January 29, 2020

3114 words 15 mins read

Paper Group ANR 662

APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection. Using Latent Class Analysis to Identify ARDS Sub-phenotypes for Enhanced Machine Learning Predictive Performance. Event Detection in Micro-PMU Data: A Generative Adversarial Network Scoring Method. An Expert System Approach for determine the stage of UiTM Perlis Palapes Cadet P …

APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection


Title	APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection
Authors	Anneliese Braunegg, Amartya Chakraborty, Michael Krumdick, Nicole Lape, Sara Leary, Keith Manville, Elizabeth Merkhofer, Laura Strickhart, Matthew Walmer
Abstract	Physical adversarial attacks threaten to fool object detection systems, but reproducible research on the real-world effectiveness of physical patches and how to defend against them requires a publicly available benchmark dataset. We present APRICOT, a collection of over 1,000 annotated photographs of printed adversarial patches in public locations. The patches target several object categories for three COCO-trained detection models, and the photos represent natural variation in position, distance, lighting conditions, and viewing angle. Our analysis suggests that maintaining adversarial robustness in uncontrolled settings is highly challenging, but it is still possible to produce targeted detections under white-box and sometimes black-box settings. We establish baselines for defending against adversarial patches through several methods, including a detector supervised with synthetic data and unsupervised methods such as kernel density estimation, Bayesian uncertainty, and reconstruction error. Our results suggest that adversarial patches can be effectively flagged, both in a high-knowledge, attack-specific scenario, and in an unsupervised setting where patches are detected as anomalies in natural images. This dataset and the described experiments provide a benchmark for future research on the effectiveness of and defenses against physical adversarial objects in the wild.
Tasks	Density Estimation, Object Detection
Published	2019-12-17
URL	https://arxiv.org/abs/1912.08166v1
PDF	https://arxiv.org/pdf/1912.08166v1.pdf
PWC	https://paperswithcode.com/paper/apricot-a-dataset-of-physical-adversarial
Repo
Framework

Using Latent Class Analysis to Identify ARDS Sub-phenotypes for Enhanced Machine Learning Predictive Performance


Title	Using Latent Class Analysis to Identify ARDS Sub-phenotypes for Enhanced Machine Learning Predictive Performance
Authors	Tony Wang, Tim Tschampel, Emilia Apostolova, Tom Velez
Abstract	In this work, we utilize Machine Learning for early recognition of patients at high risk of acute respiratory distress syndrome (ARDS), which is critical for successful prevention strategies for this devastating syndrome. The difficulty in early ARDS recognition stems from its complex and heterogenous nature. In this study, we integrate knowledge of the heterogeneity of ARDS patients into predictive model building. Using MIMIC-III data, we first apply latent class analysis (LCA) to identify homogeneous sub-groups in the ARDS population, and then build predictive models on the partitioned data. The results indicate that significantly improved performances of prediction can be obtained for two of the three identified sub-phenotypes of ARDS. Experiments suggests that identifying sub-phenotypes is beneficial for building predictive model for ARDS.
Tasks
Published	2019-03-28
URL	http://arxiv.org/abs/1903.12127v1
PDF	http://arxiv.org/pdf/1903.12127v1.pdf
PWC	https://paperswithcode.com/paper/using-latent-class-analysis-to-identify-ards
Repo
Framework

Event Detection in Micro-PMU Data: A Generative Adversarial Network Scoring Method


Title	Event Detection in Micro-PMU Data: A Generative Adversarial Network Scoring Method
Authors	Armin Aligholian, Alireza Shahsavari, Ed Cortez, Emma Stewart, Hamed Mohsenian-Rad
Abstract	A new data-driven method is proposed to detect events in the data streams from distribution-level phasor measurement units, a.k.a., micro-PMUs. The proposed method is developed by constructing unsupervised deep learning anomaly detection models; thus, providing event detection algorithms that require no or minimal human knowledge. First, we develop the core components of our approach based on a Generative Adversarial Network (GAN) model. We refer to this method as the basic method. It uses the same features that are often used in the literature to detect events in micro-PMU data. Next, we propose a second method, which we refer to as the enhanced method, which is enforced with additional feature analysis. Both methods can detect point signatures on single features and also group signatures on multiple features. This capability can address the unbalanced nature of power distribution circuits. The proposed methods are evaluated using real-world micro-PMU data. We show that both methods highly outperform a state-of-the-art statistical method in terms of the event detection accuracy. The enhanced method also outperforms the basic method.
Tasks	Anomaly Detection
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05103v2
PDF	https://arxiv.org/pdf/1912.05103v2.pdf
PWC	https://paperswithcode.com/paper/event-detection-in-micro-pmu-data-a
Repo
Framework

