. Apache Spark big data framework is used in the training stage. The trained model is then tested with data from 2007 to 2017. The results indicate that by choosing the most appropriate technical indicators, the neural network model can achieve comparable results against the Buy and Hold strategy in most of the cases. Furthermore, fine tuning the technical indicators and/or optimization strategy can enhance the overall trading performance.
Tasks	Stock Price Prediction, Time Series
Published	2017-12-27
URL	http://arxiv.org/abs/1712.09592v1
PDF	http://arxiv.org/pdf/1712.09592v1.pdf
PWC	https://paperswithcode.com/paper/an-artificial-neural-network-based-stock
Repo
Framework

A Visual Measure of Changes to Weighted Self-Organizing Map Patterns


Title	A Visual Measure of Changes to Weighted Self-Organizing Map Patterns
Authors	Younjin Chung, Joachim Gudmundsson, Masahiro Takatsuka
Abstract	Estimating output changes by input changes is the main task in causal analysis. In previous work, input and output Self-Organizing Maps (SOMs) were associated for causal analysis of multivariate and nonlinear data. Based on the association, a weight distribution of the output conditional on a given input was obtained over the output map space. Such a weighted SOM pattern of the output changes when the input changes. In order to analyze the change, it is important to measure the difference of the patterns. Many methods have been proposed for the dissimilarity measure of patterns. However, it remains a major challenge when attempting to measure how the patterns change. In this paper, we propose a visualization approach that simplifies the comparison of the difference in terms of the pattern property. Using this approach, the change can be analyzed by integrating colors and star glyph shapes representing the property dissimilarity. Ecological data is used to demonstrate the usefulness of our approach and the experimental results show that our approach provides the change information effectively.
Tasks
Published	2017-03-27
URL	http://arxiv.org/abs/1703.08917v1
PDF	http://arxiv.org/pdf/1703.08917v1.pdf
PWC	https://paperswithcode.com/paper/a-visual-measure-of-changes-to-weighted-self
Repo
Framework

An aggregating strategy for shifting experts in discrete sequence prediction


Title	An aggregating strategy for shifting experts in discrete sequence prediction
Authors	Vishnu Raj, Sheetal Kalyani
Abstract	We study how we can adapt a predictor to a non-stationary environment with advises from multiple experts. We study the problem under complete feedback when the best expert changes over time from a decision theoretic point of view. Proposed algorithm is based on popular exponential weighing method with exponential discounting. We provide theoretical results bounding regret under the exponential discounting setting. Upper bound on regret is derived for finite time horizon problem. Numerical verification of different real life datasets are provided to show the utility of proposed algorithm.
Tasks
Published	2017-08-05
URL	http://arxiv.org/abs/1708.01744v1
PDF	http://arxiv.org/pdf/1708.01744v1.pdf
PWC	https://paperswithcode.com/paper/an-aggregating-strategy-for-shifting-experts
Repo
Framework

Unsupervised Domain Adaptation with Copula Models


Title	Unsupervised Domain Adaptation with Copula Models
Authors	Cuong D. Tran, Ognjen Rudovic, Vladimir Pavlovic
Abstract	We study the task of unsupervised domain adaptation, where no labeled data from the target domain is provided during training time. To deal with the potential discrepancy between the source and target distributions, both in features and labels, we exploit a copula-based regression framework. The benefits of this approach are two-fold: (a) it allows us to model a broader range of conditional predictive densities beyond the common exponential family, (b) we show how to leverage Sklar’s theorem, the essence of the copula formulation relating the joint density to the copula dependency functions, to find effective feature mappings that mitigate the domain mismatch. By transforming the data to a copula domain, we show on a number of benchmark datasets (including human emotion estimation), and using different regression models for prediction, that we can achieve a more robust and accurate estimation of target labels, compared to recently proposed feature transformation (adaptation) methods.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2017-09-29
URL	http://arxiv.org/abs/1710.00018v1
PDF	http://arxiv.org/pdf/1710.00018v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-domain-adaptation-with-copula
Repo
Framework

PoseTrack: A Benchmark for Human Pose Estimation and Tracking


Title	PoseTrack: A Benchmark for Human Pose Estimation and Tracking
Authors	Mykhaylo Andriluka, Umar Iqbal, Eldar Insafutdinov, Leonid Pishchulin, Anton Milan, Juergen Gall, Bernt Schiele
Abstract	Human poses and motions are important cues for analysis of videos with people and there is strong evidence that representations based on body pose are highly effective for a variety of tasks such as activity recognition, content retrieval and social signal processing. In this work, we aim to further advance the state of the art by establishing “PoseTrack”, a new large-scale benchmark for video-based human pose estimation and articulated tracking, and bringing together the community of researchers working on visual human analysis. The benchmark encompasses three competition tracks focusing on i) single-frame multi-person pose estimation, ii) multi-person pose estimation in videos, and iii) multi-person articulated tracking. To facilitate the benchmark and challenge we collect, annotate and release a new %large-scale benchmark dataset that features videos with multiple people labeled with person tracks and articulated pose. A centralized evaluation server is provided to allow participants to evaluate on a held-out test set. We envision that the proposed benchmark will stimulate productive research both by providing a large and representative training dataset as well as providing a platform to objectively evaluate and compare the proposed methods. The benchmark is freely accessible at https://posetrack.net.
Tasks	Activity Recognition, Multi-Person Pose Estimation, Pose Estimation
Published	2017-10-27
URL	http://arxiv.org/abs/1710.10000v2
PDF	http://arxiv.org/pdf/1710.10000v2.pdf
PWC	https://paperswithcode.com/paper/posetrack-a-benchmark-for-human-pose
Repo
Framework

