May 6, 2019

2595 words 13 mins read

Paper Group ANR 427

A Bayesian Ensemble for Unsupervised Anomaly Detection. Deep Multi-Species Embedding. Quantitative Analysis of Saliency Models. Sentiment Classification of Food Reviews. Labeling Topics with Images using Neural Networks. Theoretical Analysis of Active Contours on Graphs. A computer program for simulating time travel and a possible ‘solution’ for th …

A Bayesian Ensemble for Unsupervised Anomaly Detection


Title	A Bayesian Ensemble for Unsupervised Anomaly Detection
Authors	Edward Yu, Parth Parekh
Abstract	Methods for unsupervised anomaly detection suffer from the fact that the data is unlabeled, making it difficult to assess the optimality of detection algorithms. Ensemble learning has shown exceptional results in classification and clustering problems, but has not seen as much research in the context of outlier detection. Existing methods focus on combining output scores of individual detectors, but this leads to outputs that are not easily interpretable. In this paper, we introduce a theoretical foundation for combining individual detectors with Bayesian classifier combination. Not only are posterior distributions easily interpreted as the probability distribution of anomalies, but bias, variance, and individual error rates of detectors are all easily obtained. Performance on real-world datasets shows high accuracy across varied types of time series data.
Tasks	Anomaly Detection, Outlier Detection, Time Series, Unsupervised Anomaly Detection
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07677v1
PDF	http://arxiv.org/pdf/1610.07677v1.pdf
PWC	https://paperswithcode.com/paper/a-bayesian-ensemble-for-unsupervised-anomaly
Repo
Framework

Deep Multi-Species Embedding


Title	Deep Multi-Species Embedding
Authors	Di Chen, Yexiang Xue, Shuo Chen, Daniel Fink, Carla Gomes
Abstract	Understanding how species are distributed across landscapes over time is a fundamental question in biodiversity research. Unfortunately, most species distribution models only target a single species at a time, despite strong ecological evidence that species are not independently distributed. We propose Deep Multi-Species Embedding (DMSE), which jointly embeds vectors corresponding to multiple species as well as vectors representing environmental covariates into a common high-dimensional feature space via a deep neural network. Applied to bird observational data from the citizen science project \textit{eBird}, we demonstrate how the DMSE model discovers inter-species relationships to outperform single-species distribution models (random forests and SVMs) as well as competing multi-label models. Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling. An important domain contribution of the DMSE model is the ability to discover and describe species interactions while simultaneously learning the shared habitat preferences among species. As an additional contribution, we provide a graphical embedding of hundreds of bird species in the Northeast US.
Tasks
Published	2016-09-28
URL	http://arxiv.org/abs/1609.09353v4
PDF	http://arxiv.org/pdf/1609.09353v4.pdf
PWC	https://paperswithcode.com/paper/deep-multi-species-embedding
Repo
Framework

Quantitative Analysis of Saliency Models


Title	Quantitative Analysis of Saliency Models
Authors	Flora Ponjou Tasse, Jiří Kosinka, Neil Anthony Dodgson
Abstract	Previous saliency detection research required the reader to evaluate performance qualitatively, based on renderings of saliency maps on a few shapes. This qualitative approach meant it was unclear which saliency models were better, or how well they compared to human perception. This paper provides a quantitative evaluation framework that addresses this issue. In the first quantitative analysis of 3D computational saliency models, we evaluate four computational saliency models and two baseline models against ground-truth saliency collected in previous work.
Tasks	Saliency Detection
Published	2016-05-31
URL	http://arxiv.org/abs/1605.09451v1
PDF	http://arxiv.org/pdf/1605.09451v1.pdf
PWC	https://paperswithcode.com/paper/quantitative-analysis-of-saliency-models
Repo
Framework

Sentiment Classification of Food Reviews


Title	Sentiment Classification of Food Reviews
Authors	Hua Feng, Ruixi Lin
Abstract	Sentiment analysis of reviews is a popular task in natural language processing. In this work, the goal is to predict the score of food reviews on a scale of 1 to 5 with two recurrent neural networks that are carefully tuned. As for baseline, we train a simple RNN for classification. Then we extend the baseline to GRU. In addition, we present two different methods to deal with highly skewed data, which is a common problem for reviews. Models are evaluated using accuracies.
Tasks	Sentiment Analysis
Published	2016-09-07
URL	http://arxiv.org/abs/1609.01933v1
PDF	http://arxiv.org/pdf/1609.01933v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-classification-of-food-reviews
Repo
Framework

