Paper Group ANR 1115
Mining Sub-Interval Relationships In Time Series Data. Finding Person Relations in Image Data of the Internet Archive. Auto-Encoding Total Correlation Explanation. A Fast Text Similarity Measure for Large Document Collections using Multi-reference Cosine and Genetic Algorithm. EagleEye: Attack-Agnostic Defense against Adversarial Inputs (Technical …
Mining Sub-Interval Relationships In Time Series Data
Title | Mining Sub-Interval Relationships In Time Series Data |
Authors | Saurabh Agrawal, Saurabh Verma, Gowtham Atluri, Anuj Karpatne, Stefan Liess, Angus Macdonald III, Snigdhansu Chatterjee, Vipin Kumar |
Abstract | Time-series data is being increasingly collected and stud- ied in several areas such as neuroscience, climate science, transportation, and social media. Discovery of complex patterns of relationships between individual time-series, using data-driven approaches can improve our understanding of real-world systems. While traditional approaches typically study relationships between two entire time series, many interesting relationships in real-world applications exist in small sub-intervals of time while remaining absent or feeble during other sub-intervals. In this paper, we define the notion of a sub-interval relationship (SIR) to capture inter- actions between two time series that are prominent only in certain sub-intervals of time. We propose a novel and efficient approach to find most interesting SIR in a pair of time series. We evaluate our proposed approach on two real-world datasets from climate science and neuroscience domain and demonstrated the scalability and computational efficiency of our proposed approach. We further evaluated our discovered SIRs based on a randomization based procedure. Our results indicated the existence of several such relationships that are statistically significant, some of which were also found to have physical interpretation. |
Tasks | Time Series |
Published | 2018-02-16 |
URL | http://arxiv.org/abs/1802.06095v1 |
http://arxiv.org/pdf/1802.06095v1.pdf | |
PWC | https://paperswithcode.com/paper/mining-sub-interval-relationships-in-time |
Repo | |
Framework | |
Finding Person Relations in Image Data of the Internet Archive
Title | Finding Person Relations in Image Data of the Internet Archive |
Authors | Eric Müller-Budack, Kader Pustu-Iren, Sebastian Diering, Ralph Ewerth |
Abstract | The multimedia content in the World Wide Web is rapidly growing and contains valuable information for many applications in different domains. For this reason, the Internet Archive initiative has been gathering billions of time-versioned web pages since the mid-nineties. However, the huge amount of data is rarely labeled with appropriate metadata and automatic approaches are required to enable semantic search. Normally, the textual content of the Internet Archive is used to extract entities and their possible relations across domains such as politics and entertainment, whereas image and video content is usually neglected. In this paper, we introduce a system for person recognition in image content of web news stored in the Internet Archive. Thus, the system complements entity recognition in text and allows researchers and analysts to track media coverage and relations of persons more precisely. Based on a deep learning face recognition approach, we suggest a system that automatically detects persons of interest and gathers sample material, which is subsequently used to identify them in the image data of the Internet Archive. We evaluate the performance of the face recognition system on an appropriate standard benchmark dataset and demonstrate the feasibility of the approach with two use cases. |
Tasks | Face Recognition, Person Recognition |
Published | 2018-06-21 |
URL | https://arxiv.org/abs/1806.08246v2 |
https://arxiv.org/pdf/1806.08246v2.pdf | |
PWC | https://paperswithcode.com/paper/finding-person-relations-in-image-data-of-the |
Repo | |
Framework | |
Auto-Encoding Total Correlation Explanation
Title | Auto-Encoding Total Correlation Explanation |
Authors | Shuyang Gao, Rob Brekelmans, Greg Ver Steeg, Aram Galstyan |
Abstract | Advances in unsupervised learning enable reconstruction and generation of samples from complex distributions, but this success is marred by the inscrutability of the representations learned. We propose an information-theoretic approach to characterizing disentanglement and dependence in representation learning using multivariate mutual information, also called total correlation. The principle of total Cor-relation Ex-planation (CorEx) has motivated successful unsupervised learning applications across a variety of domains, but under some restrictive assumptions. Here we relax those restrictions by introducing a flexible variational lower bound to CorEx. Surprisingly, we find that this lower bound is equivalent to the one in variational autoencoders (VAE) under certain conditions. This information-theoretic view of VAE deepens our understanding of hierarchical VAE and motivates a new algorithm, AnchorVAE, that makes latent codes more interpretable through information maximization and enables generation of richer and more realistic samples. |
