May 5, 2019

2778 words 14 mins read

Paper Group ANR 510

On the Relationship between Online Gaussian Process Regression and Kernel Least Mean Squares Algorithms. Classification of Neurological Gait Disorders Using Multi-task Feature Learning. Applying Deep Learning to the Newsvendor Problem. Predicting First Impressions with Deep Learning. Generating captions without looking beyond objects. SPiKeS: Super …

On the Relationship between Online Gaussian Process Regression and Kernel Least Mean Squares Algorithms


Title	On the Relationship between Online Gaussian Process Regression and Kernel Least Mean Squares Algorithms
Authors	Steven Van Vaerenbergh, Jesus Fernandez-Bes, Víctor Elvira
Abstract	We study the relationship between online Gaussian process (GP) regression and kernel least mean squares (KLMS) algorithms. While the latter have no capacity of storing the entire posterior distribution during online learning, we discover that their operation corresponds to the assumption of a fixed posterior covariance that follows a simple parametric model. Interestingly, several well-known KLMS algorithms correspond to specific cases of this model. The probabilistic perspective allows us to understand how each of them handles uncertainty, which could explain some of their performance differences.
Tasks
Published	2016-09-11
URL	http://arxiv.org/abs/1609.03164v1
PDF	http://arxiv.org/pdf/1609.03164v1.pdf
PWC	https://paperswithcode.com/paper/on-the-relationship-between-online-gaussian
Repo
Framework

Classification of Neurological Gait Disorders Using Multi-task Feature Learning


Title	Classification of Neurological Gait Disorders Using Multi-task Feature Learning
Authors	Ioannis Papavasileiou, Wenlong Zhang, Xin Wang, Jinbo Bi, Li Zhang, Song Han
Abstract	As our population ages, neurological impairments and degeneration of the musculoskeletal system yield gait abnormalities, which can significantly reduce quality of life. Gait rehabilitative therapy has been widely adopted to help patients maximize community participation and living independence. To further improve the precision and efficiency of rehabilitative therapy, more objective methods need to be developed based on sensory data. In this paper, an algorithmic framework is proposed to provide classification of gait disorders caused by two common neurological diseases, stroke and Parkinson’s Disease (PD), from ground contact force (GCF) data. An advanced machine learning method, multi-task feature learning (MTFL), is used to jointly train classification models of a subject’s gait in three classes, post-stroke, PD and healthy gait. Gait parameters related to mobility, balance, strength and rhythm are used as features for the classification. Out of all the features used, the MTFL models capture the more important ones per disease, which will help provide better objective assessment and therapy progress tracking. To evaluate the proposed methodology we use data from a human participant study, which includes five PD patients, three post-stroke patients, and three healthy subjects. Despite the diversity of abnormalities, the evaluation shows that the proposed approach can successfully distinguish post-stroke and PD gait from healthy gait, as well as post-stroke from PD gait, with Area Under the Curve (AUC) score of at least 0.96. Moreover, the methodology helps select important gait features to better understand the key characteristics that distinguish abnormal gaits and design personalized treatment.
Tasks
Published	2016-12-08
URL	http://arxiv.org/abs/1612.02562v3
PDF	http://arxiv.org/pdf/1612.02562v3.pdf
PWC	https://paperswithcode.com/paper/classification-of-neurological-gait-disorders
Repo
Framework

Applying Deep Learning to the Newsvendor Problem


Title	Applying Deep Learning to the Newsvendor Problem
Authors	Afshin Oroojlooyjadid, Lawrence Snyder, Martin Takáč
Abstract	The newsvendor problem is one of the most basic and widely applied inventory models. There are numerous extensions of this problem. If the probability distribution of the demand is known, the problem can be solved analytically. However, approximating the probability distribution is not easy and is prone to error; therefore, the resulting solution to the newsvendor problem may be not optimal. To address this issue, we propose an algorithm based on deep learning that optimizes the order quantities for all products based on features of the demand data. Our algorithm integrates the forecasting and inventory-optimization steps, rather than solving them separately, as is typically done, and does not require knowledge of the probability distributions of the demand. Numerical experiments on real-world data suggest that our algorithm outperforms other approaches, including data-driven and machine learning approaches, especially for demands with high volatility. Finally, in order to show how this approach can be used for other inventory optimization problems, we provide an extension for (r,Q) policies.
Tasks
Published	2016-07-07
URL	http://arxiv.org/abs/1607.02177v4
PDF	http://arxiv.org/pdf/1607.02177v4.pdf
PWC	https://paperswithcode.com/paper/applying-deep-learning-to-the-newsvendor
Repo
Framework

