Paper Group ANR 247
Robust Associative Memories Naturally Occuring From Recurrent Hebbian Networks Under Noise. When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time. Toward a new approach for massive LiDAR data processing. Graph Neural Networks and Boolean Satisfiability. Robotic Tactile Perception of Object Properties: A Review. A …
Robust Associative Memories Naturally Occuring From Recurrent Hebbian Networks Under Noise
| Title | Robust Associative Memories Naturally Occuring From Recurrent Hebbian Networks Under Noise |
| Authors | Eliott Coyac, Vincent Gripon, Charlotte Langlais, Claude Berrou |
| Abstract | The brain is a noisy system subject to energy constraints. These facts are rarely taken into account when modelling artificial neural networks. In this paper, we are interested in demonstrating that those factors can actually lead to the appearance of robust associative memories. We first propose a simplified model of noise in the brain, taking into account synaptic noise and interference from neurons external to the network. When coarsely quantized, we show that this noise can be reduced to insertions and erasures. We take a neural network with recurrent modifiable connections, and subject it to noisy external inputs. We introduce an energy usage limitation principle in the network as well as consolidated Hebbian learning, resulting in an incremental processing of inputs. We show that the connections naturally formed correspond to state-of-the-art binary sparse associative memories. |
| Tasks | |
| Published | 2017-09-25 |
| URL | http://arxiv.org/abs/1709.08367v1 |
| http://arxiv.org/pdf/1709.08367v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-associative-memories-naturally |
| Repo | |
| Framework | |
When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time
| Title | When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time |
| Authors | David J. Miller, Yulia Wang, George Kesidis |
| Abstract | A significant threat to the recent, wide deployment of machine learning-based systems, including deep neural networks (DNNs), is adversarial learning attacks. We analyze possible test-time evasion-attack mechanisms and show that, in some important cases, when the image has been attacked, correctly classifying it has no utility: i) when the image to be attacked is (even arbitrarily) selected from the attacker’s cache; ii) when the sole recipient of the classifier’s decision is the attacker. Moreover, in some application domains and scenarios it is highly actionable to detect the attack irrespective of correctly classifying in the face of it (with classification still performed if no attack is detected). We hypothesize that, even if human-imperceptible, adversarial perturbations are machine-detectable. We propose a purely unsupervised anomaly detector (AD) that, unlike previous works: i) models the joint density of a deep layer using highly suitable null hypothesis density models (matched in particular to the non- negative support for RELU layers); ii) exploits multiple DNN layers; iii) leverages a “source” and “destination” class concept, source class uncertainty, the class confusion matrix, and DNN weight information in constructing a novel decision statistic grounded in the Kullback-Leibler divergence. Tested on MNIST and CIFAR-10 image databases under three prominent attack strategies, our approach outperforms previous detection methods, achieving strong ROC AUC detection accuracy on two attacks and better accuracy than recently reported for a variety of methods on the strongest (CW) attack. We also evaluate a fully white box attack on our system. Finally, we evaluate other important performance measures, such as classification accuracy, versus detection rate and attack strength. |
| Tasks | Anomaly Detection |
| Published | 2017-12-18 |
| URL | http://arxiv.org/abs/1712.06646v2 |
| http://arxiv.org/pdf/1712.06646v2.pdf | |
| PWC | https://paperswithcode.com/paper/when-not-to-classify-anomaly-detection-of |
| Repo | |
| Framework | |
Toward a new approach for massive LiDAR data processing
| Title | Toward a new approach for massive LiDAR data processing |
| Authors | V-H Cao, K-X Chu, Nhien-An Le-Khac, M-T Kechadi, Debra F. Laefer, Linh Truong-Hong |
