July 28, 2019

2829 words 14 mins read

Paper Group ANR 327

Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use. Rate-Distortion Classification for Self-Tuning IoT Networks. PSIque: Next Sequence Prediction of Satellite Images using a Convolutional Sequence-to-Sequence Network. Exploring Outliers in Crowdsourced Ranking for QoE. K3, L3, LP, RM3, A3, FDE: How to Ma …

Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use


Title	Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use
Authors	Vatsal Sharan, Gregory Valiant
Abstract	The popular Alternating Least Squares (ALS) algorithm for tensor decomposition is efficient and easy to implement, but often converges to poor local optima—particularly when the weights of the factors are non-uniform. We propose a modification of the ALS approach that is as efficient as standard ALS, but provably recovers the true factors with random initialization under standard incoherence assumptions on the factors of the tensor. We demonstrate the significant practical superiority of our approach over traditional ALS for a variety of tasks on synthetic data—including tensor factorization on exact, noisy and over-complete tensors, as well as tensor completion—and for computing word embeddings from a third-order word tri-occurrence tensor.
Tasks	Word Embeddings
Published	2017-03-06
URL	http://arxiv.org/abs/1703.01804v2
PDF	http://arxiv.org/pdf/1703.01804v2.pdf
PWC	https://paperswithcode.com/paper/orthogonalized-als-a-theoretically-principled
Repo
Framework

Rate-Distortion Classification for Self-Tuning IoT Networks


Title	Rate-Distortion Classification for Self-Tuning IoT Networks
Authors	Davide Zordan, Michele Rossi, Michele Zorzi
Abstract	Many future wireless sensor networks and the Internet of Things are expected to follow a software defined paradigm, where protocol parameters and behaviors will be dynamically tuned as a function of the signal statistics. New protocols will be then injected as a software as certain events occur. For instance, new data compressors could be (re)programmed on-the-fly as the monitored signal type or its statistical properties change. We consider a lossy compression scenario, where the application tolerates some distortion of the gathered signal in return for improved energy efficiency. To reap the full benefits of this paradigm, we discuss an automatic sensor profiling approach where the signal class, and in particular the corresponding rate-distortion curve, is automatically assessed using machine learning tools (namely, support vector machines and neural networks). We show that this curve can be reliably estimated on-the-fly through the computation of a small number (from ten to twenty) of statistical features on time windows of a few hundreds samples.
Tasks
Published	2017-06-27
URL	http://arxiv.org/abs/1706.08877v1
PDF	http://arxiv.org/pdf/1706.08877v1.pdf
PWC	https://paperswithcode.com/paper/rate-distortion-classification-for-self
Repo
Framework

PSIque: Next Sequence Prediction of Satellite Images using a Convolutional Sequence-to-Sequence Network


Title	PSIque: Next Sequence Prediction of Satellite Images using a Convolutional Sequence-to-Sequence Network
Authors	Seungkyun Hong, Seongchan Kim, Minsu Joh, Sa-kwang Song
Abstract	Predicting unseen weather phenomena is an important issue for disaster management. In this paper, we suggest a model for a convolutional sequence-to-sequence autoencoder for predicting undiscovered weather situations from previous satellite images. We also propose a symmetric skip connection between encoder and decoder modules to produce more comprehensive image predictions. To examine our model performance, we conducted experiments for each suggested model to predict future satellite images from historical satellite images. A specific combination of skip connection and sequence-to-sequence autoencoder was able to generate closest prediction from the ground truth image.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10644v2
PDF	http://arxiv.org/pdf/1711.10644v2.pdf
PWC	https://paperswithcode.com/paper/psique-next-sequence-prediction-of-satellite
Repo
Framework

