Paper Group ANR 221
Classification regions of deep neural networks. DC-Prophet: Predicting Catastrophic Machine Failures in DataCenters. Winning on the Merits: The Joint Effects of Content and Style on Debate Outcomes. Setpoint Tracking with Partially Observed Loads. Multiobjective Programming for Type-2 Hierarchical Fuzzy Inference Trees. Programmable Agents. Feature …
Classification regions of deep neural networks
| Title | Classification regions of deep neural networks |
| Authors | Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, Stefano Soatto |
| Abstract | The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space. We specifically study the topology of classification regions created by deep networks, as well as their associated decision boundary. Through a systematic empirical investigation, we show that state-of-the-art deep nets learn connected classification regions, and that the decision boundary in the vicinity of datapoints is flat along most directions. We further draw an essential connection between two seemingly unrelated properties of deep networks: their sensitivity to additive perturbations in the inputs, and the curvature of their decision boundary. The directions where the decision boundary is curved in fact remarkably characterize the directions to which the classifier is the most vulnerable. We finally leverage a fundamental asymmetry in the curvature of the decision boundary of deep nets, and propose a method to discriminate between original images, and images perturbed with small adversarial examples. We show the effectiveness of this purely geometric approach for detecting small adversarial perturbations in images, and for recovering the labels of perturbed images. |
| Tasks | |
| Published | 2017-05-26 |
| URL | http://arxiv.org/abs/1705.09552v1 |
| http://arxiv.org/pdf/1705.09552v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-regions-of-deep-neural |
| Repo | |
| Framework | |
DC-Prophet: Predicting Catastrophic Machine Failures in DataCenters
| Title | DC-Prophet: Predicting Catastrophic Machine Failures in DataCenters |
| Authors | You-Luen Lee, Da-Cheng Juan, Xuan-An Tseng, Yu-Ting Chen, Shih-Chieh Chang |
| Abstract | When will a server fail catastrophically in an industrial datacenter? Is it possible to forecast these failures so preventive actions can be taken to increase the reliability of a datacenter? To answer these questions, we have studied what are probably the largest, publicly available datacenter traces, containing more than 104 million events from 12,500 machines. Among these samples, we observe and categorize three types of machine failures, all of which are catastrophic and may lead to information loss, or even worse, reliability degradation of a datacenter. We further propose a two-stage framework-DC-Prophet-based on One-Class Support Vector Machine and Random Forest. DC-Prophet extracts surprising patterns and accurately predicts the next failure of a machine. Experimental results show that DC-Prophet achieves an AUC of 0.93 in predicting the next machine failure, and a F3-score of 0.88 (out of 1). On average, DC-Prophet outperforms other classical machine learning methods by 39.45% in F3-score. |
| Tasks | |
| Published | 2017-08-14 |
| URL | http://arxiv.org/abs/1709.06537v1 |
| http://arxiv.org/pdf/1709.06537v1.pdf | |
| PWC | https://paperswithcode.com/paper/dc-prophet-predicting-catastrophic-machine |
| Repo | |
| Framework | |
Winning on the Merits: The Joint Effects of Content and Style on Debate Outcomes
| Title | Winning on the Merits: The Joint Effects of Content and Style on Debate Outcomes |
| Authors | Lu Wang, Nick Beauchamp, Sarah Shugars, Kechen Qin |
| Abstract | Debate and deliberation play essential roles in politics and government, but most models presume that debates are won mainly via superior style or agenda control. Ideally, however, debates would be won on the merits, as a function of which side has the stronger arguments. We propose a predictive model of debate that estimates the effects of linguistic features and the latent persuasive strengths of different topics, as well as the interactions between the two. Using a dataset of 118 Oxford-style debates, our model’s combination of content (as latent topics) and style (as linguistic features) allows us to predict audience-adjudicated winners with 74% accuracy, significantly outperforming linguistic features alone (66%). Our model finds that winning sides employ stronger arguments, and allows us to identify the linguistic features associated with strong or weak arguments. |