| Abstract | Laser scanning (also known as Light Detection And Ranging) has been widely applied in various application. As part of that, aerial laser scanning (ALS) has been used to collect topographic data points for a large area, which triggers to million points to be acquired. Furthermore, today, with integrating full wareform (FWF) technology during ALS data acquisition, all return information of laser pulse is stored. Thus, ALS data are to be massive and complexity since the FWF of each laser pulse can be stored up to 256 samples and density of ALS data is also increasing significantly. Processing LiDAR data demands heavy operations and the traditional approaches require significant hardware and running time. On the other hand, researchers have recently proposed parallel approaches for analysing LiDAR data. These approaches are normally based on parallel architecture of target systems such as multi-core processors, GPU, etc. However, there is still missing efficient approaches/tools supporting the analysis of LiDAR data due to the lack of a deep study on both library tools and algorithms used in processing this data. In this paper, we present a comparative study of software libraries and algorithms to optimise the processing of LiDAR data. We also propose new method to improve this process with experiments on large LiDAR data. Finally, we discuss on a parallel solution of our approach where we integrate parallel computing in processing LiDAR data. |
| Tasks | |
| Published | 2017-04-11 |
| URL | http://arxiv.org/abs/1704.03527v1 |
| http://arxiv.org/pdf/1704.03527v1.pdf | |
| PWC | https://paperswithcode.com/paper/toward-a-new-approach-for-massive-lidar-data |
| Repo | |
| Framework | |
Graph Neural Networks and Boolean Satisfiability
| Title | Graph Neural Networks and Boolean Satisfiability |
| Authors | Benedikt Bünz, Matthew Lamm |
| Abstract | In this paper we explore whether or not deep neural architectures can learn to classify Boolean satisfiability (SAT). We devote considerable time to discussing the theoretical properties of SAT. Then, we define a graph representation for Boolean formulas in conjunctive normal form, and train neural classifiers over general graph structures called Graph Neural Networks, or GNNs, to recognize features of satisfiability. To the best of our knowledge this has never been tried before. Our preliminary findings are potentially profound. In a weakly-supervised setting, that is, without problem specific feature engineering, Graph Neural Networks can learn features of satisfiability. |
| Tasks | Feature Engineering |
| Published | 2017-02-12 |
| URL | http://arxiv.org/abs/1702.03592v1 |
| http://arxiv.org/pdf/1702.03592v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-neural-networks-and-boolean |
| Repo | |
| Framework | |
Robotic Tactile Perception of Object Properties: A Review
| Title | Robotic Tactile Perception of Object Properties: A Review |
| Authors | Shan Luo, Joao Bimbo, Ravinder Dahiya, Hongbin Liu |
| Abstract | Touch sensing can help robots understand their sur- rounding environment, and in particular the objects they interact with. To this end, roboticists have, in the last few decades, developed several tactile sensing solutions, extensively reported in the literature. Research into interpreting the conveyed tactile information has also started to attract increasing attention in recent years. However, a comprehensive study on this topic is yet to be reported. In an effort to collect and summarize the major scientific achievements in the area, this survey extensively reviews current trends in robot tactile perception of object properties. Available tactile sensing technologies are briefly presented before an extensive review on tactile recognition of object properties. The object properties that are targeted by this review are shape, surface material and object pose. The role of touch sensing in combination with other sensing sources is also discussed. In this review, open issues are identified and future directions for applying tactile sensing in different tasks are suggested. |
| Tasks | |
| Published | 2017-11-10 |
| URL | http://arxiv.org/abs/1711.03810v1 |
| http://arxiv.org/pdf/1711.03810v1.pdf | |
| PWC | https://paperswithcode.com/paper/robotic-tactile-perception-of-object |
| Repo | |
| Framework | |
A Region Based Easy Path Wavelet Transform For Sparse Image Representation
| Title | A Region Based Easy Path Wavelet Transform For Sparse Image Representation |
| Authors | Renato Budinich |