Predicting First Impressions with Deep Learning


Title	Predicting First Impressions with Deep Learning
Authors	Mel McCurrie, Fernando Beletti, Lucas Parzianello, Allen Westendorp, Samuel Anthony, Walter Scheirer
Abstract	Describable visual facial attributes are now commonplace in human biometrics and affective computing, with existing algorithms even reaching a sufficient point of maturity for placement into commercial products. These algorithms model objective facets of facial appearance, such as hair and eye color, expression, and aspects of the geometry of the face. A natural extension, which has not been studied to any great extent thus far, is the ability to model subjective attributes that are assigned to a face based purely on visual judgements. For instance, with just a glance, our first impression of a face may lead us to believe that a person is smart, worthy of our trust, and perhaps even our admiration - regardless of the underlying truth behind such attributes. Psychologists believe that these judgements are based on a variety of factors such as emotional states, personality traits, and other physiognomic cues. But work in this direction leads to an interesting question: how do we create models for problems where there is no ground truth, only measurable behavior? In this paper, we introduce a new convolutional neural network-based regression framework that allows us to train predictive models of crowd behavior for social attribute assignment. Over images from the AFLW face database, these models demonstrate strong correlations with human crowd ratings.
Tasks
Published	2016-10-25
URL	http://arxiv.org/abs/1610.08119v2
PDF	http://arxiv.org/pdf/1610.08119v2.pdf
PWC	https://paperswithcode.com/paper/predicting-first-impressions-with-deep
Repo
Framework

Generating captions without looking beyond objects


Title	Generating captions without looking beyond objects
Authors	Hendrik Heuer, Christof Monz, Arnold W. M. Smeulders
Abstract	This paper explores new evaluation perspectives for image captioning and introduces a noun translation task that achieves comparative image caption generation performance by translating from a set of nouns to captions. This implies that in image captioning, all word categories other than nouns can be evoked by a powerful language model without sacrificing performance on n-gram precision. The paper also investigates lower and upper bounds of how much individual word categories in the captions contribute to the final BLEU score. A large possible improvement exists for nouns, verbs, and prepositions.
Tasks	Image Captioning, Language Modelling
Published	2016-10-12
URL	http://arxiv.org/abs/1610.03708v2
PDF	http://arxiv.org/pdf/1610.03708v2.pdf
PWC	https://paperswithcode.com/paper/generating-captions-without-looking-beyond
Repo
Framework

SPiKeS: Superpixel-Keypoints Structure for Robust Visual Tracking


Title	SPiKeS: Superpixel-Keypoints Structure for Robust Visual Tracking
Authors	François-Xavier Derue, Guillaume-Alexandre Bilodeau, Robert Bergevin
Abstract	In visual tracking, part-based trackers are attractive since they are robust against occlusion and deformation. However, a part represented by a rectangular patch does not account for the shape of the target, while a superpixel does thanks to its boundary evidence. Nevertheless, tracking superpixels is difficult due to their lack of discriminative power. Therefore, to enable superpixels to be tracked discriminatively as object parts, we propose to enhance them with keypoints. By combining properties of these two features, we build a novel element designated as a Superpixel-Keypoints structure (SPiKeS). Being discriminative, these new object parts can be located efficiently by a simple nearest neighbor matching process. Then, in a tracking process, each match votes for the target’s center to give its location. In addition, the interesting properties of our new feature allows the development of an efficient model update for more robust tracking. According to experimental results, our SPiKeS-based tracker proves to be robust in many challenging scenarios by performing favorably against the state-of-the-art.
Tasks	Visual Tracking
Published	2016-10-23
URL	http://arxiv.org/abs/1610.07238v1
PDF	http://arxiv.org/pdf/1610.07238v1.pdf
PWC	https://paperswithcode.com/paper/spikes-superpixel-keypoints-structure-for
Repo
Framework

Meta-Unsupervised-Learning: A supervised approach to unsupervised learning


Title	Meta-Unsupervised-Learning: A supervised approach to unsupervised learning
Authors	Vikas K. Garg, Adam Tauman Kalai
Abstract	We introduce a new paradigm to investigate unsupervised learning, reducing unsupervised learning to supervised learning. Specifically, we mitigate the subjectivity in unsupervised decision-making by leveraging knowledge acquired from prior, possibly heterogeneous, supervised learning tasks. We demonstrate the versatility of our framework via comprehensive expositions and detailed experiments on several unsupervised problems such as (a) clustering, (b) outlier detection, and (c) similarity prediction under a common umbrella of meta-unsupervised-learning. We also provide rigorous PAC-agnostic bounds to establish the theoretical foundations of our framework, and show that our framing of meta-clustering circumvents Kleinberg’s impossibility theorem for clustering.
Tasks	Decision Making, Outlier Detection
Published	2016-12-29
URL	http://arxiv.org/abs/1612.09030v2
PDF	http://arxiv.org/pdf/1612.09030v2.pdf
PWC	https://paperswithcode.com/paper/meta-unsupervised-learning-a-supervised
Repo
Framework

Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection


Title	Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection
Authors	Mahdyar Ravanbakhsh, Moin Nabi, Hossein Mousavi, Enver Sangineto, Nicu Sebe
Abstract	Most of the crowd abnormal event detection methods rely on complex hand-crafted features to represent the crowd motion and appearance. Convolutional Neural Networks (CNN) have shown to be a powerful tool with excellent representational capacities, which can leverage the need for hand-crafted features. In this paper, we show that keeping track of the changes in the CNN feature across time can facilitate capturing the local abnormality. We specifically propose a novel measure-based method which allows measuring the local abnormality in a video by combining semantic information (inherited from existing CNN models) with low-level Optical-Flow. One of the advantage of this method is that it can be used without the fine-tuning costs. The proposed method is validated on challenging abnormality detection datasets and the results show the superiority of our method compared to the state-of-the-art methods.
Tasks	Anomaly Detection, Optical Flow Estimation
Published	2016-10-02
URL	http://arxiv.org/abs/1610.00307v3
PDF	http://arxiv.org/pdf/1610.00307v3.pdf
PWC	https://paperswithcode.com/paper/plug-and-play-cnn-for-crowd-motion-analysis
Repo
Framework

Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking


Title	Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
Authors	Martin Danelljan, Andreas Robinson, Fahad Shahbaz Khan, Michael Felsberg
Abstract	Discriminative Correlation Filters (DCF) have demonstrated excellent performance for visual object tracking. The key to their success is the ability to efficiently exploit available negative data by including all shifted versions of a training sample. However, the underlying DCF formulation is restricted to single-resolution feature maps, significantly limiting its potential. In this paper, we go beyond the conventional DCF framework and introduce a novel formulation for training continuous convolution filters. We employ an implicit interpolation model to pose the learning problem in the continuous spatial domain. Our proposed formulation enables efficient integration of multi-resolution deep feature maps, leading to superior results on three object tracking benchmarks: OTB-2015 (+5.1% in mean OP), Temple-Color (+4.6% in mean OP), and VOT2015 (20% relative reduction in failure rate). Additionally, our approach is capable of sub-pixel localization, crucial for the task of accurate feature point tracking. We also demonstrate the effectiveness of our learning formulation in extensive feature point tracking experiments. Code and supplementary material are available at http://www.cvl.isy.liu.se/research/objrec/visualtracking/conttrack/index.html.
Tasks	Object Tracking, Visual Object Tracking, Visual Tracking
Published	2016-08-12
URL	http://arxiv.org/abs/1608.03773v2
PDF	http://arxiv.org/pdf/1608.03773v2.pdf
PWC	https://paperswithcode.com/paper/beyond-correlation-filters-learning
Repo
Framework

Quantum Machine Learning


Title	Quantum Machine Learning
Authors	Jacob Biamonte, Peter Wittek, Nicola Pancotti, Patrick Rebentrost, Nathan Wiebe, Seth Lloyd
Abstract	Fuelled by increasing computer power and algorithmic advances, machine learning techniques have become powerful tools for finding patterns in data. Since quantum systems produce counter-intuitive patterns believed not to be efficiently produced by classical systems, it is reasonable to postulate that quantum computers may outperform classical computers on machine learning tasks. The field of quantum machine learning explores how to devise and implement concrete quantum software that offers such advantages. Recent work has made clear that the hardware and software challenges are still considerable but has also opened paths towards solutions.
Tasks	Quantum Machine Learning
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09347v2
PDF	http://arxiv.org/pdf/1611.09347v2.pdf
PWC	https://paperswithcode.com/paper/quantum-machine-learning
Repo
Framework

Grammatical Constraints on Intra-sentential Code-Switching: From Theories to Working Models


Title	Grammatical Constraints on Intra-sentential Code-Switching: From Theories to Working Models
Authors	Gayatri Bhat, Monojit Choudhury, Kalika Bali
Abstract	We make one of the first attempts to build working models for intra-sentential code-switching based on the Equivalence-Constraint (Poplack 1980) and Matrix-Language (Myers-Scotton 1993) theories. We conduct a detailed theoretical analysis, and a small-scale empirical study of the two models for Hindi-English CS. Our analyses show that the models are neither sound nor complete. Taking insights from the errors made by the models, we propose a new model that combines features of both the theories.
Tasks
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04538v1
PDF	http://arxiv.org/pdf/1612.04538v1.pdf
PWC	https://paperswithcode.com/paper/grammatical-constraints-on-intra-sentential
Repo
Framework

Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes


Title	Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
Authors	Caglar Gulcehre, Sarath Chandar, Kyunghyun Cho, Yoshua Bengio
Abstract	We extend neural Turing machine (NTM) model into a dynamic neural Turing machine (D-NTM) by introducing a trainable memory addressing scheme. This addressing scheme maintains for each memory cell two separate vectors, content and address vectors. This allows the D-NTM to learn a wide variety of location-based addressing strategies including both linear and nonlinear ones. We implement the D-NTM with both continuous, differentiable and discrete, non-differentiable read/write mechanisms. We investigate the mechanisms and effects of learning to read and write into a memory through experiments on Facebook bAbI tasks using both a feedforward and GRUcontroller. The D-NTM is evaluated on a set of Facebook bAbI tasks and shown to outperform NTM and LSTM baselines. We have done extensive analysis of our model and different variations of NTM on bAbI task. We also provide further experimental results on sequential pMNIST, Stanford Natural Language Inference, associative recall and copy tasks.
Tasks	Natural Language Inference, Question Answering
Published	2016-06-30
URL	http://arxiv.org/abs/1607.00036v2
PDF	http://arxiv.org/pdf/1607.00036v2.pdf
PWC	https://paperswithcode.com/paper/dynamic-neural-turing-machine-with-soft-and
Repo
Framework

Delaunay Triangulation on Skeleton of Flowers for Classification


Title	Delaunay Triangulation on Skeleton of Flowers for Classification
Authors	Y H Sharath Kumar, N Vinay Kumar, D S Guru
Abstract	In this work, we propose a Triangle based approach to classify flower images. Initially, flowers are segmented using whorl based region merging segmentation. Skeleton of a flower is obtained from the segmented flower using a skeleton pruning method. The Delaunay triangulation is obtained from the endpoints and junction points detected on the skeleton. The length and angle features are extracted from the obtained Delaunay triangles and then are aggregated to represent in the form of interval-valued type data. A suitable classifier has been explored for the purpose of classification. To corroborate the efficacy of the proposed method, an experiment is conducted on our own data set of 30 classes of flowers, containing 3000 samples.
Tasks
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01828v1
PDF	http://arxiv.org/pdf/1609.01828v1.pdf
PWC	https://paperswithcode.com/paper/delaunay-triangulation-on-skeleton-of-flowers
Repo
Framework

Condensed Memory Networks for Clinical Diagnostic Inferencing


Title	Condensed Memory Networks for Clinical Diagnostic Inferencing
Authors	Aaditya Prakash, Siyuan Zhao, Sadid A. Hasan, Vivek Datla, Kathy Lee, Ashequl Qadir, Joey Liu, Oladimeji Farri
Abstract	Diagnosis of a clinical condition is a challenging task, which often requires significant medical investigation. Previous work related to diagnostic inferencing problems mostly consider multivariate observational data (e.g. physiological signals, lab tests etc.). In contrast, we explore the problem using free-text medical notes recorded in an electronic health record (EHR). Complex tasks like these can benefit from structured knowledge bases, but those are not scalable. We instead exploit raw text from Wikipedia as a knowledge source. Memory networks have been demonstrated to be effective in tasks which require comprehension of free-form text. They use the final iteration of the learned representation to predict probable classes. We introduce condensed memory neural networks (C-MemNNs), a novel model with iterative condensation of memory representations that preserves the hierarchy of features in the memory. Experiments on the MIMIC-III dataset show that the proposed model outperforms other variants of memory networks to predict the most probable diagnoses given a complex clinical scenario.
Tasks
Published	2016-12-06
URL	http://arxiv.org/abs/1612.01848v2
PDF	http://arxiv.org/pdf/1612.01848v2.pdf
PWC	https://paperswithcode.com/paper/condensed-memory-networks-for-clinical
Repo
Framework

Saliency Detection with Spaces of Background-based Distribution


Title	Saliency Detection with Spaces of Background-based Distribution
Authors	Tong Zhao, Lin Li, Xinghao Ding, Yue Huang, Delu Zeng
Abstract	In this letter, an effective image saliency detection method is proposed by constructing some novel spaces to model the background and redefine the distance of the salient patches away from the background. Concretely, given the backgroundness prior, eigendecomposition is utilized to create four spaces of background-based distribution (SBD) to model the background, in which a more appropriate metric (Mahalanobis distance) is quoted to delicately measure the saliency of every image patch away from the background. After that, a coarse saliency map is obtained by integrating the four adjusted Mahalanobis distance maps, each of which is formed by the distances between all the patches and background in the corresponding SBD. To be more discriminative, the coarse saliency map is further enhanced into the posterior probability map within Bayesian perspective. Finally, the final saliency map is generated by properly refining the posterior probability map with geodesic distance. Experimental results on two usual datasets show that the proposed method is effective compared with the state-of-the-art algorithms.
Tasks	Saliency Detection
Published	2016-03-17
URL	http://arxiv.org/abs/1603.05335v1
PDF	http://arxiv.org/pdf/1603.05335v1.pdf
PWC	https://paperswithcode.com/paper/saliency-detection-with-spaces-of-background
Repo
Framework