| Tasks | |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05040v1 |
| http://arxiv.org/pdf/1705.05040v1.pdf | |
| PWC | https://paperswithcode.com/paper/winning-on-the-merits-the-joint-effects-of |
| Repo | |
| Framework | |
Setpoint Tracking with Partially Observed Loads
| Title | Setpoint Tracking with Partially Observed Loads |
| Authors | Antoine Lesage-Landry, Joshua A. Taylor |
| Abstract | We use online convex optimization (OCO) for setpoint tracking with uncertain, flexible loads. We consider full feedback from the loads, bandit feedback, and two intermediate types of feedback: partial bandit where a subset of the loads are individually observed and the rest are observed in aggregate, and Bernoulli feedback where in each round the aggregator receives either full or bandit feedback according to a known probability. We give sublinear regret bounds in all cases. We numerically evaluate our algorithms on examples with thermostatically controlled loads and electric vehicles. |
| Tasks | |
| Published | 2017-09-12 |
| URL | http://arxiv.org/abs/1709.04077v2 |
| http://arxiv.org/pdf/1709.04077v2.pdf | |
| PWC | https://paperswithcode.com/paper/setpoint-tracking-with-partially-observed |
| Repo | |
| Framework | |
Multiobjective Programming for Type-2 Hierarchical Fuzzy Inference Trees
| Title | Multiobjective Programming for Type-2 Hierarchical Fuzzy Inference Trees |
| Authors | Varun Kumar Ojha, Vaclav Snasel, Ajith Abraham |
| Abstract | This paper proposes a design of hierarchical fuzzy inference tree (HFIT). An HFIT produces an optimum treelike structure, i.e., a natural hierarchical structure that accommodates simplicity by combining several low-dimensional fuzzy inference systems (FISs). Such a natural hierarchical structure provides a high degree of approximation accuracy. The construction of HFIT takes place in two phases. Firstly, a nondominated sorting based multiobjective genetic programming (MOGP) is applied to obtain a simple tree structure (a low complexity model) with a high accuracy. Secondly, the differential evolution algorithm is applied to optimize the obtained tree’s parameters. In the derived tree, each node acquires a different input’s combination, where the evolutionary process governs the input’s combination. Hence, HFIT nodes are heterogeneous in nature, which leads to a high diversity among the rules generated by the HFIT. Additionally, the HFIT provides an automatic feature selection because it uses MOGP for the tree’s structural optimization that accepts inputs only relevant to the knowledge contained in data. The HFIT was studied in the context of both type-1 and type-2 FISs, and its performance was evaluated through six application problems. Moreover, the proposed multiobjective HFIT was compared both theoretically and empirically with recently proposed FISs methods from the literature, such as McIT2FIS, TSCIT2FNN, SIT2FNN, RIT2FNS-WB, eT2FIS, MRIT2NFS, IT2FNN-SVR, etc. From the obtained results, it was found that the HFIT provided less complex and highly accurate models compared to the models produced by the most of other methods. Hence, the proposed HFIT is an efficient and competitive alternative to the other FISs for function approximation and feature selection. |
| Tasks | Feature Selection |
| Published | 2017-05-16 |
| URL | http://arxiv.org/abs/1705.05769v1 |
| http://arxiv.org/pdf/1705.05769v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiobjective-programming-for-type-2 |
| Repo | |
| Framework | |
Programmable Agents
| Title | Programmable Agents |
| Authors | Misha Denil, Sergio Gómez Colmenarejo, Serkan Cabi, David Saxton, Nando de Freitas |
| Abstract | We build deep RL agents that execute declarative programs expressed in formal language. The agents learn to ground the terms in this language in their environment, and can generalize their behavior at test time to execute new programs that refer to objects that were not referenced during training. The agents develop disentangled interpretable representations that allow them to generalize to a wide variety of zero-shot semantic tasks. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06383v1 |
| http://arxiv.org/pdf/1706.06383v1.pdf | |
| PWC | https://paperswithcode.com/paper/programmable-agents |
| Repo | |
| Framework | |
Feature Selection based on the Local Lift Dependence Scale
