July 27, 2019

2800 words 14 mins read

Paper Group ANR 508

Hierarchical Symbolic Dynamic Filtering of Streaming Non-stationary Time Series Data. Continuous Authentication Using One-class Classifiers and their Fusion. A Novel VHR Image Change Detection Algorithm Based on Image Fusion and Fuzzy C-Means Clustering. Beyond similarity assessment: Selecting the optimal model for sequence alignment via the Factor …

Hierarchical Symbolic Dynamic Filtering of Streaming Non-stationary Time Series Data


Title	Hierarchical Symbolic Dynamic Filtering of Streaming Non-stationary Time Series Data
Authors	Adedotun Akintayo, Soumik Sarkar
Abstract	This paper proposes a hierarchical feature extractor for non-stationary streaming time series based on the concept of switching observable Markov chain models. The slow time-scale non-stationary behaviors are considered to be a mixture of quasi-stationary fast time-scale segments that are exhibited by complex dynamical systems. The idea is to model each unique stationary characteristic without a priori knowledge (e.g., number of possible unique characteristics) at a lower logical level, and capture the transitions from one low-level model to another at a higher level. In this context, the concepts in the recently developed Symbolic Dynamic Filtering (SDF) is extended, to build an online algorithm suited for handling quasi-stationary data at a lower level and a non-stationary behavior at a higher level without a priori knowledge. A key observation made in this study is that the rate of change of data likelihood seems to be a better indicator of change in data characteristics compared to the traditional methods that mostly consider data likelihood for change detection. The algorithm minimizes model complexity and captures data likelihood. Efficacy demonstration and comparative evaluation of the proposed algorithm are performed using time series data simulated from systems that exhibit nonlinear dynamics. We discuss results that show that the proposed hierarchical SDF algorithm can identify underlying features with significantly high degree of accuracy, even under very noisy conditions. Algorithm is demonstrated to perform better than the baseline Hierarchical Dirichlet Process-Hidden Markov Models (HDP-HMM). The low computational complexity of algorithm makes it suitable for on-board, real time operations.
Tasks	Time Series
Published	2017-02-06
URL	http://arxiv.org/abs/1702.01811v1
PDF	http://arxiv.org/pdf/1702.01811v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-symbolic-dynamic-filtering-of
Repo
Framework

Continuous Authentication Using One-class Classifiers and their Fusion


Title	Continuous Authentication Using One-class Classifiers and their Fusion
Authors	Rajesh Kumar, Partha Pratim Kundu, Vir V. Phoha
Abstract	While developing continuous authentication systems (CAS), we generally assume that samples from both genuine and impostor classes are readily available. However, the assumption may not be true in certain circumstances. Therefore, we explore the possibility of implementing CAS using only genuine samples. Specifically, we investigate the usefulness of four one-class classifiers OCC (elliptic envelope, isolation forest, local outliers factor, and one-class support vector machines) and their fusion. The performance of these classifiers was evaluated on four distinct behavioral biometric datasets, and compared with eight multi-class classifiers (MCC). The results demonstrate that if we have sufficient training data from the genuine user the OCC, and their fusion can closely match the performance of the majority of MCC. Our findings encourage the research community to use OCC in order to build CAS as they do not require knowledge of impostor class during the enrollment process.
Tasks
Published	2017-10-30
URL	http://arxiv.org/abs/1710.11075v1
PDF	http://arxiv.org/pdf/1710.11075v1.pdf
PWC	https://paperswithcode.com/paper/continuous-authentication-using-one-class
Repo
Framework

A Novel VHR Image Change Detection Algorithm Based on Image Fusion and Fuzzy C-Means Clustering


Title	A Novel VHR Image Change Detection Algorithm Based on Image Fusion and Fuzzy C-Means Clustering
Authors	Rongcui Dong, Haoxiang Wang
Abstract	This thesis describes a study to perform change detection on Very High Resolution satellite images using image fusion based on 2D Discrete Wavelet Transform and Fuzzy C-Means clustering algorithm. Multiple other methods are also quantitatively and qualitatively compared in this study.
Tasks
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07157v1
PDF	http://arxiv.org/pdf/1706.07157v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-vhr-image-change-detection-algorithm
Repo
Framework

Beyond similarity assessment: Selecting the optimal model for sequence alignment via the Factorized Asymptotic Bayesian algorithm