An Expert System Approach for determine the stage of UiTM Perlis Palapes Cadet Performance and Ranking Selection


Title	An Expert System Approach for determine the stage of UiTM Perlis Palapes Cadet Performance and Ranking Selection
Authors	Tajul Rosli Razak
Abstract	The palapes cadets are one of the uniform organizations in UiTM Perlis for extra-curricular activities. The palapes cadets arrange their organization in a hierarchy according to grade. Senior uniform officer (SUO) is the highest rank, followed by a junior uniform officer (JUO), sergeant, corporal, lance corporal, and lastly, cadet officer, which is the lowest rank. The palapes organization has several methods to measure performance toward promotion to a higher rank, whether individual performance or in a group. Cadets are selected for promotion based on demonstrated leadership abilities, acquired skills, physical fitness, and comprehension of information as measured through standardized testing. However, this method is too complicated when manually assessed by a trainer or coach. Therefore, this study will propose an expert system, which is one of the artificial intelligence techniques that can recognize the readiness and progression of a palapes cadet.
Tasks
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07651v1
PDF	https://arxiv.org/pdf/1908.07651v1.pdf
PWC	https://paperswithcode.com/paper/190807651
Repo
Framework

Analytical classical density functionals from an equation learning network


Title	Analytical classical density functionals from an equation learning network
Authors	Shang-Chun Lin, Georg Martius, Martin Oettel
Abstract	We explore the feasibility of using machine learning methods to obtain an analytic form of the classical free energy functional for two model fluids, hard rods and Lennard–Jones, in one dimension . The Equation Learning Network proposed in Ref. 1 is suitably modified to construct free energy densities which are functions of a set of weighted densities and which are built from a small number of basis functions with flexible combination rules. This setup considerably enlarges the functional space used in the machine learning optimization as compared to previous work 2 where the functional is limited to a simple polynomial form. As a result, we find a good approximation for the exact hard rod functional and its direct correlation function. For the Lennard–Jones fluid, we let the network learn (i) the full excess free energy functional and (ii) the excess free energy functional related to interparticle attractions. Both functionals show a good agreement with simulated density profiles for thermodynamic parameters inside and outside the training region.
Tasks
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12752v2
PDF	https://arxiv.org/pdf/1910.12752v2.pdf
PWC	https://paperswithcode.com/paper/analytical-classical-density-functionals-from
Repo
Framework

SelectFusion: A Generic Framework to Selectively Learn Multisensory Fusion


Title	SelectFusion: A Generic Framework to Selectively Learn Multisensory Fusion
Authors	Changhao Chen, Stefano Rosa, Chris Xiaoxuan Lu, Niki Trigoni, Andrew Markham
Abstract	Autonomous vehicles and mobile robotic systems are typically equipped with multiple sensors to provide redundancy. By integrating the observations from different sensors, these mobile agents are able to perceive the environment and estimate system states, e.g. locations and orientations. Although deep learning approaches for multimodal odometry estimation and localization have gained traction, they rarely focus on the issue of robust sensor fusion - a necessary consideration to deal with noisy or incomplete sensor observations in the real world. Moreover, current deep odometry models also suffer from a lack of interpretability. To this extent, we propose SelectFusion, an end-to-end selective sensor fusion module which can be applied to useful pairs of sensor modalities such as monocular images and inertial measurements, depth images and LIDAR point clouds. During prediction, the network is able to assess the reliability of the latent features from different sensor modalities and estimate both trajectory at scale and global pose. In particular, we propose two fusion modules based on different attention strategies: deterministic soft fusion and stochastic hard fusion, and we offer a comprehensive study of the new strategies compared to trivial direct fusion. We evaluate all fusion strategies in both ideal conditions and on progressively degraded datasets that present occlusions, noisy and missing data and time misalignment between sensors, and we investigate the effectiveness of the different fusion strategies in attending the most reliable features, which in itself, provides insights into the operation of the various models.
Tasks	Autonomous Vehicles, Sensor Fusion
Published	2019-12-30
URL	https://arxiv.org/abs/1912.13077v1
PDF	https://arxiv.org/pdf/1912.13077v1.pdf
PWC	https://paperswithcode.com/paper/selectfusion-a-generic-framework-to
Repo
Framework