Labeling Topics with Images using Neural Networks


Title	Labeling Topics with Images using Neural Networks
Authors	Nikolaos Aletras, Arpit Mittal
Abstract	Topics generated by topic models are usually represented by lists of $t$ terms or alternatively using short phrases and images. The current state-of-the-art work on labeling topics using images selects images by re-ranking a small set of candidates for a given topic. In this paper, we present a more generic method that can estimate the degree of association between any arbitrary pair of an unseen topic and image using a deep neural network. Our method has better runtime performance $O(n)$ compared to $O(n^2)$ for the current state-of-the-art method, and is also significantly more accurate.
Tasks	Topic Models
Published	2016-08-01
URL	http://arxiv.org/abs/1608.00470v2
PDF	http://arxiv.org/pdf/1608.00470v2.pdf
PWC	https://paperswithcode.com/paper/labeling-topics-with-images-using-neural
Repo
Framework

Theoretical Analysis of Active Contours on Graphs


Title	Theoretical Analysis of Active Contours on Graphs
Authors	Christos Sakaridis, Kimon Drakopoulos, Petros Maragos
Abstract	Active contour models based on partial differential equations have proved successful in image segmentation, yet the study of their geometric formulation on arbitrary geometric graphs is still at an early stage. In this paper, we introduce geometric approximations of gradient and curvature, which are used in the geodesic active contour model. We prove convergence in probability of our gradient approximation to the true gradient value and derive an asymptotic upper bound for the error of this approximation for the class of random geometric graphs. Two different approaches for the approximation of curvature are presented and both are also proved to converge in probability in the case of random geometric graphs. We propose neighborhood-based filtering on graphs to improve the accuracy of the aforementioned approximations and define two variants of Gaussian smoothing on graphs which include normalization in order to adapt to graph non-uniformities. The performance of our active contour framework on graphs is demonstrated in the segmentation of regular images and geographical data defined on arbitrary graphs.
Tasks	Semantic Segmentation
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07381v1
PDF	http://arxiv.org/pdf/1610.07381v1.pdf
PWC	https://paperswithcode.com/paper/theoretical-analysis-of-active-contours-on
Repo
Framework

A computer program for simulating time travel and a possible ‘solution’ for the grandfather paradox


Title	A computer program for simulating time travel and a possible ‘solution’ for the grandfather paradox
Authors	Doron Friedman
Abstract	While the possibility of time travel in physics is still debated, the explosive growth of virtual-reality simulations opens up new possibilities to rigorously explore such time travel and its consequences in the digital domain. Here we provide a computational model of time travel and a computer program that allows exploring digital time travel. In order to explain our method we formalize a simplified version of the famous grandfather paradox, show how the system can allow the participant to go back in time, try to kill their ancestors before they were born, and experience the consequences. The system has even come up with scenarios that can be considered consistent “solutions” of the grandfather paradox. We discuss the conditions for digital time travel, which indicate that it has a large number of practical applications.
Tasks
Published	2016-09-26
URL	http://arxiv.org/abs/1609.08470v1
PDF	http://arxiv.org/pdf/1609.08470v1.pdf
PWC	https://paperswithcode.com/paper/a-computer-program-for-simulating-time-travel
Repo
Framework

Local Canonical Correlation Analysis for Nonlinear Common Variables Discovery


Title	Local Canonical Correlation Analysis for Nonlinear Common Variables Discovery
Authors	Or Yair, Ronen Talmon
Abstract	In this paper, we address the problem of hidden common variables discovery from multimodal data sets of nonlinear high-dimensional observations. We present a metric based on local applications of canonical correlation analysis (CCA) and incorporate it in a kernel-based manifold learning technique.We show that this metric discovers the hidden common variables underlying the multimodal observations by estimating the Euclidean distance between them. Our approach can be viewed both as an extension of CCA to a nonlinear setting as well as an extension of manifold learning to multiple data sets. Experimental results show that our method indeed discovers the common variables underlying high-dimensional nonlinear observations without assuming prior rigid model assumptions.
Tasks
Published	2016-06-14
URL	http://arxiv.org/abs/1606.04268v1
PDF	http://arxiv.org/pdf/1606.04268v1.pdf
PWC	https://paperswithcode.com/paper/local-canonical-correlation-analysis-for
Repo
Framework

