July 28, 2019

3255 words 16 mins read

Paper Group ANR 400

Mechanisms of dimensionality reduction and decorrelation in deep neural networks. Motion Deblurring in the Wild. Estimation of a Low-rank Topic-Based Model for Information Cascades. Development and analysis of a Bayesian water balance model for large lake systems. How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics. Atte …

Mechanisms of dimensionality reduction and decorrelation in deep neural networks


Title	Mechanisms of dimensionality reduction and decorrelation in deep neural networks
Authors	Haiping Huang
Abstract	Deep neural networks are widely used in various domains. However, the nature of computations at each layer of the deep networks is far from being well understood. Increasing the interpretability of deep neural networks is thus important. Here, we construct a mean-field framework to understand how compact representations are developed across layers, not only in deterministic deep networks with random weights but also in generative deep networks where an unsupervised learning is carried out. Our theory shows that the deep computation implements a dimensionality reduction while maintaining a finite level of weak correlations between neurons for possible feature extraction. Mechanisms of dimensionality reduction and decorrelation are unified in the same framework. This work may pave the way for understanding how a sensory hierarchy works.
Tasks	Dimensionality Reduction
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01467v3
PDF	http://arxiv.org/pdf/1710.01467v3.pdf
PWC	https://paperswithcode.com/paper/mechanisms-of-dimensionality-reduction-and
Repo
Framework

Motion Deblurring in the Wild


Title	Motion Deblurring in the Wild
Authors	Mehdi Noroozi, Paramanand Chandramouli, Paolo Favaro
Abstract	The task of image deblurring is a very ill-posed problem as both the image and the blur are unknown. Moreover, when pictures are taken in the wild, this task becomes even more challenging due to the blur varying spatially and the occlusions between the object. Due to the complexity of the general image model we propose a novel convolutional network architecture which directly generates the sharp image.This network is built in three stages, and exploits the benefits of pyramid schemes often used in blind deconvolution. One of the main difficulties in training such a network is to design a suitable dataset. While useful data can be obtained by synthetically blurring a collection of images, more realistic data must be collected in the wild. To obtain such data we use a high frame rate video camera and keep one frame as the sharp image and frame average as the corresponding blurred image. We show that this realistic dataset is key in achieving state-of-the-art performance and dealing with occlusions.
Tasks	Deblurring
Published	2017-01-05
URL	http://arxiv.org/abs/1701.01486v2
PDF	http://arxiv.org/pdf/1701.01486v2.pdf
PWC	https://paperswithcode.com/paper/motion-deblurring-in-the-wild
Repo
Framework

Estimation of a Low-rank Topic-Based Model for Information Cascades


Title	Estimation of a Low-rank Topic-Based Model for Information Cascades
Authors	Ming Yu, Varun Gupta, Mladen Kolar
Abstract	We consider the problem of estimating the latent structure of a social network based on the observed information diffusion events, or cascades, where the observations for a given cascade consist of only the timestamps of infection for infected nodes but not the source of the infection. Most of the existing work on this problem has focused on estimating a diffusion matrix without any structural assumptions on it. In this paper, we propose a novel model based on the intuition that an information is more likely to propagate among two nodes if they are interested in similar topics which are also prominent in the information content. In particular, our model endows each node with an influence vector (which measures how authoritative the node is on each topic) and a receptivity vector (which measures how susceptible the node is for each topic). We show how this node-topic structure can be estimated from the observed cascades, and prove the consistency of the estimator. Experiments on synthetic and real data demonstrate the improved performance and better interpretability of our model compared to existing state-of-the-art methods.
Tasks	Recommendation Systems
Published	2017-09-06
URL	https://arxiv.org/abs/1709.01919v3
PDF	https://arxiv.org/pdf/1709.01919v3.pdf
PWC	https://paperswithcode.com/paper/an-influence-receptivity-model-for-topic
Repo
Framework

Development and analysis of a Bayesian water balance model for large lake systems