On Automating the Doctrine of Double Effect


Title	On Automating the Doctrine of Double Effect
Authors	Naveen Sundar Govindarajulu, Selmer Bringsjord
Abstract	The doctrine of double effect ($\mathcal{DDE}$) is a long-studied ethical principle that governs when actions that have both positive and negative effects are to be allowed. The goal in this paper is to automate $\mathcal{DDE}$. We briefly present $\mathcal{DDE}$, and use a first-order modal logic, the deontic cognitive event calculus, as our framework to formalize the doctrine. We present formalizations of increasingly stronger versions of the principle, including what is known as the doctrine of triple effect. We then use our framework to simulate successfully scenarios that have been used to test for the presence of the principle in human subjects. Our framework can be used in two different modes: One can use it to build $\mathcal{DDE}$-compliant autonomous systems from scratch, or one can use it to verify that a given AI system is $\mathcal{DDE}$-compliant, by applying a $\mathcal{DDE}$ layer on an existing system or model. For the latter mode, the underlying AI system can be built using any architecture (planners, deep neural networks, bayesian networks, knowledge-representation systems, or a hybrid); as long as the system exposes a few parameters in its model, such verification is possible. The role of the $\mathcal{DDE}$ layer here is akin to a (dynamic or static) software verifier that examines existing software modules. Finally, we end by presenting initial work on how one can apply our $\mathcal{DDE}$ layer to the STRIPS-style planning model, and to a modified POMDP model.This is preliminary work to illustrate the feasibility of the second mode, and we hope that our initial sketches can be useful for other researchers in incorporating DDE in their own frameworks.
Tasks
Published	2017-03-27
URL	http://arxiv.org/abs/1703.08922v5
PDF	http://arxiv.org/pdf/1703.08922v5.pdf
PWC	https://paperswithcode.com/paper/on-automating-the-doctrine-of-double-effect
Repo
Framework

Frequency Based Index Estimating the Subclusters’ Connection Strength


Title	Frequency Based Index Estimating the Subclusters’ Connection Strength
Authors	Lukas Pastorek
Abstract	In this paper, a frequency coefficient based on the Sen-Shorrocks-Thon (SST) poverty index notion is proposed. The clustering SST index can be used as the method for determination of the connection between similar neighbor sub-clusters. Consequently, connections can reveal existence of natural homogeneous. Through estimation of the connection strength, we can also verify information about the estimated number of natural clusters that is necessary assumption of efficient market segmentation and campaign management and financial decisions. The index can be used as the complementary tool for the U-matrix visualization. The index is tested on an artificial dataset with known parameters and compared with results obtained by the Unified-distance matrix method.
Tasks
Published	2017-10-19
URL	http://arxiv.org/abs/1710.07340v2
PDF	http://arxiv.org/pdf/1710.07340v2.pdf
PWC	https://paperswithcode.com/paper/frequency-based-index-estimating-the
Repo
Framework

RNN Decoding of Linear Block Codes


Title	RNN Decoding of Linear Block Codes
Authors	Eliya Nachmani, Elad Marciano, David Burshtein, Yair Be’ery
Abstract	Designing a practical, low complexity, close to optimal, channel decoder for powerful algebraic codes with short to moderate block length is an open research problem. Recently it has been shown that a feed-forward neural network architecture can improve on standard belief propagation decoding, despite the large example space. In this paper we introduce a recurrent neural network architecture for decoding linear block codes. Our method shows comparable bit error rate results compared to the feed-forward neural network with significantly less parameters. We also demonstrate improved performance over belief propagation on sparser Tanner graph representations of the codes. Furthermore, we demonstrate that the RNN decoder can be used to improve the performance or alternatively reduce the computational complexity of the mRRD algorithm for low complexity, close to optimal, decoding of short BCH codes.
Tasks
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07560v1
PDF	http://arxiv.org/pdf/1702.07560v1.pdf
PWC	https://paperswithcode.com/paper/rnn-decoding-of-linear-block-codes
Repo
Framework