| Abstract | The Easy Path Wavelet Transform is an adaptive transform for bivariate functions (in particular natural images) which has been proposed in [1]. It provides a sparse representation by finding a path in the domain of the function leveraging the local correlations of the function values. It then applies a one dimensional wavelet transform to the obtained vector, decimates the points and iterates the procedure. The main drawback of such method is the need to store, for each level of the transform, the path which vectorizes the two dimensional data. Here we propose a variation on the method which consists of firstly applying a segmentation procedure to the function domain, partitioning it into regions where the variation in the function values is low; in a second step, inside each such region, a path is found in some deterministic way, i.e. not data-dependent. This circumvents the need to store the paths at each level, while still obtaining good quality lossy compression. This method is particularly well suited to encode a Region of Interest in the image with different quality than the rest of the image. [1] Gerlind Plonka. The easy path wavelet transform: A new adaptive wavelet transform for sparse representation of two-dimensional data. Multiscale Modeling & Simulation, 7(3):1474$-$1496, 2008. |
| Tasks | |
| Published | 2017-02-07 |
| URL | http://arxiv.org/abs/1702.01961v2 |
| http://arxiv.org/pdf/1702.01961v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-region-based-easy-path-wavelet-transform |
| Repo | |
| Framework | |
NEON+: Accelerated Gradient Methods for Extracting Negative Curvature for Non-Convex Optimization
| Title | NEON+: Accelerated Gradient Methods for Extracting Negative Curvature for Non-Convex Optimization |
| Authors | Yi Xu, Rong Jin, Tianbao Yang |
| Abstract | Accelerated gradient (AG) methods are breakthroughs in convex optimization, improving the convergence rate of the gradient descent method for optimization with smooth functions. However, the analysis of AG methods for non-convex optimization is still limited. It remains an open question whether AG methods from convex optimization can accelerate the convergence of the gradient descent method for finding local minimum of non-convex optimization problems. This paper provides an affirmative answer to this question. In particular, we analyze two renowned variants of AG methods (namely Polyak’s Heavy Ball method and Nesterov’s Accelerated Gradient method) for extracting the negative curvature from random noise, which is central to escaping from saddle points. By leveraging the proposed AG methods for extracting the negative curvature, we present a new AG algorithm with double loops for non-convex optimization~\footnote{this is in contrast to a single-loop AG algorithm proposed in a recent manuscript~\citep{AGNON}, which directly analyzed the Nesterov’s AG method for non-convex optimization and appeared online on November 29, 2017. However, we emphasize that our work is an independent work, which is inspired by our earlier work~\citep{NEON17} and is based on a different novel analysis.}, which converges to second-order stationary point $\x$ such that $\nabla f(\x)\leq \epsilon$ and $\nabla^2 f(\x)\geq -\sqrt{\epsilon} I$ with $\widetilde O(1/\epsilon^{1.75})$ iteration complexity, improving that of gradient descent method by a factor of $\epsilon^{-0.25}$ and matching the best iteration complexity of second-order Hessian-free methods for non-convex optimization. |
| Tasks | |
| Published | 2017-12-04 |
| URL | http://arxiv.org/abs/1712.01033v2 |
| http://arxiv.org/pdf/1712.01033v2.pdf | |
| PWC | https://paperswithcode.com/paper/neon-accelerated-gradient-methods-for |
| Repo | |
| Framework | |
Deep-Learning the Landscape
| Title | Deep-Learning the Landscape |
| Authors | Yang-Hui He |
| Abstract | We propose a paradigm to deep-learn the ever-expanding databases which have emerged in mathematical physics and particle phenomenology, as diverse as the statistics of string vacua or combinatorial and algebraic geometry. As concrete examples, we establish multi-layer neural networks as both classifiers and predictors and train them with a host of available data ranging from Calabi-Yau manifolds and vector bundles, to quiver representations for gauge theories. We find that even a relatively simple neural network can learn many significant quantities to astounding accuracy in a matter of minutes and can also predict hithertofore unencountered results. This paradigm should prove a valuable tool in various investigations in landscapes in physics as well as pure mathematics. |