Convergence Rate of Frank-Wolfe for Non-Convex Objectives


Title	Convergence Rate of Frank-Wolfe for Non-Convex Objectives
Authors	Simon Lacoste-Julien
Abstract	We give a simple proof that the Frank-Wolfe algorithm obtains a stationary point at a rate of $O(1/\sqrt{t})$ on non-convex objectives with a Lipschitz continuous gradient. Our analysis is affine invariant and is the first, to the best of our knowledge, giving a similar rate to what was already proven for projected gradient methods (though on slightly different measures of stationarity).
Tasks
Published	2016-07-01
URL	http://arxiv.org/abs/1607.00345v1
PDF	http://arxiv.org/pdf/1607.00345v1.pdf
PWC	https://paperswithcode.com/paper/convergence-rate-of-frank-wolfe-for-non
Repo
Framework

Active Deep Learning for Classification of Hyperspectral Images


Title	Active Deep Learning for Classification of Hyperspectral Images
Authors	Peng Liu, Hui Zhang, Kie B. Eom
Abstract	Active deep learning classification of hyperspectral images is considered in this paper. Deep learning has achieved success in many applications, but good-quality labeled samples are needed to construct a deep learning network. It is expensive getting good labeled samples in hyperspectral images for remote sensing applications. An active learning algorithm based on a weighted incremental dictionary learning is proposed for such applications. The proposed algorithm selects training samples that maximize two selection criteria, namely representative and uncertainty. This algorithm trains a deep network efficiently by actively selecting training samples at each iteration. The proposed algorithm is applied for the classification of hyperspectral images, and compared with other classification algorithms employing active learning. It is shown that the proposed algorithm is efficient and effective in classifying hyperspectral images.
Tasks	Active Learning, Classification Of Hyperspectral Images, Dictionary Learning
Published	2016-11-30
URL	http://arxiv.org/abs/1611.10031v1
PDF	http://arxiv.org/pdf/1611.10031v1.pdf
PWC	https://paperswithcode.com/paper/active-deep-learning-for-classification-of
Repo
Framework

Discovering Phase Transitions with Unsupervised Learning


Title	Discovering Phase Transitions with Unsupervised Learning
Authors	Lei Wang
Abstract	Unsupervised learning is a discipline of machine learning which aims at discovering patterns in big data sets or classifying the data into several categories without being trained explicitly. We show that unsupervised learning techniques can be readily used to identify phases and phases transitions of many body systems. Starting with raw spin configurations of a prototypical Ising model, we use principal component analysis to extract relevant low dimensional representations the original data and use clustering analysis to identify distinct phases in the feature space. This approach successfully finds out physical concepts such as order parameter and structure factor to be indicators of the phase transition. We discuss future prospects of discovering more complex phases and phase transitions using unsupervised learning techniques.
Tasks
Published	2016-06-01
URL	http://arxiv.org/abs/1606.00318v2
PDF	http://arxiv.org/pdf/1606.00318v2.pdf
PWC	https://paperswithcode.com/paper/discovering-phase-transitions-with
Repo
Framework

On Data-Independent Properties for Density-Based Dissimilarity Measures in Hybrid Clustering


Title	On Data-Independent Properties for Density-Based Dissimilarity Measures in Hybrid Clustering
Authors	Kajsa Møllersen, Subhra S. Dhar, Fred Godtliebsen
Abstract	Hybrid clustering combines partitional and hierarchical clustering for computational effectiveness and versatility in cluster shape. In such clustering, a dissimilarity measure plays a crucial role in the hierarchical merging. The dissimilarity measure has great impact on the final clustering, and data-independent properties are needed to choose the right dissimilarity measure for the problem at hand. Properties for distance-based dissimilarity measures have been studied for decades, but properties for density-based dissimilarity measures have so far received little attention. Here, we propose six data-independent properties to evaluate density-based dissimilarity measures associated with hybrid clustering, regarding equality, orthogonality, symmetry, outlier and noise observations, and light-tailed models for heavy-tailed clusters. The significance of the properties is investigated, and we study some well-known dissimilarity measures based on Shannon entropy, misclassification rate, Bhattacharyya distance and Kullback-Leibler divergence with respect to the proposed properties. As none of them satisfy all the proposed properties, we introduce a new dissimilarity measure based on the Kullback-Leibler information and show that it satisfies all proposed properties. The effect of the proposed properties is also illustrated on several real and simulated data sets.
Tasks
Published	2016-09-21
URL	http://arxiv.org/abs/1609.06533v1
PDF	http://arxiv.org/pdf/1609.06533v1.pdf
PWC	https://paperswithcode.com/paper/on-data-independent-properties-for-density
Repo
Framework