Title	Development and analysis of a Bayesian water balance model for large lake systems
Authors	Joeseph P. Smith, Andrew D. Gronewold
Abstract	Water balance models (WBMs) are often employed to understand regional hydrologic cycles over various time scales. Most WBMs, however, are physically-based, and few employ state-of-the-art statistical methods to reconcile independent input measurement uncertainty and bias. Further, few WBMs exist for large lakes, and most large lake WBMs perform additive accounting, with minimal consideration towards input data uncertainty. Here, we introduce a framework for improving a previously developed large lake statistical water balance model (L2SWBM). Focusing on the water balances of Lakes Superior and Michigan-Huron, we demonstrate our new analytical framework, identifying L2SWBMs from 26 alternatives that adequately close the water balance of the lakes with satisfactory computation times compared with the prototype model. We expect our new framework will be used to develop water balance models for other lakes around the world.
Tasks
Published	2017-10-26
URL	http://arxiv.org/abs/1710.10161v4
PDF	http://arxiv.org/pdf/1710.10161v4.pdf
PWC	https://paperswithcode.com/paper/development-and-analysis-of-a-bayesian-water
Repo
Framework

How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics


Title	How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics
Authors	Anirudha Majumdar, Marco Pavone
Abstract	Endowing robots with the capability of assessing risk and making risk-aware decisions is widely considered a key step toward ensuring safety for robots operating under uncertainty. But, how should a robot quantify risk? A natural and common approach is to consider the framework whereby costs are assigned to stochastic outcomes - an assignment captured by a cost random variable. Quantifying risk then corresponds to evaluating a risk metric, i.e., a mapping from the cost random variable to a real number. Yet, the question of what constitutes a “good” risk metric has received little attention within the robotics community. The goal of this paper is to explore and partially address this question by advocating axioms that risk metrics in robotics applications should satisfy in order to be employed as rational assessments of risk. We discuss general representation theorems that precisely characterize the class of metrics that satisfy these axioms (referred to as distortion risk metrics), and provide instantiations that can be used in applications. We further discuss pitfalls of commonly used risk metrics in robotics, and discuss additional properties that one must consider in sequential decision making tasks. Our hope is that the ideas presented here will lead to a foundational framework for quantifying risk (and hence safety) in robotics applications.
Tasks	Decision Making
Published	2017-10-30
URL	http://arxiv.org/abs/1710.11040v2
PDF	http://arxiv.org/pdf/1710.11040v2.pdf
PWC	https://paperswithcode.com/paper/how-should-a-robot-assess-risk-towards-an
Repo
Framework

Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings


Title	Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings
Authors	Shaohui Kuang, Junhui Li, António Branco, Weihua Luo, Deyi Xiong
Abstract	In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase. Differently from statistical machine translation, the associations between source words and their possible target counterparts are not explicitly stored. Source and target words are at the two ends of a long information processing procedure, mediated by hidden states at both the source encoding and the target decoding phases. This makes it possible that a source word is incorrectly translated into a target word that is not any of its admissible equivalent counterparts in the target language. In this paper, we seek to somewhat shorten the distance between source and target words in that procedure, and thus strengthen their association, by means of a method we term bridging source and target word embeddings. We experiment with three strategies: (1) a source-side bridging model, where source word embeddings are moved one step closer to the output target sequence; (2) a target-side bridging model, which explores the more relevant source word embeddings for the prediction of the target sequence; and (3) a direct bridging model, which directly connects source and target word embeddings seeking to minimize errors in the translation of ones by the others. Experiments and analysis presented in this paper demonstrate that the proposed bridging models are able to significantly improve quality of both sentence translation, in general, and alignment and translation of individual source words with target words, in particular.
Tasks	Machine Translation, Word Embeddings
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05380v4
PDF	http://arxiv.org/pdf/1711.05380v4.pdf
PWC	https://paperswithcode.com/paper/attention-focusing-for-neural-machine
Repo
Framework

Investigating Natural Image Pleasantness Recognition using Deep Features and Eye Tracking for Loosely Controlled Human-computer Interaction