| Tasks | |
| Published | 2017-06-08 |
| URL | http://arxiv.org/abs/1706.02714v3 |
| http://arxiv.org/pdf/1706.02714v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-the-landscape |
| Repo | |
| Framework | |
Applying Ricci Flow to High Dimensional Manifold Learning
| Title | Applying Ricci Flow to High Dimensional Manifold Learning |
| Authors | Yangyang Li, Ruqian Lu |
| Abstract | Traditional manifold learning algorithms often bear an assumption that the local neighborhood of any point on embedded manifold is roughly equal to the tangent space at that point without considering the curvature. The curvature indifferent way of manifold processing often makes traditional dimension reduction poorly neighborhood preserving. To overcome this drawback we propose a new algorithm called RF-ML to perform an operation on the manifold with help of Ricci flow before reducing the dimension of manifold. |
| Tasks | Dimensionality Reduction |
| Published | 2017-03-03 |
| URL | http://arxiv.org/abs/1703.10675v4 |
| http://arxiv.org/pdf/1703.10675v4.pdf | |
| PWC | https://paperswithcode.com/paper/applying-ricci-flow-to-high-dimensional |
| Repo | |
| Framework | |
Mixtures and products in two graphical models
| Title | Mixtures and products in two graphical models |
| Authors | Anna Seigal, Guido Montufar |
| Abstract | We compare two statistical models of three binary random variables. One is a mixture model and the other is a product of mixtures model called a restricted Boltzmann machine. Although the two models we study look different from their parametrizations, we show that they represent the same set of distributions on the interior of the probability simplex, and are equal up to closure. We give a semi-algebraic description of the model in terms of six binomial inequalities and obtain closed form expressions for the maximum likelihood estimates. We briefly discuss extensions to larger models. |
| Tasks | |
| Published | 2017-09-15 |
| URL | http://arxiv.org/abs/1709.05276v1 |
| http://arxiv.org/pdf/1709.05276v1.pdf | |
| PWC | https://paperswithcode.com/paper/mixtures-and-products-in-two-graphical-models |
| Repo | |
| Framework | |
A Tutor Agent for MOBA Games
| Title | A Tutor Agent for MOBA Games |
| Authors | Victor do Nascimento Silva, Luiz Chaimowicz |
| Abstract | Digital games have become a key player in the entertainment industry, attracting millions of new players each year. In spite of that, novice players may have a hard time when playing certain types of games, such as MOBAs and MMORPGs, due to their steep learning curves and not so friendly online communities. In this paper, we present an approach to help novice players in MOBA games overcome these problems. An artificial intelligence agent plays alongside the player analyzing his/her performance and giving tips about the game. Experiments performed with the game {\em League of Legends} show the potential of this approach. |
| Tasks | League of Legends |
| Published | 2017-06-09 |
| URL | http://arxiv.org/abs/1706.02832v1 |
| http://arxiv.org/pdf/1706.02832v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-tutor-agent-for-moba-games |
| Repo | |
| Framework | |
SAFS: A Deep Feature Selection Approach for Precision Medicine
| Title | SAFS: A Deep Feature Selection Approach for Precision Medicine |
| Authors | Milad Zafar Nezhad, Dongxiao Zhu, Xiangrui Li, Kai Yang, Phillip Levy |
| Abstract | In this paper, we propose a new deep feature selection method based on deep architecture. Our method uses stacked auto-encoders for feature representation in higher-level abstraction. We developed and applied a novel feature learning approach to a specific precision medicine problem, which focuses on assessing and prioritizing risk factors for hypertension (HTN) in a vulnerable demographic subgroup (African-American). Our approach is to use deep learning to identify significant risk factors affecting left ventricular mass indexed to body surface area (LVMI) as an indicator of heart damage risk. The results show that our feature learning and representation approach leads to better results in comparison with others. |