Exploring Outliers in Crowdsourced Ranking for QoE


Title	Exploring Outliers in Crowdsourced Ranking for QoE
Authors	Qianqian Xu, Ming Yan, Chendi Huang, Jiechao Xiong, Qingming Huang, Yuan Yao
Abstract	Outlier detection is a crucial part of robust evaluation for crowdsourceable assessment of Quality of Experience (QoE) and has attracted much attention in recent years. In this paper, we propose some simple and fast algorithms for outlier detection and robust QoE evaluation based on the nonconvex optimization principle. Several iterative procedures are designed with or without knowing the number of outliers in samples. Theoretical analysis is given to show that such procedures can reach statistically good estimates under mild conditions. Finally, experimental results with simulated and real-world crowdsourcing datasets show that the proposed algorithms could produce similar performance to Huber-LASSO approach in robust ranking, yet with nearly 8 or 90 times speed-up, without or with a prior knowledge on the sparsity size of outliers, respectively. Therefore the proposed methodology provides us a set of helpful tools for robust QoE evaluation with crowdsourcing data.
Tasks	Outlier Detection
Published	2017-07-18
URL	http://arxiv.org/abs/1707.07539v1
PDF	http://arxiv.org/pdf/1707.07539v1.pdf
PWC	https://paperswithcode.com/paper/exploring-outliers-in-crowdsourced-ranking
Repo
Framework

K3, L3, LP, RM3, A3, FDE: How to Make Many-Valued Logics Work for You


Title	K3, L3, LP, RM3, A3, FDE: How to Make Many-Valued Logics Work for You
Authors	Allen P. Hazen, Francis Jeffry Pelletier
Abstract	We investigate some well-known (and a few not-so-well-known) many-valued logics that have a small number (3 or 4) of truth values. For some of them we complain that they do not have any \emph{logical} use (despite their perhaps having some intuitive semantic interest) and we look at ways to add features so as to make them useful, while retaining their intuitive appeal. At the end, we show some surprising results in the system FDE, and its relationships with features of other logics. We close with some new examples of “synonymous logics.” An Appendix contains a natural deduction system for our augmented FDE, and proofs of soundness and completeness.
Tasks
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05816v1
PDF	http://arxiv.org/pdf/1711.05816v1.pdf
PWC	https://paperswithcode.com/paper/k3-l3-lp-rm3-a3-fde-how-to-make-many-valued
Repo
Framework

Discussion among Different Methods of Updating Model Filter in Object Tracking


Title	Discussion among Different Methods of Updating Model Filter in Object Tracking
Authors	Taihang Dong, Sheng Zhong
Abstract	Discriminative correlation filters (DCF) have recently shown excellent performance in visual object tracking area. In this paper, we summarize the methods of updating model filter from discriminative correlation filter (DCF) based tracking algorithms and analyzes similarities and differences among these methods. We deduce the relationship between updating coefficient in high dimension (kernel trick), updating filter in frequency domain and updating filter in spatial domain, and analyze the difference among these different ways. We also analyze the difference between the updating filter directly and updating filter’s numerator (object response power) with updating filter’s denominator (filter’s power). The experiments about comparing different updating methods and visualizing the template filters are used to prove our derivation.
Tasks	Object Tracking, Visual Object Tracking
Published	2017-11-21
URL	https://arxiv.org/abs/1711.07829v2
PDF	https://arxiv.org/pdf/1711.07829v2.pdf
PWC	https://paperswithcode.com/paper/discussion-among-different-methods-of
Repo
Framework

Rotation Invariance Neural Network


Title	Rotation Invariance Neural Network
Authors	Shiyuan Li
Abstract	Rotation invariance and translation invariance have great values in image recognition tasks. In this paper, we bring a new architecture in convolutional neural network (CNN) named cyclic convolutional layer to achieve rotation invariance in 2-D symbol recognition. We can also get the position and orientation of the 2-D symbol by the network to achieve detection purpose for multiple non-overlap target. Last but not least, this architecture can achieve one-shot learning in some cases using those invariance.
Tasks	One-Shot Learning
Published	2017-06-17
URL	http://arxiv.org/abs/1706.05534v1
PDF	http://arxiv.org/pdf/1706.05534v1.pdf
PWC	https://paperswithcode.com/paper/rotation-invariance-neural-network
Repo
Framework