Title	Beyond similarity assessment: Selecting the optimal model for sequence alignment via the Factorized Asymptotic Bayesian algorithm
Authors	Taikai Takeda, Michiaki Hamada
Abstract	Pair Hidden Markov Models (PHMMs) are probabilistic models used for pairwise sequence alignment, a quintessential problem in bioinformatics. PHMMs include three types of hidden states: match, insertion and deletion. Most previous studies have used one or two hidden states for each PHMM state type. However, few studies have examined the number of states suitable for representing sequence data or improving alignment accuracy.We developed a novel method to select superior models (including the number of hidden states) for PHMM. Our method selects models with the highest posterior probability using Factorized Information Criteria (FIC), which is widely utilised in model selection for probabilistic models with hidden variables. Our simulations indicated this method has excellent model selection capabilities with slightly improved alignment accuracy. We applied our method to DNA datasets from 5 and 28 species, ultimately selecting more complex models than those used in previous studies.
Tasks	Model Selection
Published	2017-05-19
URL	http://arxiv.org/abs/1705.06911v2
PDF	http://arxiv.org/pdf/1705.06911v2.pdf
PWC	https://paperswithcode.com/paper/beyond-similarity-assessment-selecting-the
Repo
Framework

ToPs: Ensemble Learning with Trees of Predictors


Title	ToPs: Ensemble Learning with Trees of Predictors
Authors	Jinsung Yoon, William R. Zame, Mihaela van der Schaar
Abstract	We present a new approach to ensemble learning. Our approach constructs a tree of subsets of the feature space and associates a predictor (predictive model) - determined by training one of a given family of base learners on an endogenously determined training set - to each node of the tree; we call the resulting object a tree of predictors. The (locally) optimal tree of predictors is derived recursively; each step involves jointly optimizing the split of the terminal nodes of the previous tree and the choice of learner and training set (hence predictor) for each set in the split. The feature vector of a new instance determines a unique path through the optimal tree of predictors; the final prediction aggregates the predictions of the predictors along this path. We derive loss bounds for the final predictor in terms of the Rademacher complexity of the base learners. We report the results of a number of experiments on a variety of datasets, showing that our approach provides statistically significant improvements over state-of-the-art machine learning algorithms, including various ensemble learning methods. Our approach works because it allows us to endogenously create more complex learners - when needed - and endogenously match both the learner and the training set to the characteristics of the dataset while still avoiding over-fitting.
Tasks
Published	2017-06-05
URL	http://arxiv.org/abs/1706.01396v2
PDF	http://arxiv.org/pdf/1706.01396v2.pdf
PWC	https://paperswithcode.com/paper/tops-ensemble-learning-with-trees-of
Repo
Framework

Graph Convolutional Encoders for Syntax-aware Neural Machine Translation


Title	Graph Convolutional Encoders for Syntax-aware Neural Machine Translation
Authors	Joost Bastings, Ivan Titov, Wilker Aziz, Diego Marcheggiani, Khalil Sima’an
Abstract	We present a simple and effective approach to incorporating syntactic structure into neural attention-based encoder-decoder models for machine translation. We rely on graph-convolutional networks (GCNs), a recent class of neural networks developed for modeling graph-structured data. Our GCNs use predicted syntactic dependency trees of source sentences to produce representations of words (i.e. hidden states of the encoder) that are sensitive to their syntactic neighborhoods. GCNs take word representations as input and produce word representations as output, so they can easily be incorporated as layers into standard encoders (e.g., on top of bidirectional RNNs or convolutional neural networks). We evaluate their effectiveness with English-German and English-Czech translation experiments for different types of encoders and observe substantial improvements over their syntax-agnostic versions in all the considered setups.
Tasks	Machine Translation
Published	2017-04-15
URL	http://arxiv.org/abs/1704.04675v3
PDF	http://arxiv.org/pdf/1704.04675v3.pdf
PWC	https://paperswithcode.com/paper/graph-convolutional-encoders-for-syntax-aware
Repo
Framework

Energy-Based Spherical Sparse Coding


Title	Energy-Based Spherical Sparse Coding
Authors	Bailey Kong, Charless C. Fowlkes
Abstract	In this paper, we explore an efficient variant of convolutional sparse coding with unit norm code vectors where reconstruction quality is evaluated using an inner product (cosine distance). To use these codes for discriminative classification, we describe a model we term Energy-Based Spherical Sparse Coding (EB-SSC) in which the hypothesized class label introduces a learned linear bias into the coding step. We evaluate and visualize performance of stacking this encoder to make a deep layered model for image classification.
Tasks	Image Classification
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01820v1
PDF	http://arxiv.org/pdf/1710.01820v1.pdf
PWC	https://paperswithcode.com/paper/energy-based-spherical-sparse-coding
Repo
Framework

Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017)


Title	Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017)
Authors	Been Kim, Dmitry M. Malioutov, Kush R. Varshney, Adrian Weller
Abstract	This is the Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017), which was held in Sydney, Australia, August 10, 2017. Invited speakers were Tony Jebara, Pang Wei Koh, and David Sontag.
Tasks
Published	2017-08-08
URL	http://arxiv.org/abs/1708.02666v1
PDF	http://arxiv.org/pdf/1708.02666v1.pdf
PWC	https://paperswithcode.com/paper/proceedings-of-the-2017-icml-workshop-on
Repo
Framework