Automatic Variational ABC


Title	Automatic Variational ABC
Authors	Alexander Moreno, Tameem Adel, Edward Meeds, James M. Rehg, Max Welling
Abstract	Approximate Bayesian Computation (ABC) is a framework for performing likelihood-free posterior inference for simulation models. Stochastic Variational inference (SVI) is an appealing alternative to the inefficient sampling approaches commonly used in ABC. However, SVI is highly sensitive to the variance of the gradient estimators, and this problem is exacerbated by approximating the likelihood. We draw upon recent advances in variance reduction for SV and likelihood-free inference using deterministic simulations to produce low variance gradient estimators of the variational lower-bound. By then exploiting automatic differentiation libraries we can avoid nearly all model-specific derivations. We demonstrate performance on three problems and compare to existing SVI algorithms. Our results demonstrate the correctness and efficiency of our algorithm.
Tasks
Published	2016-06-28
URL	http://arxiv.org/abs/1606.08549v1
PDF	http://arxiv.org/pdf/1606.08549v1.pdf
PWC	https://paperswithcode.com/paper/automatic-variational-abc
Repo
Framework

Estimating Activity at Multiple Scales using Spatial Abstractions


Title	Estimating Activity at Multiple Scales using Spatial Abstractions
Authors	Majd Hawasly, Florian T. Pokorny, Subramanian Ramamoorthy
Abstract	Autonomous robots operating in dynamic environments must maintain beliefs over a hypothesis space that is rich enough to represent the activities of interest at different scales. This is important both in order to accommodate the availability of evidence at varying degrees of coarseness, such as when interpreting and assimilating natural instructions, but also in order to make subsequent reactive planning more efficient. We present an algorithm that combines a topology-based trajectory clustering procedure that generates hierarchically-structured spatial abstractions with a bank of particle filters at each of these abstraction levels so as to produce probability estimates over an agent’s navigation activity that is kept consistent across the hierarchy. We study the performance of the proposed method using a synthetic trajectory dataset in 2D, as well as a dataset taken from AIS-based tracking of ships in an extended harbour area. We show that, in comparison to a baseline which is a particle filter that estimates activity without exploiting such structure, our method achieves a better normalised error in predicting the trajectory as well as better time to convergence to a true class when compared against ground truth.
Tasks
Published	2016-07-25
URL	http://arxiv.org/abs/1607.07311v1
PDF	http://arxiv.org/pdf/1607.07311v1.pdf
PWC	https://paperswithcode.com/paper/estimating-activity-at-multiple-scales-using
Repo
Framework

The Off-Switch Game


Title	The Off-Switch Game
Authors	Dylan Hadfield-Menell, Anca Dragan, Pieter Abbeel, Stuart Russell
Abstract	It is clear that one of the primary tools we can use to mitigate the potential risk from a misbehaving AI system is the ability to turn the system off. As the capabilities of AI systems improve, it is important to ensure that such systems do not adopt subgoals that prevent a human from switching them off. This is a challenge because many formulations of rational agents create strong incentives for self-preservation. This is not caused by a built-in instinct, but because a rational agent will maximize expected utility and cannot achieve whatever objective it has been given if it is dead. Our goal is to study the incentives an agent has to allow itself to be switched off. We analyze a simple game between a human H and a robot R, where H can press R’s off switch but R can disable the off switch. A traditional agent takes its reward function for granted: we show that such agents have an incentive to disable the off switch, except in the special case where H is perfectly rational. Our key insight is that for R to want to preserve its off switch, it needs to be uncertain about the utility associated with the outcome, and to treat H’s actions as important observations about that utility. (R also has no incentive to switch itself off in this setting.) We conclude that giving machines an appropriate level of uncertainty about their objectives leads to safer designs, and we argue that this setting is a useful generalization of the classical AI paradigm of rational agents.
Tasks
Published	2016-11-24
URL	http://arxiv.org/abs/1611.08219v3
PDF	http://arxiv.org/pdf/1611.08219v3.pdf
PWC	https://paperswithcode.com/paper/the-off-switch-game
Repo
Framework