Tasks | Representation Learning |
Published | 2018-02-16 |
URL | http://arxiv.org/abs/1802.05822v1 |
http://arxiv.org/pdf/1802.05822v1.pdf | |
PWC | https://paperswithcode.com/paper/auto-encoding-total-correlation-explanation |
Repo | |
Framework | |
A Fast Text Similarity Measure for Large Document Collections using Multi-reference Cosine and Genetic Algorithm
Title | A Fast Text Similarity Measure for Large Document Collections using Multi-reference Cosine and Genetic Algorithm |
Authors | Hamid Mohammadi, Seyed Hossein Khasteh |
Abstract | One of the important factors that make a search engine fast and accurate is a concise and duplicate free index. In order to remove duplicate and near-duplicate documents from the index, a search engine needs a swift and reliable duplicate and near-duplicate text document detection system. Traditional approaches to this problem, such as brute force comparisons or simple hash-based algorithms are not suitable as they are not scalable and are not capable of detecting near-duplicate documents effectively. In this paper, a new signature-based approach to text similarity detection is introduced which is fast, scalable, reliable and needs less storage space. The proposed method is examined on popular text document data-sets such as CiteseerX, Enron, Gold Set of Near-duplicate News Articles and etc. The results are promising and comparable with the best cutting-edge algorithms, considering the accuracy and performance. The proposed method is based on the idea of using reference texts to generate signatures for text documents. The novelty of this paper is the use of genetic algorithms to generate better reference texts. |
Tasks | |
Published | 2018-10-07 |
URL | https://arxiv.org/abs/1810.03102v3 |
https://arxiv.org/pdf/1810.03102v3.pdf | |
PWC | https://paperswithcode.com/paper/a-fast-text-similarity-measure-for-large |
Repo | |
Framework | |
EagleEye: Attack-Agnostic Defense against Adversarial Inputs (Technical Report)
Title | EagleEye: Attack-Agnostic Defense against Adversarial Inputs (Technical Report) |
Authors | Yujie Ji, Xinyang Zhang, Ting Wang |
Abstract | Deep neural networks (DNNs) are inherently vulnerable to adversarial inputs: such maliciously crafted samples trigger DNNs to misbehave, leading to detrimental consequences for DNN-powered systems. The fundamental challenges of mitigating adversarial inputs stem from their adaptive and variable nature. Existing solutions attempt to improve DNN resilience against specific attacks; yet, such static defenses can often be circumvented by adaptively engineered inputs or by new attack variants. Here, we present EagleEye, an attack-agnostic adversarial tampering analysis engine for DNN-powered systems. Our design exploits the {\em minimality principle} underlying many attacks: to maximize the attack’s evasiveness, the adversary often seeks the minimum possible distortion to convert genuine inputs to adversarial ones. We show that this practice entails the distinct distributional properties of adversarial inputs in the input space. By leveraging such properties in a principled manner, EagleEye effectively discriminates adversarial inputs and even uncovers their correct classification outputs. Through extensive empirical evaluation using a range of benchmark datasets and DNN models, we validate EagleEye’s efficacy. We further investigate the adversary’s possible countermeasures, which implies a difficult dilemma for her: to evade EagleEye’s detection, excessive distortion is necessary, thereby significantly reducing the attack’s evasiveness regarding other detection mechanisms. |
Tasks | |
Published | 2018-08-01 |
URL | http://arxiv.org/abs/1808.00123v1 |
http://arxiv.org/pdf/1808.00123v1.pdf | |
PWC | https://paperswithcode.com/paper/eagleeye-attack-agnostic-defense-against |
Repo | |
Framework | |
Improving Hearthstone AI by Combining MCTS and Supervised Learning Algorithms
Title | Improving Hearthstone AI by Combining MCTS and Supervised Learning Algorithms |
Authors | Maciej Świechowski, Tomasz Tajmajer, Andrzej Janusz |