| Title | Feature Selection based on the Local Lift Dependence Scale |
| Authors | Diego Marcondes, Adilson Simonis, Junior Barrera |
| Abstract | This paper uses a classical approach to feature selection: minimization of a cost function applied on estimated joint distributions. However, the search space in which such minimization is performed is extended. In the original formulation, the search space is the Boolean lattice of features sets (BLFS), while, in the present formulation, it is a collection of Boolean lattices of ordered pairs (features, associated value) (CBLOP), indexed by the elements of the BLFS. In this approach, we may not only select the features that are most related to a variable Y, but also select the values of the features that most influence the variable or that are most prone to have a specific value of Y. A local formulation of Shanon’s mutual information is applied on a CBLOP to select features, namely, the Local Lift Dependence Scale, an scale for measuring variable dependence in multiple resolutions. The main contribution of this paper is to define and apply this local measure, which permits to analyse local properties of joint distributions that are neglected by the classical Shanon’s global measure. The proposed approach is applied to a dataset consisting of student performances on a university entrance exam, as well as on undergraduate courses. The approach is also applied to two datasets of the UCI Machine Learning Repository. |
| Tasks | Feature Selection |
| Published | 2017-11-11 |
| URL | http://arxiv.org/abs/1711.04181v3 |
| http://arxiv.org/pdf/1711.04181v3.pdf | |
| PWC | https://paperswithcode.com/paper/feature-selection-based-on-the-local-lift |
| Repo | |
| Framework | |
NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles
| Title | NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles |
| Authors | Jiajun Lu, Hussein Sibai, Evan Fabry, David Forsyth |
| Abstract | It has been shown that most machine learning algorithms are susceptible to adversarial perturbations. Slightly perturbing an image in a carefully chosen direction in the image space may cause a trained neural network model to misclassify it. Recently, it was shown that physical adversarial examples exist: printing perturbed images then taking pictures of them would still result in misclassification. This raises security and safety concerns. However, these experiments ignore a crucial property of physical objects: the camera can view objects from different distances and at different angles. In this paper, we show experiments that suggest that current constructions of physical adversarial examples do not disrupt object detection from a moving platform. Instead, a trained neural network classifies most of the pictures taken from different distances and angles of a perturbed image correctly. We believe this is because the adversarial property of the perturbation is sensitive to the scale at which the perturbed picture is viewed, so (for example) an autonomous car will misclassify a stop sign only from a small range of distances. Our work raises an important question: can one construct examples that are adversarial for many or most viewing conditions? If so, the construction should offer very significant insights into the internal representation of patterns by deep networks. If not, there is a good prospect that adversarial examples can be reduced to a curiosity with little practical impact. |
| Tasks | Autonomous Vehicles, Object Detection |
| Published | 2017-07-12 |
| URL | http://arxiv.org/abs/1707.03501v1 |
| http://arxiv.org/pdf/1707.03501v1.pdf | |
| PWC | https://paperswithcode.com/paper/no-need-to-worry-about-adversarial-examples |
| Repo | |
| Framework | |
Sparse Linear Isotonic Models
| Title | Sparse Linear Isotonic Models |
| Authors | Sheng Chen, Arindam Banerjee |
| Abstract | In machine learning and data mining, linear models have been widely used to model the response as parametric linear functions of the predictors. To relax such stringent assumptions made by parametric linear models, additive models consider the response to be a summation of unknown transformations applied on the predictors; in particular, additive isotonic models (AIMs) assume the unknown transformations to be monotone. In this paper, we introduce sparse linear isotonic models (SLIMs) for highdimensional problems by hybridizing ideas in parametric sparse linear models and AIMs, which enjoy a few appealing advantages over both. In the high-dimensional setting, a two-step algorithm is proposed for estimating the sparse parameters as well as the monotone functions over predictors. Under mild statistical assumptions, we show that the algorithm can accurately estimate the parameters. Promising preliminary experiments are presented to support the theoretical results. |