Manifold regularization based on Nystr{ö}m type subsampling


Title	Manifold regularization based on Nystr{ö}m type subsampling
Authors	Abhishake Rastogi, Sivananthan Sampath
Abstract	In this paper, we study the Nystr{"o}m type subsampling for large scale kernel methods to reduce the computational complexities of big data. We discuss the multi-penalty regularization scheme based on Nystr{"o}m type subsampling which is motivated from well-studied manifold regularization schemes. We develop a theoretical analysis of multi-penalty least-square regularization scheme under the general source condition in vector-valued function setting, therefore the results can also be applied to multi-task learning problems. We achieve the optimal minimax convergence rates of multi-penalty regularization using the concept of effective dimension for the appropriate subsampling size. We discuss an aggregation approach based on linear function strategy to combine various Nystr{"o}m approximants. Finally, we demonstrate the performance of multi-penalty regularization based on Nystr{"o}m type subsampling on Caltech-101 data set for multi-class image classification and NSL-KDD benchmark data set for intrusion detection problem.
Tasks	Image Classification, Intrusion Detection, Multi-Task Learning
Published	2017-10-13
URL	http://arxiv.org/abs/1710.04872v1
PDF	http://arxiv.org/pdf/1710.04872v1.pdf
PWC	https://paperswithcode.com/paper/manifold-regularization-based-on-nystrom-type
Repo
Framework

Part-based Deep Hashing for Large-scale Person Re-identification


Title	Part-based Deep Hashing for Large-scale Person Re-identification
Authors	Fuqing Zhu, Xiangwei Kong, Liang Zheng, Haiyan Fu, Qi Tian
Abstract	Large-scale is a trend in person re-identification (re-id). It is important that real-time search be performed in a large gallery. While previous methods mostly focus on discriminative learning, this paper makes the attempt in integrating deep learning and hashing into one framework to evaluate the efficiency and accuracy for large-scale person re-id. We integrate spatial information for discriminative visual representation by partitioning the pedestrian image into horizontal parts. Specifically, Part-based Deep Hashing (PDH) is proposed, in which batches of triplet samples are employed as the input of the deep hashing architecture. Each triplet sample contains two pedestrian images (or parts) with the same identity and one pedestrian image (or part) of the different identity. A triplet loss function is employed with a constraint that the Hamming distance of pedestrian images (or parts) with the same identity is smaller than ones with the different identity. In the experiment, we show that the proposed Part-based Deep Hashing method yields very competitive re-id accuracy on the large-scale Market-1501 and Market-1501+500K datasets.
Tasks	Large-Scale Person Re-Identification, Person Re-Identification
Published	2017-05-05
URL	http://arxiv.org/abs/1705.02145v1
PDF	http://arxiv.org/pdf/1705.02145v1.pdf
PWC	https://paperswithcode.com/paper/part-based-deep-hashing-for-large-scale
Repo
Framework

Combining learned and analytical models for predicting action effects


Title	Combining learned and analytical models for predicting action effects
Authors	Alina Kloss, Stefan Schaal, Jeannette Bohg
Abstract	One of the most basic skills a robot should possess is predicting the effect of physical interactions with objects in the environment. This enables optimal action selection to reach a certain goal state. Traditionally, dynamics are approximated by physics-based analytical models. These models rely on specific state representations that may be hard to obtain from raw sensory data, especially if no knowledge of the object shape is assumed. More recently, we have seen learning approaches that can predict the effect of complex physical interactions directly from sensory input. It is however an open question how far these models generalize beyond their training data. In this work, we investigate the advantages and limitations of neural network based learning approaches for predicting the effects of actions based on sensory input and show how analytical and learned models can be combined to leverage the best of both worlds. As physical interaction task, we use planar pushing, for which there exists a well-known analytical model and a large real-world dataset. We propose to use a convolutional neural network to convert raw depth images or organized point clouds into a suitable representation for the analytical model and compare this approach to using neural networks for both, perception and prediction. A systematic evaluation of the proposed approach on a very large real-world dataset shows two main advantages of the hybrid architecture. Compared to a pure neural network, it significantly (i) reduces required training data and (ii) improves generalization to novel physical interaction.
Tasks
Published	2017-10-11
URL	http://arxiv.org/abs/1710.04102v3
PDF	http://arxiv.org/pdf/1710.04102v3.pdf
PWC	https://paperswithcode.com/paper/combining-learned-and-analytical-models-for
Repo
Framework