Abstract | We investigate the impact of supervised prediction models on the strength and efficiency of artificial agents that use the Monte-Carlo Tree Search (MCTS) algorithm to play a popular video game Hearthstone: Heroes of Warcraft. We overview our custom implementation of the MCTS that is well-suited for games with partially hidden information and random effects. We also describe experiments which we designed to quantify the performance of our Hearthstone agent’s decision making. We show that even simple neural networks can be trained and successfully used for the evaluation of game states. Moreover, we demonstrate that by providing a guidance to the game state search heuristic, it is possible to substantially improve the win rate, and at the same time reduce the required computations. |
Tasks | Decision Making |
Published | 2018-08-14 |
URL | http://arxiv.org/abs/1808.04794v1 |
http://arxiv.org/pdf/1808.04794v1.pdf | |
PWC | https://paperswithcode.com/paper/improving-hearthstone-ai-by-combining-mcts |
Repo | |
Framework | |
Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images
Title | Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images |
Authors | Iljoo Baek, Albert Davies, Geng Yan, Ragunathan, Rajkumar |
Abstract | The ability to detect pedestrians and other moving objects is crucial for an autonomous vehicle. This must be done in real-time with minimum system overhead. This paper discusses the implementation of a surround view system to identify moving as well as static objects that are close to the ego vehicle. The algorithm works on 4 views captured by fisheye cameras which are merged into a single frame. The moving object detection and tracking solution uses minimal system overhead to isolate regions of interest (ROIs) containing moving objects. These ROIs are then analyzed using a deep neural network (DNN) to categorize the moving object. With deployment and testing on a real car in urban environments, we have demonstrated the practical feasibility of the solution. The video demos of our algorithm have been uploaded to Youtube: https://youtu.be/vpoCfC724iA, https://youtu.be/2X4aqH2bMBs |
Tasks | Object Detection |
Published | 2018-03-16 |
URL | http://arxiv.org/abs/1803.06077v2 |
http://arxiv.org/pdf/1803.06077v2.pdf | |
PWC | https://paperswithcode.com/paper/real-time-detection-tracking-and |
Repo | |
Framework | |
Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion
Title | Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion |
Authors | Alex Zihao Zhu, Liangzhe Yuan, Kenneth Chaney, Kostas Daniilidis |
Abstract | In this work, we propose a novel framework for unsupervised learning for event cameras that learns motion information from only the event stream. In particular, we propose an input representation of the events in the form of a discretized volume that maintains the temporal distribution of the events, which we pass through a neural network to predict the motion of the events. This motion is used to attempt to remove any motion blur in the event image. We then propose a loss function applied to the motion compensated event image that measures the motion blur in this image. We train two networks with this framework, one to predict optical flow, and one to predict egomotion and depths, and evaluate these networks on the Multi Vehicle Stereo Event Camera dataset, along with qualitative results from a variety of different scenes. |
Tasks | Optical Flow Estimation |
Published | 2018-12-19 |
URL | http://arxiv.org/abs/1812.08156v1 |
http://arxiv.org/pdf/1812.08156v1.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-event-based-learning-of-optical |
Repo | |
Framework | |
Learning of Multi-Context Models for Autonomous Underwater Vehicles
Title | Learning of Multi-Context Models for Autonomous Underwater Vehicles |
Authors | Bilal Wehbe, Octavio Arriaga, Mario Michael Krell, Frank Kirchner |
Abstract | Multi-context model learning is crucial for marine robotics where several factors can cause disturbances to the system’s dynamics. This work addresses the problem of identifying multiple contexts of an AUV model. We build a simulation model of the robot from experimental data, and use it to fill in the missing data and generate different model contexts. We implement an architecture based on long-short-term-memory (LSTM) networks to learn the different contexts directly from the data. We show that the LSTM network can achieve high classification accuracy compared to baseline methods, showing robustness against noise and scaling efficiently on large datasets. |
Tasks | |
Published | 2018-09-17 |
URL | http://arxiv.org/abs/1809.06179v1 |
http://arxiv.org/pdf/1809.06179v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-of-multi-context-models-for |
Repo | |
Framework | |
On the Blindspots of Convolutional Networks