Statically Detecting Vulnerabilities by Processing Programming Languages as Natural Languages


Title	Statically Detecting Vulnerabilities by Processing Programming Languages as Natural Languages
Authors	Ibéria Medeiros, Nuno Neves, Miguel Correia
Abstract	Web applications continue to be a favorite target for hackers due to a combination of wide adoption and rapid deployment cycles, which often lead to the introduction of high impact vulnerabilities. Static analysis tools are important to search for bugs automatically in the program source code, supporting developers on their removal. However, building these tools requires programming the knowledge on how to discover the vulnerabilities. This paper presents an alternative approach in which tools learn to detect flaws automatically by resorting to artificial intelligence concepts, more concretely to natural language processing. The approach employs a sequence model to learn to characterize vulnerabilities based on an annotated corpus. Afterwards, the model is utilized to discover and identify vulnerabilities in the source code. It was implemented in the DEKANT tool and evaluated experimentally with a large set of PHP applications and WordPress plugins. Overall, we found several hundred vulnerabilities belonging to 12 classes of input validation vulnerabilities, where 62 of them were zero-day.
Tasks
Published	2019-10-12
URL	https://arxiv.org/abs/1910.06826v1
PDF	https://arxiv.org/pdf/1910.06826v1.pdf
PWC	https://paperswithcode.com/paper/statically-detecting-vulnerabilities-by
Repo
Framework

The Random Conditional Distribution for Higher-Order Probabilistic Inference


Title	The Random Conditional Distribution for Higher-Order Probabilistic Inference
Authors	Zenna Tavares, Xin Zhang, Edgar Minaysan, Javier Burroni, Rajesh Ranganath, Armando Solar Lezama
Abstract	The need to condition distributional properties such as expectation, variance, and entropy arises in algorithmic fairness, model simplification, robustness and many other areas. At face value however, distributional properties are not random variables, and hence conditioning them is a semantic error and type error in probabilistic programming languages. On the other hand, distributional properties are contingent on other variables in the model, change in value when we observe more information, and hence in a precise sense are random variables too. In order to capture the uncertain over distributional properties, we introduce a probability construct – the random conditional distribution – and incorporate it into a probabilistic programming language Omega. A random conditional distribution is a higher-order random variable whose realizations are themselves conditional random variables. In Omega we extend distributional properties of random variables to random conditional distributions, such that for example while the expectation a real valued random variable is a real value, the expectation of a random conditional distribution is a distribution over expectations. As a consequence, it requires minimal syntax to encode inference problems over distributional properties, which so far have evaded treatment within probabilistic programming systems and probabilistic modeling in general. We demonstrate our approach case studies in algorithmic fairness and robustness.
Tasks	Probabilistic Programming
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10556v1
PDF	http://arxiv.org/pdf/1903.10556v1.pdf
PWC	https://paperswithcode.com/paper/the-random-conditional-distribution-for
Repo
Framework

Migrating Monarch Butterfly Localization Using Multi-Sensor Fusion Neural Networks