| Tasks | Feature Selection |
| Published | 2017-04-20 |
| URL | http://arxiv.org/abs/1704.05960v1 |
| http://arxiv.org/pdf/1704.05960v1.pdf | |
| PWC | https://paperswithcode.com/paper/safs-a-deep-feature-selection-approach-for |
| Repo | |
| Framework | |
MagNet and “Efficient Defenses Against Adversarial Attacks” are Not Robust to Adversarial Examples
| Title | MagNet and “Efficient Defenses Against Adversarial Attacks” are Not Robust to Adversarial Examples |
| Authors | Nicholas Carlini, David Wagner |
| Abstract | MagNet and “Efficient Defenses…” were recently proposed as a defense to adversarial examples. We find that we can construct adversarial examples that defeat these defenses with only a slight increase in distortion. |
| Tasks | |
| Published | 2017-11-22 |
| URL | http://arxiv.org/abs/1711.08478v1 |
| http://arxiv.org/pdf/1711.08478v1.pdf | |
| PWC | https://paperswithcode.com/paper/magnet-and-efficient-defenses-against |
| Repo | |
| Framework | |
Wind models and cross-site interpolation for the refugee reception islands in Greece
| Title | Wind models and cross-site interpolation for the refugee reception islands in Greece |
| Authors | Harris V. Georgiou |
| Abstract | In this study, the wind data series from five locations in Aegean Sea islands, the most active `hotspots’ in terms of refugee influx during the Oct/2015 - Jan/2016 period, are investigated. The analysis of the three-per-site data series includes standard statistical analysis and parametric distributions, auto-correlation analysis, cross-correlation analysis between the sites, as well as various ARMA models for estimating the feasibility and accuracy of such spatio-temporal linear regressors for predictive analytics. Strong correlations are detected across specific sites and appropriately trained ARMA(7,5) models achieve 1-day look-ahead error (RMSE) of less than 1.9 km/h on average wind speed. The results show that such data-driven statistical approaches are extremely useful in identifying unexpected and sometimes counter-intuitive associations between the available spatial data nodes, which is very important when designing corresponding models for short-term forecasting of sea condition, especially average wave height and direction, which is in fact what defines the associated weather risk of crossing these passages in refugee influx patterns. | |
| Tasks | |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.07885v1 |
| http://arxiv.org/pdf/1707.07885v1.pdf | |
| PWC | https://paperswithcode.com/paper/wind-models-and-cross-site-interpolation-for |
| Repo | |
| Framework | |
Predicting Surgery Duration with Neural Heteroscedastic Regression
| Title | Predicting Surgery Duration with Neural Heteroscedastic Regression |
| Authors | Nathan Ng, Rodney A Gabriel, Julian McAuley, Charles Elkan, Zachary C Lipton |
| Abstract | Scheduling surgeries is a challenging task due to the fundamental uncertainty of the clinical environment, as well as the risks and costs associated with under- and over-booking. We investigate neural regression algorithms to estimate the parameters of surgery case durations, focusing on the issue of heteroscedasticity. We seek to simultaneously estimate the duration of each surgery, as well as a surgery-specific notion of our uncertainty about its duration. Estimating this uncertainty can lead to more nuanced and effective scheduling strategies, as we are able to schedule surgeries more efficiently while allowing an informed and case-specific margin of error. Using surgery records %from the UC San Diego Health System, from a large United States health system we demonstrate potential improvements on the order of 20% (in terms of minutes overbooked) compared to current scheduling techniques. Moreover, we demonstrate that surgery durations are indeed heteroscedastic. We show that models that estimate case-specific uncertainty better fit the data (log likelihood). Additionally, we show that the heteroscedastic predictions can more optimally trade off between over and under-booking minutes, especially when idle minutes and scheduling collisions confer disparate costs. |
| Tasks | |
| Published | 2017-02-17 |
| URL | http://arxiv.org/abs/1702.05386v3 |
| http://arxiv.org/pdf/1702.05386v3.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-surgery-duration-with-neural |
| Repo | |
| Framework | |