Title	Investigating Natural Image Pleasantness Recognition using Deep Features and Eye Tracking for Loosely Controlled Human-computer Interaction
Authors	Hamed R. Tavakoli, Jorma Laaksonen, Esa Rahtu
Abstract	This paper revisits recognition of natural image pleasantness by employing deep convolutional neural networks and affordable eye trackers. There exist several approaches to recognize image pleasantness: (1) computer vision, and (2) psychophysical signals. For natural images, computer vision approaches have not been as successful as for abstract paintings and is lagging behind the psychophysical signals like eye movements. Despite better results, the scalability of eye movements is adversely affected by the sensor cost. While the introduction of affordable sensors have helped the scalability issue by making the sensors more accessible, the application of such sensors in a loosely controlled human-computer interaction setup is not yet studied for affective image tagging. On the other hand, deep convolutional neural networks have boosted the performance of vision-based techniques significantly in recent years. To investigate the current status in regard to affective image tagging, we (1) introduce a new eye movement dataset using an affordable eye tracker, (2) study the use of deep neural networks for pleasantness recognition, (3) investigate the gap between deep features and eye movements. To meet these ends, we record eye movements in a less controlled setup, akin to daily human-computer interaction. We assess features from eye movements, visual features, and their combination. Our results show that (1) recognizing natural image pleasantness from eye movement under less restricted setup is difficult and previously used techniques are prone to fail, and (2) visual class categories are strong cues for predicting pleasantness, due to their correlation with emotions, necessitating careful study of this phenomenon. This latter finding is alerting as some deep learning approaches may fit to the class category bias.
Tasks	Eye Tracking
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02218v1
PDF	http://arxiv.org/pdf/1704.02218v1.pdf
PWC	https://paperswithcode.com/paper/investigating-natural-image-pleasantness
Repo
Framework

Reinforcement Learning with Analogical Similarity to Guide Schema Induction and Attention


Title	Reinforcement Learning with Analogical Similarity to Guide Schema Induction and Attention
Authors	James M. Foster, Matt Jones
Abstract	Research in analogical reasoning suggests that higher-order cognitive functions such as abstract reasoning, far transfer, and creativity are founded on recognizing structural similarities among relational systems. Here we integrate theories of analogy with the computational framework of reinforcement learning (RL). We propose a psychology theory that is a computational synergy between analogy and RL, in which analogical comparison provides the RL learning algorithm with a measure of relational similarity, and RL provides feedback signals that can drive analogical learning. Simulation results support the power of this approach.
Tasks
Published	2017-12-28
URL	http://arxiv.org/abs/1712.10070v1
PDF	http://arxiv.org/pdf/1712.10070v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-with-analogical
Repo
Framework

BubbleView: an interface for crowdsourcing image importance maps and tracking visual attention


Title	BubbleView: an interface for crowdsourcing image importance maps and tracking visual attention
Authors	Nam Wook Kim, Zoya Bylinskii, Michelle A. Borkin, Krzysztof Z. Gajos, Aude Oliva, Fredo Durand, Hanspeter Pfister
Abstract	In this paper, we present BubbleView, an alternative methodology for eye tracking using discrete mouse clicks to measure which information people consciously choose to examine. BubbleView is a mouse-contingent, moving-window interface in which participants are presented with a series of blurred images and click to reveal “bubbles” - small, circular areas of the image at original resolution, similar to having a confined area of focus like the eye fovea. Across 10 experiments with 28 different parameter combinations, we evaluated BubbleView on a variety of image types: information visualizations, natural images, static webpages, and graphic designs, and compared the clicks to eye fixations collected with eye-trackers in controlled lab settings. We found that BubbleView clicks can both (i) successfully approximate eye fixations on different images, and (ii) be used to rank image and design elements by importance. BubbleView is designed to collect clicks on static images, and works best for defined tasks such as describing the content of an information visualization or measuring image importance. BubbleView data is cleaner and more consistent than related methodologies that use continuous mouse movements. Our analyses validate the use of mouse-contingent, moving-window methodologies as approximating eye fixations for different image and task types.
Tasks	Eye Tracking
Published	2017-02-16
URL	http://arxiv.org/abs/1702.05150v3
PDF	http://arxiv.org/pdf/1702.05150v3.pdf
PWC	https://paperswithcode.com/paper/bubbleview-an-interface-for-crowdsourcing
Repo
Framework