Deep Semantics-Aware Photo Adjustment


Title	Deep Semantics-Aware Photo Adjustment
Authors	Seonghyeon Nam, Seon Joo Kim
Abstract	Automatic photo adjustment is to mimic the photo retouching style of professional photographers and automatically adjust photos to the learned style. There have been many attempts to model the tone and the color adjustment globally with low-level color statistics. Also, spatially varying photo adjustment methods have been studied by exploiting high-level features and semantic label maps. Those methods are semantics-aware since the color mapping is dependent on the high-level semantic context. However, their performance is limited to the pre-computed hand-crafted features and it is hard to reflect user’s preference to the adjustment. In this paper, we propose a deep neural network that models the semantics-aware photo adjustment. The proposed network exploits bilinear models that are the multiplicative interaction of the color and the contexual features. As the contextual features we propose the semantic adjustment map, which discovers the inherent photo retouching presets that are applied according to the scene context. The proposed method is trained using a robust loss with a scene parsing task. The experimental results show that the proposed method outperforms the existing method both quantitatively and qualitatively. The proposed method also provides users a way to retouch the photo by their own likings by giving customized adjustment maps.
Tasks	Scene Parsing
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08260v1
PDF	http://arxiv.org/pdf/1706.08260v1.pdf
PWC	https://paperswithcode.com/paper/deep-semantics-aware-photo-adjustment
Repo
Framework

Automatic Vertebra Labeling in Large-Scale 3D CT using Deep Image-to-Image Network with Message Passing and Sparsity Regularization


Title	Automatic Vertebra Labeling in Large-Scale 3D CT using Deep Image-to-Image Network with Message Passing and Sparsity Regularization
Authors	Dong Yang, Tao Xiong, Daguang Xu, Qiangui Huang, David Liu, S. Kevin Zhou, Zhoubing Xu, JinHyeong Park, Mingqing Chen, Trac D. Tran, Sang Peter Chin, Dimitris Metaxas, Dorin Comaniciu
Abstract	Automatic localization and labeling of vertebra in 3D medical images plays an important role in many clinical tasks, including pathological diagnosis, surgical planning and postoperative assessment. However, the unusual conditions of pathological cases, such as the abnormal spine curvature, bright visual imaging artifacts caused by metal implants, and the limited field of view, increase the difficulties of accurate localization. In this paper, we propose an automatic and fast algorithm to localize and label the vertebra centroids in 3D CT volumes. First, we deploy a deep image-to-image network (DI2IN) to initialize vertebra locations, employing the convolutional encoder-decoder architecture together with multi-level feature concatenation and deep supervision. Next, the centroid probability maps from DI2IN are iteratively evolved with the message passing schemes based on the mutual relation of vertebra centroids. Finally, the localization results are refined with sparsity regularization. The proposed method is evaluated on a public dataset of 302 spine CT volumes with various pathologies. Our method outperforms other state-of-the-art methods in terms of localization accuracy. The run time is around 3 seconds on average per case. To further boost the performance, we retrain the DI2IN on additional 1000+ 3D CT volumes from different patients. To the best of our knowledge, this is the first time more than 1000 3D CT volumes with expert annotation are adopted in experiments for the anatomic landmark detection tasks. Our experimental results show that training with such a large dataset significantly improves the performance and the overall identification rate, for the first time by our knowledge, reaches 90 %.
Tasks
Published	2017-05-17
URL	http://arxiv.org/abs/1705.05998v1
PDF	http://arxiv.org/pdf/1705.05998v1.pdf
PWC	https://paperswithcode.com/paper/automatic-vertebra-labeling-in-large-scale-3d
Repo
Framework

An inner-loop free solution to inverse problems using deep neural networks


Title	An inner-loop free solution to inverse problems using deep neural networks
Authors	Qi Wei, Kai Fan, Lawrence Carin, Katherine A. Heller
Abstract	We propose a new method that uses deep learning techniques to accelerate the popular alternating direction method of multipliers (ADMM) solution for inverse problems. The ADMM updates consist of a proximity operator, a least squares regression that includes a big matrix inversion, and an explicit solution for updating the dual variables. Typically, inner loops are required to solve the first two sub-minimization problems due to the intractability of the prior and the matrix inversion. To avoid such drawbacks or limitations, we propose an inner-loop free update rule with two pre-trained deep convolutional architectures. More specifically, we learn a conditional denoising auto-encoder which imposes an implicit data-dependent prior/regularization on ground-truth in the first sub-minimization problem. This design follows an empirical Bayesian strategy, leading to so-called amortized inference. For matrix inversion in the second sub-problem, we learn a convolutional neural network to approximate the matrix inversion, i.e., the inverse mapping is learned by feeding the input through the learned forward network. Note that training this neural network does not require ground-truth or measurements, i.e., it is data-independent. Extensive experiments on both synthetic data and real datasets demonstrate the efficiency and accuracy of the proposed method compared with the conventional ADMM solution using inner loops for solving inverse problems.
Tasks	Denoising
Published	2017-09-06
URL	http://arxiv.org/abs/1709.01841v3
PDF	http://arxiv.org/pdf/1709.01841v3.pdf
PWC	https://paperswithcode.com/paper/an-inner-loop-free-solution-to-inverse
Repo
Framework