Comparison of Maximum Likelihood and GAN-based training of Real NVPs


Title	Comparison of Maximum Likelihood and GAN-based training of Real NVPs
Authors	Ivo Danihelka, Balaji Lakshminarayanan, Benigno Uria, Daan Wierstra, Peter Dayan
Abstract	We train a generator by maximum likelihood and we also train the same generator architecture by Wasserstein GAN. We then compare the generated samples, exact log-probability densities and approximate Wasserstein distances. We show that an independent critic trained to approximate Wasserstein distance between the validation set and the generator distribution helps detect overfitting. Finally, we use ideas from the one-shot learning literature to develop a novel fast learning critic.
Tasks	One-Shot Learning
Published	2017-05-15
URL	http://arxiv.org/abs/1705.05263v1
PDF	http://arxiv.org/pdf/1705.05263v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-maximum-likelihood-and-gan
Repo
Framework

Some variations on Ensembled Random Survival Forest with application to Cancer Research


Title	Some variations on Ensembled Random Survival Forest with application to Cancer Research
Authors	Arabin Kumar Dey, Suhas N., Talasila Sai Teja, Anshul Juneja
Abstract	In this paper we describe a novel implementation of adaboost for prediction of survival function. We take different variations of the algorithm and compare the algorithms based on system run time and root mean square error. Our construction includes right censoring data and competing risk data too. We take different data set to illustrate the performance of the algorithms.
Tasks
Published	2017-09-16
URL	http://arxiv.org/abs/1709.05515v2
PDF	http://arxiv.org/pdf/1709.05515v2.pdf
PWC	https://paperswithcode.com/paper/some-variations-on-ensembled-random-survival
Repo
Framework

Smooth Pinball Neural Network for Probabilistic Forecasting of Wind Power


Title	Smooth Pinball Neural Network for Probabilistic Forecasting of Wind Power
Authors	Kostas Hatalis, Alberto J. Lamadrid, Katya Scheinberg, Shalinee Kishore
Abstract	Uncertainty analysis in the form of probabilistic forecasting can significantly improve decision making processes in the smart power grid for better integrating renewable energy sources such as wind. Whereas point forecasting provides a single expected value, probabilistic forecasts provide more information in the form of quantiles, prediction intervals, or full predictive densities. This paper analyzes the effectiveness of a novel approach for nonparametric probabilistic forecasting of wind power that combines a smooth approximation of the pinball loss function with a neural network architecture and a weighting initialization scheme to prevent the quantile cross over problem. A numerical case study is conducted using publicly available wind data from the Global Energy Forecasting Competition 2014. Multiple quantiles are estimated to form 10%, to 90% prediction intervals which are evaluated using a quantile score and reliability measures. Benchmark models such as the persistence and climatology distributions, multiple quantile regression, and support vector quantile regression are used for comparison where results demonstrate the proposed approach leads to improved performance while preventing the problem of overlapping quantile estimates.
Tasks	Decision Making
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01720v1
PDF	http://arxiv.org/pdf/1710.01720v1.pdf
PWC	https://paperswithcode.com/paper/smooth-pinball-neural-network-for
Repo
Framework

An empirical evaluation for the intrusion detection features based on machine learning and feature selection methods