Title	Migrating Monarch Butterfly Localization Using Multi-Sensor Fusion Neural Networks
Authors	Mingyu Yang, Roger Hsiao, Gordy Carichner, Katherine Ernst, Jaechan Lim, Delbert A. Green II, Inhee Lee, David Blaauw, Hun-Seok Kim
Abstract	Details of Monarch butterfly migration from the U.S. to Mexico remain a mystery due to lack of a proper localization technology to accurately localize and track butterfly migration. In this paper, we propose a deep learning based butterfly localization algorithm that can estimate a butterfly’s daily location by analyzing a light and temperature sensor data log continuously obtained from an ultra-low power, mm-scale sensor attached to the butterfly. To train and test the proposed neural network based multi-sensor fusion localization algorithm, we collected over 1500 days of real world sensor measurement data with 82 volunteers all over the U.S. The proposed algorithm exhibits a mean absolute error of <1.5 degree in latitude and <0.5 degree in longitude Earth coordinate, satisfying our target goal for the Monarch butterfly migration study.
Tasks	Sensor Fusion
Published	2019-12-14
URL	https://arxiv.org/abs/1912.06907v1
PDF	https://arxiv.org/pdf/1912.06907v1.pdf
PWC	https://paperswithcode.com/paper/migrating-monarch-butterfly-localization
Repo
Framework

Efficient Search-Based Weighted Model Integration


Title	Efficient Search-Based Weighted Model Integration
Authors	Zhe Zeng, Guy Van den Broeck
Abstract	Weighted model integration (WMI) extends Weighted model counting (WMC) to the integration of functions over mixed discrete-continuous domains. It has shown tremendous promise for solving inference problems in graphical models and probabilistic programming. Yet, state-of-the-art tools for WMI are limited in terms of performance and ignore the independence structure that is crucial to improving efficiency. To address this limitation, we propose an efficient model integration algorithm for theories with tree primal graphs. We exploit the sparse graph structure by using search to performing integration. Our algorithm greatly improves the computational efficiency on such problems and exploits context-specific independence between variables. Experimental results show dramatic speedups compared to existing WMI solvers on problems with tree-shaped dependencies.
Tasks	Probabilistic Programming
Published	2019-03-13
URL	https://arxiv.org/abs/1903.05334v4
PDF	https://arxiv.org/pdf/1903.05334v4.pdf
PWC	https://paperswithcode.com/paper/efficient-search-based-weighted-model
Repo
Framework

Hidden Structure in the Solutions Set of the N Queens Problem


Title	Hidden Structure in the Solutions Set of the N Queens Problem
Authors	T. E. Raptis
Abstract	Some preliminary results are reported on the equivalence of any n-queens problem with the roots of a Boolean valued quadratic form via a generic dimensional reduction scheme. It is then proven that the solutions set is encoded in the entries of a special matrix. Further examination reveals a direct association with pointwise Boolean fractal operators applied on certain integer sequences associated with this matrix suggesting the presence of an underlying special geometry of the solutions set.
Tasks
Published	2019-07-26
URL	https://arxiv.org/abs/1909.05628v1
PDF	https://arxiv.org/pdf/1909.05628v1.pdf
PWC	https://paperswithcode.com/paper/hidden-structure-in-the-solutions-set-of-the
Repo
Framework

Tracking and Improving Information in the Service of Fairness


Title	Tracking and Improving Information in the Service of Fairness
Authors	Sumegha Garg, Michael P. Kim, Omer Reingold
Abstract	As algorithmic prediction systems have become widespread, fears that these systems may inadvertently discriminate against members of underrepresented populations have grown. With the goal of understanding fundamental principles that underpin the growing number of approaches to mitigating algorithmic discrimination, we investigate the role of information in fair prediction. A common strategy for decision-making uses a predictor to assign individuals a risk score; then, individuals are selected or rejected on the basis of this score. In this work, we study a formal framework for measuring the information content of predictors. Central to this framework is the notion of a refinement, first studied by Degroot and Fienberg. Intuitively, a refinement of a predictor $z$ increases the overall informativeness of the predictions without losing the information already contained in $z$. We show that increasing information content through refinements improves the downstream selection rules across a wide range of fairness measures (e.g. true positive rates, false positive rates, selection rates). In turn, refinements provide a simple but effective tool for reducing disparity in treatment and impact without sacrificing the utility of the predictions. Our results suggest that in many applications, the perceived “cost of fairness” results from an information disparity across populations, and thus, may be avoided with improved information.
Tasks	Decision Making
Published	2019-04-22
URL	https://arxiv.org/abs/1904.09942v2
PDF	https://arxiv.org/pdf/1904.09942v2.pdf
PWC	https://paperswithcode.com/paper/tracking-and-improving-information-in-the
Repo
Framework