| Tasks | |
| Published | 2017-10-16 |
| URL | http://arxiv.org/abs/1710.05989v1 |
| http://arxiv.org/pdf/1710.05989v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-linear-isotonic-models |
| Repo | |
| Framework | |
Avaliação da doença de Alzheimer pela análise multiespectral de imagens DW-MR por redes RBF como alternativa aos mapas ADC
| Title | Avaliação da doença de Alzheimer pela análise multiespectral de imagens DW-MR por redes RBF como alternativa aos mapas ADC |
| Authors | Wellington Pinheiro dos Santos, Ricardo Emmanuel de Souza, Ascendino Flávio Dias e Silva, Plínio Batista dos Santos Filho |
| Abstract | Alzheimer’s disease is the most common cause of dementia, yet difficult to accurately diagnose without the use of invasive techniques, particularly at the beginning of the disease. This work addresses the classification and analysis of multispectral synthetic images composed by diffusion-weighted magnetic resonance brain volumes for evaluation of the area of cerebrospinal fluid and its correlation with the progression of Alzheimer’s disease. A 1.5 T MR imaging system was used to acquire all the images presented. The classification methods are based on multilayer perceptrons and classifiers of radial basis function networks. It is assumed that the classes of interest can be separated by hyperquadrics. A polynomial network of degree 2 is used to classify the original volumes, generating a ground-truth volume. The classification results are used to improve the usual analysis by the map of apparent diffusion coefficients. |
| Tasks | |
| Published | 2017-12-03 |
| URL | http://arxiv.org/abs/1712.01700v1 |
| http://arxiv.org/pdf/1712.01700v1.pdf | |
| PWC | https://paperswithcode.com/paper/avaliacao-da-doenca-de-alzheimer-pela-analise |
| Repo | |
| Framework | |
Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation
| Title | Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation |
| Authors | Matteo Ruggero Ronchi, Pietro Perona |
| Abstract | We propose a new method to analyze the impact of errors in algorithms for multi-instance pose estimation and a principled benchmark that can be used to compare them. We define and characterize three classes of errors - localization, scoring, and background - study how they are influenced by instance attributes and their impact on an algorithm’s performance. Our technique is applied to compare the two leading methods for human pose estimation on the COCO Dataset, measure the sensitivity of pose estimation with respect to instance size, type and number of visible keypoints, clutter due to multiple instances, and the relative score of instances. The performance of algorithms, and the types of error they make, are highly dependent on all these variables, but mostly on the number of keypoints and the clutter. The analysis and software tools we propose offer a novel and insightful approach for understanding the behavior of pose estimation algorithms and an effective method for measuring their strengths and weaknesses. |
| Tasks | Pose Estimation |
| Published | 2017-07-17 |
| URL | http://arxiv.org/abs/1707.05388v2 |
| http://arxiv.org/pdf/1707.05388v2.pdf | |
| PWC | https://paperswithcode.com/paper/benchmarking-and-error-diagnosis-in-multi |
| Repo | |
| Framework | |
Answer Set Solving with Bounded Treewidth Revisited
| Title | Answer Set Solving with Bounded Treewidth Revisited |
| Authors | Johannes Fichte, Markus Hecher, Michael Morak, Stefan Woltran |
| Abstract | Parameterized algorithms are a way to solve hard problems more efficiently, given that a specific parameter of the input is small. In this paper, we apply this idea to the field of answer set programming (ASP). To this end, we propose two kinds of graph representations of programs to exploit their treewidth as a parameter. Treewidth roughly measures to which extent the internal structure of a program resembles a tree. Our main contribution is the design of parameterized dynamic programming algorithms, which run in linear time if the treewidth and weights of the given program are bounded. Compared to previous work, our algorithms handle the full syntax of ASP. Finally, we report on an empirical evaluation that shows good runtime behaviour for benchmark instances of low treewidth, especially for counting answer sets. |