Title	An empirical evaluation for the intrusion detection features based on machine learning and feature selection methods
Authors	Mouhammd Alkasassbeh
Abstract	Despite the great developments in information technology, particularly the Internet, computer networks, global information exchange, and its positive impact in all areas of daily life, it has also contributed to the development of penetration and intrusion which forms a high risk to the security of information organizations, government agencies, and causes large economic losses. There are many techniques designed for protection such as firewall and intrusion detection systems (IDS). IDS is a set of software and/or hardware techniques used to detect hacker’s activities in computer systems. Two types of anomalies are used in IDS to detect intrusive activities different from normal user behavior. Misuse relies on the knowledge base that contains all known attack techniques and intrusion is discovered through research in this knowledge base. Artificial intelligence techniques have been introduced to improve the performance of these systems. The importance of IDS is to identify unauthorized access attempting to compromise confidentiality, integrity or availability of the computer network. This paper investigates the Intrusion Detection (ID) problem using three machine learning algorithms namely, BayesNet algorithm, Multi-Layer Perceptron (MLP), and Support Vector Machine (SVM). The algorithms are applied on a real, Management Information Based (MIB) dataset that is collected from real life environment. To enhance the detection process accuracy, a set of feature selection approaches is used; Infogain (IG), ReleifF (RF), and Genetic Search (GS). Our experiments show that the three feature selection methods have enhanced the classification performance. GS with bayesNet, MLP and SVM give high accuracy rates, more specifically the BayesNet with the GS accuracy rate is 99.9%.
Tasks	Feature Selection, Intrusion Detection
Published	2017-12-27
URL	http://arxiv.org/abs/1712.09623v1
PDF	http://arxiv.org/pdf/1712.09623v1.pdf
PWC	https://paperswithcode.com/paper/an-empirical-evaluation-for-the-intrusion
Repo
Framework

RESPARC: A Reconfigurable and Energy-Efficient Architecture with Memristive Crossbars for Deep Spiking Neural Networks


Title	RESPARC: A Reconfigurable and Energy-Efficient Architecture with Memristive Crossbars for Deep Spiking Neural Networks
Authors	Aayush Ankit, Abhronil Sengupta, Priyadarshini Panda, Kaushik Roy
Abstract	Neuromorphic computing using post-CMOS technologies is gaining immense popularity due to its promising abilities to address the memory and power bottlenecks in von-Neumann computing systems. In this paper, we propose RESPARC - a reconfigurable and energy efficient architecture built-on Memristive Crossbar Arrays (MCA) for deep Spiking Neural Networks (SNNs). Prior works were primarily focused on device and circuit implementations of SNNs on crossbars. RESPARC advances this by proposing a complete system for SNN acceleration and its subsequent analysis. RESPARC utilizes the energy-efficiency of MCAs for inner-product computation and realizes a hierarchical reconfigurable design to incorporate the data-flow patterns in an SNN in a scalable fashion. We evaluate the proposed architecture on different SNNs ranging in complexity from 2k-230k neurons and 1.2M-5.5M synapses. Simulation results on these networks show that compared to the baseline digital CMOS architecture, RESPARC achieves 500X (15X) efficiency in energy benefits at 300X (60X) higher throughput for multi-layer perceptrons (deep convolutional networks). Furthermore, RESPARC is a technology-aware architecture that maps a given SNN topology to the most optimized MCA size for the given crossbar technology.
Tasks
Published	2017-02-20
URL	http://arxiv.org/abs/1702.06064v1
PDF	http://arxiv.org/pdf/1702.06064v1.pdf
PWC	https://paperswithcode.com/paper/resparc-a-reconfigurable-and-energy-efficient
Repo
Framework