Inferring Latent dimension of Linear Dynamical System with Minimum Description Length


Title	Inferring Latent dimension of Linear Dynamical System with Minimum Description Length
Authors	Yang Li
Abstract	Time-invariant linear dynamical system arises in many real-world applications,and its usefulness is widely acknowledged. A practical limitation with this model is that its latent dimension that has a large impact on the model capability needs to be manually specified. It can be demonstrated that a lower-order model class could be totally nested into a higher-order class, and the corresponding likelihood is nondecreasing. Hence, criterion built on the likelihood is not appropriate for model selection. This paper addresses the issue and proposes a criterion for linear dynamical system based on the principle of minimum description length. The latent structure, which is omitted in previous work, is explicitly considered in this newly proposed criterion. Our work extends the principle of minimum description length and demonstrates its effectiveness in the tasks of model training. The experiments on both univariate and multivariate sequences confirm the good performance of our newly proposed method.
Tasks	Model Selection
Published	2019-06-23
URL	https://arxiv.org/abs/1906.09536v1
PDF	https://arxiv.org/pdf/1906.09536v1.pdf
PWC	https://paperswithcode.com/paper/inferring-latent-dimension-of-linear
Repo
Framework

LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models


Title	LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models
Authors	Yuan Zhou, Bradley J. Gram-Hansen, Tobias Kohn, Tom Rainforth, Hongseok Yang, Frank Wood
Abstract	We develop a new Low-level, First-order Probabilistic Programming Language (LF-PPL) suited for models containing a mix of continuous, discrete, and/or piecewise-continuous variables. The key success of this language and its compilation scheme is in its ability to automatically distinguish parameters the density function is discontinuous with respect to, while further providing runtime checks for boundary crossings. This enables the introduction of new inference engines that are able to exploit gradient information, while remaining efficient for models which are not everywhere differentiable. We demonstrate this ability by incorporating a discontinuous Hamiltonian Monte Carlo (DHMC) inference engine that is able to deliver automated and efficient inference for non-differentiable models. Our system is backed up by a mathematical formalism that ensures that any model expressed in this language has a density with measure zero discontinuities to maintain the validity of the inference engine.
Tasks	Probabilistic Programming
Published	2019-03-06
URL	http://arxiv.org/abs/1903.02482v1
PDF	http://arxiv.org/pdf/1903.02482v1.pdf
PWC	https://paperswithcode.com/paper/lf-ppl-a-low-level-first-order-probabilistic
Repo
Framework

An Intrinsic Nearest Neighbor Analysis of Neural Machine Translation Architectures


Title	An Intrinsic Nearest Neighbor Analysis of Neural Machine Translation Architectures
Authors	Hamidreza Ghader, Christof Monz
Abstract	Earlier approaches indirectly studied the information captured by the hidden states of recurrent and non-recurrent neural machine translation models by feeding them into different classifiers. In this paper, we look at the encoder hidden states of both transformer and recurrent machine translation models from the nearest neighbors perspective. We investigate to what extent the nearest neighbors share information with the underlying word embeddings as well as related WordNet entries. Additionally, we study the underlying syntactic structure of the nearest neighbors to shed light on the role of syntactic similarities in bringing the neighbors together. We compare transformer and recurrent models in a more intrinsic way in terms of capturing lexical semantics and syntactic structures, in contrast to extrinsic approaches used by previous works. In agreement with the extrinsic evaluations in the earlier works, our experimental results show that transformers are superior in capturing lexical semantics, but not necessarily better in capturing the underlying syntax. Additionally, we show that the backward recurrent layer in a recurrent model learns more about the semantics of words, whereas the forward recurrent layer encodes more context.
Tasks	Machine Translation, Word Embeddings
Published	2019-07-08
URL	https://arxiv.org/abs/1907.03885v1
PDF	https://arxiv.org/pdf/1907.03885v1.pdf
PWC	https://paperswithcode.com/paper/an-intrinsic-nearest-neighbor-analysis-of
Repo
Framework