Semiblind subgraph reconstruction in Gaussian graphical models


Title	Semiblind subgraph reconstruction in Gaussian graphical models
Authors	Tianpei Xie, Sijia Liu, Alfred O. Hero III
Abstract	Consider a social network where only a few nodes (agents) have meaningful interactions in the sense that the conditional dependency graph over node attribute variables (behaviors) is sparse. A company that can only observe the interactions between its own customers will generally not be able to accurately estimate its customers’ dependency subgraph: it is blinded to any external interactions of its customers and this blindness creates false edges in its subgraph. In this paper we address the semiblind scenario where the company has access to a noisy summary of the complementary subgraph connecting external agents, e.g., provided by a consolidator. The proposed framework applies to other applications as well, including field estimation from a network of awake and sleeping sensors and privacy-constrained information sharing over social subnetworks. We propose a penalized likelihood approach in the context of a graph signal obeying a Gaussian graphical models (GGM). We use a convex-concave iterative optimization algorithm to maximize the penalized likelihood.
Tasks
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05391v1
PDF	http://arxiv.org/pdf/1711.05391v1.pdf
PWC	https://paperswithcode.com/paper/semiblind-subgraph-reconstruction-in-gaussian
Repo
Framework

Learning a time-dependent master saliency map from eye-tracking data in videos


Title	Learning a time-dependent master saliency map from eye-tracking data in videos
Authors	Antoine Coutrot, Nathalie Guyader
Abstract	To predict the most salient regions of complex natural scenes, saliency models commonly compute several feature maps (contrast, orientation, motion…) and linearly combine them into a master saliency map. Since feature maps have different spatial distribution and amplitude dynamic ranges, determining their contributions to overall saliency remains an open problem. Most state-of-the-art models do not take time into account and give feature maps constant weights across the stimulus duration. However, visual exploration is a highly dynamic process shaped by many time-dependent factors. For instance, some systematic viewing patterns such as the center bias are known to dramatically vary across the time course of the exploration. In this paper, we use maximum likelihood and shrinkage methods to dynamically and jointly learn feature map and systematic viewing pattern weights directly from eye-tracking data recorded on videos. We show that these weights systematically vary as a function of time, and heavily depend upon the semantic visual category of the videos being processed. Our fusion method allows taking these variations into account, and outperforms other state-of-the-art fusion schemes using constant weights over time. The code, videos and eye-tracking data we used for this study are available online: http://antoinecoutrot.magix.net/public/research.html
Tasks	Eye Tracking
Published	2017-02-02
URL	http://arxiv.org/abs/1702.00714v1
PDF	http://arxiv.org/pdf/1702.00714v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-time-dependent-master-saliency-map
Repo
Framework

General problem solving with category theory


Title	General problem solving with category theory
Authors	Francisco J. Arjonilla, Tetsuya Ogata
Abstract	This paper proposes a formal cognitive framework for problem solving based on category theory. We introduce cognitive categories, which are categories with exactly one morphism between any two objects. Objects in these categories are interpreted as states and morphisms as transformations between states. Moreover, cognitive problems are reduced to the specification of two objects in a cognitive category: an outset (i.e. the current state of the system) and a goal (i.e. the desired state). Cognitive systems transform the target system by means of generators and evaluators. Generators realize cognitive operations over a system by grouping morphisms, whilst evaluators group objects as a way to generalize outsets and goals to partially defined states. Meta-cognition emerges when the whole cognitive system is self-referenced as sub-states in the cognitive category, whilst learning must always be considered as a meta-cognitive process to maintain consistency. Several examples grounded in basic AI methods are provided as well.
Tasks
Published	2017-09-14
URL	http://arxiv.org/abs/1709.04825v1
PDF	http://arxiv.org/pdf/1709.04825v1.pdf
PWC	https://paperswithcode.com/paper/general-problem-solving-with-category-theory
Repo
Framework