Title | On the Blindspots of Convolutional Networks |
Authors | Elad Hoffer, Shai Fine, Daniel Soudry |
Abstract | Deep convolutional network has been the state-of-the-art approach for a wide variety of tasks over the last few years. Its successes have, in many cases, turned it into the default model in quite a few domains. In this work, we will demonstrate that convolutional networks have limitations that may, in some cases, hinder it from learning properties of the data, which are easily recognizable by traditional, less demanding, models. To this end, we present a series of competitive analysis studies on image recognition and text analysis tasks, for which convolutional networks are known to provide state-of-the-art results. In our studies, we inject a truth-revealing signal, indiscernible for the network, thus hitting time and again the network’s blind spots. The signal does not impair the network’s existing performances, but it does provide an opportunity for a significant performance boost by models that can capture it. The various forms of the carefully designed signals shed a light on the strengths and weaknesses of convolutional network, which may provide insights for both theoreticians that study the power of deep architectures, and for practitioners that consider applying convolutional networks to the task at hand. |
Tasks | |
Published | 2018-02-14 |
URL | http://arxiv.org/abs/1802.05187v2 |
http://arxiv.org/pdf/1802.05187v2.pdf | |
PWC | https://paperswithcode.com/paper/on-the-blindspots-of-convolutional-networks |
Repo | |
Framework | |
Socially Guided Intrinsic Motivation for Robot Learning of Motor Skills
Title | Socially Guided Intrinsic Motivation for Robot Learning of Motor Skills |
Authors | Sao Mai Nguyen, Pierre-Yves Oudeyer |
Abstract | This paper presents a technical approach to robot learning of motor skills which combines active intrinsically motivated learning with imitation learning. Our architecture, called SGIM-D, allows efficient learning of high-dimensional continuous sensorimotor inverse models in robots, and in particular learns distributions of parameterised motor policies that solve a corresponding distribution of parameterised goals/tasks. This is made possible by the technical integration of imitation learning techniques within an algorithm for learning inverse models that relies on active goal babbling. After reviewing social learning and intrinsic motivation approaches to action learning, we describe the general framework of our algorithm, before detailing its architecture. In an experiment where a robot arm has to learn to use a flexible fishing line , we illustrate that SGIM-D efficiently combines the advantages of social learning and intrinsic motivation and benefits from human demonstration properties to learn how to produce varied outcomes in the environment, while developing more precise control policies in large spaces. |
Tasks | Imitation Learning |
Published | 2018-04-19 |
URL | http://arxiv.org/abs/1804.07269v1 |
http://arxiv.org/pdf/1804.07269v1.pdf | |
PWC | https://paperswithcode.com/paper/socially-guided-intrinsic-motivation-for |
Repo | |
Framework | |
Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
Title | Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator |
Authors | Makoto Yamada, Denny Wu, Yao-Hung Hubert Tsai, Ichiro Takeuchi, Ruslan Salakhutdinov, Kenji Fukumizu |
Abstract | Measuring divergence between two distributions is essential in machine learning and statistics and has various applications including binary classification, change point detection, and two-sample test. Furthermore, in the era of big data, designing divergence measure that is interpretable and can handle high-dimensional and complex data becomes extremely important. In the paper, we propose a post selection inference (PSI) framework for divergence measure, which can select a set of statistically significant features that discriminate two distributions. Specifically, we employ an additive variant of maximum mean discrepancy (MMD) for features and introduce a general hypothesis test for PSI. A novel MMD estimator using the incomplete U-statistics, which has an asymptotically Normal distribution (under mild assumptions) and gives high detection power in PSI, is also proposed and analyzed theoretically. Through synthetic and real-world feature selection experiments, we show that the proposed framework can successfully detect statistically significant features. Last, we propose a sample selection framework for analyzing different members in the Generative Adversarial Networks (GANs) family. |
Tasks | Change Point Detection, Feature Selection |
Published | 2018-02-17 |
URL | http://arxiv.org/abs/1802.06226v1 |