| Tasks | |
| Published | 2017-02-09 |
| URL | http://arxiv.org/abs/1702.02890v1 |
| http://arxiv.org/pdf/1702.02890v1.pdf | |
| PWC | https://paperswithcode.com/paper/answer-set-solving-with-bounded-treewidth |
| Repo | |
| Framework | |
GAGAN: Geometry-Aware Generative Adversarial Networks
| Title | GAGAN: Geometry-Aware Generative Adversarial Networks |
| Authors | Jean Kossaifi, Linh Tran, Yannis Panagakis, Maja Pantic |
| Abstract | Deep generative models learned through adversarial training have become increasingly popular for their ability to generate naturalistic image textures. However, aside from their texture, the visual appearance of objects is significantly influenced by their shape geometry; information which is not taken into account by existing generative models. This paper introduces the Geometry-Aware Generative Adversarial Networks (GAGAN) for incorporating geometric information into the image generation process. Specifically, in GAGAN the generator samples latent variables from the probability space of a statistical shape model. By mapping the output of the generator to a canonical coordinate frame through a differentiable geometric transformation, we enforce the geometry of the objects and add an implicit connection from the prior to the generated object. Experimental results on face generation indicate that the GAGAN can generate realistic images of faces with arbitrary facial attributes such as facial expression, pose, and morphology, that are of better quality than current GAN-based methods. Our method can be used to augment any existing GAN architecture and improve the quality of the images generated. |
| Tasks | Face Generation, Image Generation |
| Published | 2017-12-03 |
| URL | http://arxiv.org/abs/1712.00684v3 |
| http://arxiv.org/pdf/1712.00684v3.pdf | |
| PWC | https://paperswithcode.com/paper/gagan-geometry-aware-generative-adversarial |
| Repo | |
| Framework | |
Towards Grounding Conceptual Spaces in Neural Representations
| Title | Towards Grounding Conceptual Spaces in Neural Representations |
| Authors | Lucas Bechberger, Kai-Uwe Kühnberger |
| Abstract | The highly influential framework of conceptual spaces provides a geometric way of representing knowledge. It aims at bridging the gap between symbolic and subsymbolic processing. Instances are represented by points in a high-dimensional space and concepts are represented by convex regions in this space. In this paper, we present our approach towards grounding the dimensions of a conceptual space in latent spaces learned by an InfoGAN from unlabeled data. |
| Tasks | |
| Published | 2017-06-15 |
| URL | http://arxiv.org/abs/1706.04825v2 |
| http://arxiv.org/pdf/1706.04825v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-grounding-conceptual-spaces-in-neural |
| Repo | |
| Framework | |
Geometric Loss Functions for Camera Pose Regression with Deep Learning
| Title | Geometric Loss Functions for Camera Pose Regression with Deep Learning |
| Authors | Alex Kendall, Roberto Cipolla |
| Abstract | Deep learning has shown to be effective for robust and real-time monocular image relocalisation. In particular, PoseNet is a deep convolutional neural network which learns to regress the 6-DOF camera pose from a single image. It learns to localize using high level features and is robust to difficult lighting, motion blur and unknown camera intrinsics, where point based SIFT registration fails. However, it was trained using a naive loss function, with hyper-parameters which require expensive tuning. In this paper, we give the problem a more fundamental theoretical treatment. We explore a number of novel loss functions for learning camera pose which are based on geometry and scene reprojection error. Additionally we show how to automatically learn an optimal weighting to simultaneously regress position and orientation. By leveraging geometry, we demonstrate that our technique significantly improves PoseNet’s performance across datasets ranging from indoor rooms to a small city. |
| Tasks | |
| Published | 2017-04-02 |
| URL | http://arxiv.org/abs/1704.00390v2 |
| http://arxiv.org/pdf/1704.00390v2.pdf | |
| PWC | https://paperswithcode.com/paper/geometric-loss-functions-for-camera-pose |
| Repo | |
| Framework | |