Adversarial Examples for Semantic Image Segmentation


Title	Adversarial Examples for Semantic Image Segmentation
Authors	Volker Fischer, Mummadi Chaithanya Kumar, Jan Hendrik Metzen, Thomas Brox
Abstract	Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this contribution, we analyse how adversarial perturbations can affect the task of semantic segmentation. We show how existing adversarial attackers can be transferred to this task and that it is possible to create imperceptible adversarial perturbations that lead a deep network to misclassify almost all pixels of a chosen class while leaving network prediction nearly unchanged outside this class.
Tasks	Image Classification, Semantic Segmentation
Published	2017-03-03
URL	http://arxiv.org/abs/1703.01101v1
PDF	http://arxiv.org/pdf/1703.01101v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-examples-for-semantic-image
Repo
Framework

Best-Effort Inductive Logic Programming via Fine-grained Cost-based Hypothesis Generation


Title	Best-Effort Inductive Logic Programming via Fine-grained Cost-based Hypothesis Generation
Authors	Peter Schüller, Mishal Benz
Abstract	We describe the Inspire system which participated in the first competition on Inductive Logic Programming (ILP). Inspire is based on Answer Set Programming (ASP). The distinguishing feature of Inspire is an ASP encoding for hypothesis space generation: given a set of facts representing the mode bias, and a set of cost configuration parameters, each answer set of this encoding represents a single rule that is considered for finding a hypothesis that entails the given examples. Compared with state-of-the-art methods that use the length of the rule body as a metric for rule complexity, our approach permits a much more fine-grained specification of the shape of hypothesis candidate rules. The Inspire system iteratively increases the rule cost limit and thereby increases the search space until it finds a suitable hypothesis. The system searches for a hypothesis that entails a single example at a time, utilizing an ASP encoding derived from the encoding used in XHAIL. We perform experiments with the development and test set of the ILP competition. For comparison we also adapted the ILASP system to process competition instances. Experimental results show that the cost parameters for the hypothesis search space are an important factor for finding hypotheses to competition instances within tight resource bounds.
Tasks
Published	2017-07-10
URL	http://arxiv.org/abs/1707.02729v2
PDF	http://arxiv.org/pdf/1707.02729v2.pdf
PWC	https://paperswithcode.com/paper/best-effort-inductive-logic-programming-via
Repo
Framework

Recognizing Abnormal Heart Sounds Using Deep Learning


Title	Recognizing Abnormal Heart Sounds Using Deep Learning
Authors	Jonathan Rubin, Rui Abreu, Anurag Ganguli, Saigopal Nelaturi, Ion Matei, Kumar Sricharan
Abstract	The work presented here applies deep learning to the task of automated cardiac auscultation, i.e. recognizing abnormalities in heart sounds. We describe an automated heart sound classification algorithm that combines the use of time-frequency heat map representations with a deep convolutional neural network (CNN). Given the cost-sensitive nature of misclassification, our CNN architecture is trained using a modified loss function that directly optimizes the trade-off between sensitivity and specificity. We evaluated our algorithm at the 2016 PhysioNet Computing in Cardiology challenge where the objective was to accurately classify normal and abnormal heart sounds from single, short, potentially noisy recordings. Our entry to the challenge achieved a final specificity of 0.95, sensitivity of 0.73 and overall score of 0.84. We achieved the greatest specificity score out of all challenge entries and, using just a single CNN, our algorithm differed in overall score by only 0.02 compared to the top place finisher, which used an ensemble approach.
Tasks
Published	2017-07-14
URL	http://arxiv.org/abs/1707.04642v2
PDF	http://arxiv.org/pdf/1707.04642v2.pdf
PWC	https://paperswithcode.com/paper/recognizing-abnormal-heart-sounds-using-deep
Repo
Framework