http://arxiv.org/pdf/1802.06226v1.pdf | |
PWC | https://paperswithcode.com/paper/post-selection-inference-with-incomplete |
Repo | |
Framework | |
Effective extractive summarization using frequency-filtered entity relationship graphs
Title | Effective extractive summarization using frequency-filtered entity relationship graphs |
Authors | Archit Sakhadeo, Nisheeth Srivastava |
Abstract | Word frequency-based methods for extractive summarization are easy to implement and yield reasonable results across languages. However, they have significant limitations - they ignore the role of context, they offer uneven coverage of topics in a document, and sometimes are disjointed and hard to read. We use a simple premise from linguistic typology - that English sentences are complete descriptors of potential interactions between entities, usually in the order subject-verb-object - to address a subset of these difficulties. We have developed a hybrid model of extractive summarization that combines word-frequency based keyword identification with information from automatically generated entity relationship graphs to select sentences for summaries. Comparative evaluation with word-frequency and topic word-based methods shows that the proposed method is competitive by conventional ROUGE standards, and yields moderately more informative summaries on average, as assessed by a large panel (N=94) of human raters. |
Tasks | |
Published | 2018-10-24 |
URL | http://arxiv.org/abs/1810.10419v1 |
http://arxiv.org/pdf/1810.10419v1.pdf | |
PWC | https://paperswithcode.com/paper/effective-extractive-summarization-using |
Repo | |
Framework | |
An Introduction to Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications
Title | An Introduction to Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications |
Authors | Hyeryung Jang, Osvaldo Simeone, Brian Gardner, André Grüning |
Abstract | Spiking Neural Networks (SNNs) are distributed trainable systems whose computing elements, or neurons, are characterized by internal analog dynamics and by digital and sparse synaptic communications. The sparsity of the synaptic spiking inputs and the corresponding event-driven nature of neural processing can be leveraged by hardware implementations that have demonstrated significant energy reductions as compared to conventional Artificial Neural Networks (ANNs). Most existing training algorithms for SNNs have been designed either for biological plausibility or through conversion from pre-trained ANNs via rate encoding. This paper aims at providing an introduction to SNNs by focusing on a probabilistic signal processing methodology that enables the direct derivation of learning rules leveraging the unique time encoding capabilities of SNNs. To this end, the paper adopts discrete-time probabilistic models for networked spiking neurons, and it derives supervised and unsupervised learning rules from first principles by using variational inference. Examples and open research problems are also provided. |
Tasks | |
Published | 2018-12-10 |
URL | https://arxiv.org/abs/1812.03929v5 |
https://arxiv.org/pdf/1812.03929v5.pdf | |
PWC | https://paperswithcode.com/paper/spiking-neural-networks-a-stochastic-signal |
Repo | |
Framework | |
How to Maximize the Spread of Social Influence: A Survey
Title | How to Maximize the Spread of Social Influence: A Survey |
Authors | Giuseppe De Nittis, Nicola Gatti |
Abstract | This survey presents the main results achieved for the influence maximization problem in social networks. This problem is well studied in the literature and, thanks to its recent applications, some of which currently deployed on the field, it is receiving more and more attention in the scientific community. The problem can be formulated as follows: given a graph, with each node having a certain probability of influencing its neighbors, select a subset of vertices so that the number of nodes in the network that are influenced is maximized. Starting from this model, we introduce the main theoretical developments and computational results that have been achieved, taking into account different diffusion models describing how the information spreads throughout the network, various ways in which the sources of information could be placed, and how to tackle the problem in the presence of uncertainties affecting the network. Finally, we present one of the main application that has been developed and deployed exploiting tools and techniques previously discussed. |
Tasks | |
Published | 2018-06-19 |
URL | http://arxiv.org/abs/1806.07757v1 |
http://arxiv.org/pdf/1806.07757v1.pdf | |
PWC | https://paperswithcode.com/paper/how-to-maximize-the-spread-of-social |
Repo | |
Framework | |