Optimizing PID parameters with machine learning


Title	Optimizing PID parameters with machine learning
Authors	Adam Nyberg
Abstract	This paper examines the Evolutionary programming (EP) method for optimizing PID parameters. PID is the most common type of regulator within control theory, partly because it’s relatively simple and yields stable results for most applications. The p, i and d parameters vary for each application; therefore, choosing the right parameters is crucial for obtaining good results but also somewhat difficult. EP is a derivative-free optimization algorithm which makes it suitable for PID optimization. The experiments in this paper demonstrate the power of EP to solve the problem of optimizing PID parameters without getting stuck in local minimums.
Tasks
Published	2017-09-26
URL	http://arxiv.org/abs/1709.09227v1
PDF	http://arxiv.org/pdf/1709.09227v1.pdf
PWC	https://paperswithcode.com/paper/optimizing-pid-parameters-with-machine
Repo
Framework

Deep Patch Learning for Weakly Supervised Object Classification and Discovery


Title	Deep Patch Learning for Weakly Supervised Object Classification and Discovery
Authors	Peng Tang, Xinggang Wang, Zilong Huang, Xiang Bai, Wenyu Liu
Abstract	Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background. Many existing methods usually require fine-grained supervisions (e.g., bounding-box annotations) to learn patch features, which requires a great effort to label images may limit their potential applications. In this paper, we propose to learn patch features via weak supervisions, i.e., only image-level supervisions. To achieve this goal, we treat images as bags and patches as instances to integrate the weakly supervised multiple instance learning constraints into deep neural networks. Also, our method integrates the traditional multiple stages of weakly supervised object classification and discovery into a unified deep convolutional neural network and optimizes the network in an end-to-end way. The network processes the two tasks object classification and discovery jointly, and shares hierarchical deep features. Through this jointly learning strategy, weakly supervised object classification and discovery are beneficial to each other. We test the proposed method on the challenging PASCAL VOC datasets. The results show that our method can obtain state-of-the-art performance on object classification, and very competitive results on object discovery, with faster testing speed than competitors.
Tasks	Multiple Instance Learning, Object Classification
Published	2017-05-06
URL	http://arxiv.org/abs/1705.02429v1
PDF	http://arxiv.org/pdf/1705.02429v1.pdf
PWC	https://paperswithcode.com/paper/deep-patch-learning-for-weakly-supervised
Repo
Framework

AI Safety and Reproducibility: Establishing Robust Foundations for the Neuropsychology of Human Values


Title	AI Safety and Reproducibility: Establishing Robust Foundations for the Neuropsychology of Human Values
Authors	Gopal P. Sarma, Nick J. Hay, Adam Safron
Abstract	We propose the creation of a systematic effort to identify and replicate key findings in neuropsychology and allied fields related to understanding human values. Our aim is to ensure that research underpinning the value alignment problem of artificial intelligence has been sufficiently validated to play a role in the design of AI systems.
Tasks
Published	2017-12-08
URL	http://arxiv.org/abs/1712.04307v3
PDF	http://arxiv.org/pdf/1712.04307v3.pdf
PWC	https://paperswithcode.com/paper/ai-safety-and-reproducibility-establishing
Repo
Framework

Action Representation Using Classifier Decision Boundaries


Title	Action Representation Using Classifier Decision Boundaries
Authors	Jue Wang, Anoop Cherian, Fatih Porikli, Stephen Gould
Abstract	Most popular deep learning based models for action recognition are designed to generate separate predictions within their short temporal windows, which are often aggregated by heuristic means to assign an action label to the full video segment. Given that not all frames from a video characterize the underlying action, pooling schemes that impose equal importance to all frames might be unfavorable. In an attempt towards tackling this challenge, we propose a novel pooling scheme, dubbed SVM pooling, based on the notion that among the bag of features generated by a CNN on all temporal windows, there is at least one feature that characterizes the action. To this end, we learn a decision hyperplane that separates this unknown yet useful feature from the rest. Applying multiple instance learning in an SVM setup, we use the parameters of this separating hyperplane as a descriptor for the video. Since these parameters are directly related to the support vectors in a max-margin framework, they serve as robust representations for pooling of the CNN features. We devise a joint optimization objective and an efficient solver that learns these hyperplanes per video and the corresponding action classifiers over the hyperplanes. Showcased experiments on the standard HMDB and UCF101 datasets demonstrate state-of-the-art performance.
Tasks	Multiple Instance Learning, Temporal Action Localization
Published	2017-04-06
URL	http://arxiv.org/abs/1704.01716v1
PDF	http://arxiv.org/pdf/1704.01716v1.pdf
PWC	https://paperswithcode.com/paper/action-representation-using-classifier
Repo
Framework