Online Meta-learning by Parallel Algorithm Competition


Title	Online Meta-learning by Parallel Algorithm Competition
Authors	Stefan Elfwing, Eiji Uchibe, Kenji Doya
Abstract	The efficiency of reinforcement learning algorithms depends critically on a few meta-parameters that modulates the learning updates and the trade-off between exploration and exploitation. The adaptation of the meta-parameters is an open question in reinforcement learning, which arguably has become more of an issue recently with the success of deep reinforcement learning in high-dimensional state spaces. The long learning times in domains such as Atari 2600 video games makes it not feasible to perform comprehensive searches of appropriate meta-parameter values. We propose the Online Meta-learning by Parallel Algorithm Competition (OMPAC) method. In the OMPAC method, several instances of a reinforcement learning algorithm are run in parallel with small differences in the initial values of the meta-parameters. After a fixed number of episodes, the instances are selected based on their performance in the task at hand. Before continuing the learning, Gaussian noise is added to the meta-parameters with a predefined probability. We validate the OMPAC method by improving the state-of-the-art results in stochastic SZ-Tetris and in standard Tetris with a smaller, 10$\times$10, board, by 31% and 84%, respectively, and by improving the results for deep Sarsa($\lambda$) agents in three Atari 2600 games by 62% or more. The experiments also show the ability of the OMPAC method to adapt the meta-parameters according to the learning progress in different tasks.
Tasks	Atari Games, Meta-Learning
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07490v1
PDF	http://arxiv.org/pdf/1702.07490v1.pdf
PWC	https://paperswithcode.com/paper/online-meta-learning-by-parallel-algorithm
Repo
Framework

Predictive-State Decoders: Encoding the Future into Recurrent Networks


Title	Predictive-State Decoders: Encoding the Future into Recurrent Networks
Authors	Arun Venkatraman, Nicholas Rhinehart, Wen Sun, Lerrel Pinto, Martial Hebert, Byron Boots, Kris M. Kitani, J. Andrew Bagnell
Abstract	Recurrent neural networks (RNNs) are a vital modeling technique that rely on internal states learned indirectly by optimization of a supervised, unsupervised, or reinforcement training loss. RNNs are used to model dynamic processes that are characterized by underlying latent states whose form is often unknown, precluding its analytic representation inside an RNN. In the Predictive-State Representation (PSR) literature, latent state processes are modeled by an internal state representation that directly models the distribution of future observations, and most recent work in this area has relied on explicitly representing and targeting sufficient statistics of this probability distribution. We seek to combine the advantages of RNNs and PSRs by augmenting existing state-of-the-art recurrent neural networks with Predictive-State Decoders (PSDs), which add supervision to the network’s internal state representation to target predicting future observations. Predictive-State Decoders are simple to implement and easily incorporated into existing training pipelines via additional loss regularization. We demonstrate the effectiveness of PSDs with experimental results in three different domains: probabilistic filtering, Imitation Learning, and Reinforcement Learning. In each, our method improves statistical performance of state-of-the-art recurrent baselines and does so with fewer iterations and less data.
Tasks	Imitation Learning
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08520v1
PDF	http://arxiv.org/pdf/1709.08520v1.pdf
PWC	https://paperswithcode.com/paper/predictive-state-decoders-encoding-the-future
Repo
Framework

Synthesis versus analysis in patch-based image priors


Title	Synthesis versus analysis in patch-based image priors
Authors	Mario A. T. Figueiredo
Abstract	In global models/priors (for example, using wavelet frames), there is a well known analysis vs synthesis dichotomy in the way signal/image priors are formulated. In patch-based image models/priors, this dichotomy is also present in the choice of how each patch is modeled. This paper shows that there is another analysis vs synthesis dichotomy, in terms of how the whole image is related to the patches, and that all existing patch-based formulations that provide a global image prior belong to the analysis category. We then propose a synthesis formulation, where the image is explicitly modeled as being synthesized by additively combining a collection of independent patches. We formally establish that these analysis and synthesis formulations are not equivalent in general and that both formulations are compatible with analysis and synthesis formulations at the patch level. Finally, we present an instance of the alternating direction method of multipliers (ADMM) that can be used to perform image denoising under the proposed synthesis formulation, showing its computational feasibility. Rather than showing the superiority of the synthesis or analysis formulations, the contributions of this paper is to establish the existence of both alternatives, thus closing the corresponding gap in the field of patch-based image processing.
Tasks	Denoising, Image Denoising
Published	2017-02-20
URL	http://arxiv.org/abs/1702.06085v1
PDF	http://arxiv.org/pdf/1702.06085v1.pdf
PWC	https://paperswithcode.com/paper/synthesis-versus-analysis-in-patch-based
Repo
Framework