Paper Group ANR 1566
Enforcing Linearity in DNN succours Robustness and Adversarial Image Generation. Transfer learning enhanced physics informed neural network for phase-field modeling of fracture. Social Behavioral Phenotyping of Drosophila with a2D-3D Hybrid CNN Framework. Quantifying Urban Canopy Cover with Deep Convolutional Neural Networks. Automatic learner summ …
Enforcing Linearity in DNN succours Robustness and Adversarial Image Generation
| Title | Enforcing Linearity in DNN succours Robustness and Adversarial Image Generation |
| Authors | Anindya Sarkar, Nikhil Kumar Gupta, Raghu Iyengar |
| Abstract | Recent studies on the adversarial vulnerability of neural networks have shown that models trained with the objective of minimizing an upper bound on the worst-case loss over all possible adversarial perturbations improve robustness against adversarial attacks. Beside exploiting adversarial training framework, we show that by enforcing a Deep Neural Network (DNN) to be linear in transformed input and feature space improves robustness significantly. We also demonstrate that by augmenting the objective function with Local Lipschitz regularizer boost robustness of the model further. Our method outperforms most sophisticated adversarial training methods and achieves state of the art adversarial accuracy on MNIST, CIFAR10 and SVHN dataset. In this paper, we also propose a novel adversarial image generation method by leveraging Inverse Representation Learning and Linearity aspect of an adversarially trained deep neural network classifier. |
| Tasks | Adversarial Defense, Image Generation, Representation Learning |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.08108v2 |
| https://arxiv.org/pdf/1910.08108v2.pdf | |
| PWC | https://paperswithcode.com/paper/enforcing-linearity-in-dnn-succours |
| Repo | |
| Framework | |
Transfer learning enhanced physics informed neural network for phase-field modeling of fracture
| Title | Transfer learning enhanced physics informed neural network for phase-field modeling of fracture |
| Authors | Somdatta Goswami, Cosmin Anitescu, Souvik Chakraborty, Timon Rabczuk |
| Abstract | We present a new physics informed neural network (PINN) algorithm for solving brittle fracture problems. While most of the PINN algorithms available in the literature minimize the residual of the governing partial differential equation, the proposed approach takes a different path by minimizing the variational energy of the system. Additionally, we modify the neural network output such that the boundary conditions associated with the problem are exactly satisfied. Compared to conventional residual based PINN, the proposed approach has two major advantages. First, the imposition of boundary conditions is relatively simpler and more robust. Second, the order of derivatives present in the functional form of the variational energy is of lower order than in the residual form. Hence, training the network is faster. To compute the total variational energy of the system, an efficient scheme that takes as input a geometry described by spline based CAD model and employs Gauss quadrature rules for numerical integration has been proposed. Moreover, we utilize the concept of transfer learning to obtain the crack path in an efficient manner. The proposed approach is used to solve four fracture mechanics problems. For all the examples, results obtained using the proposed approach match closely with the results available in the literature. For the first two examples, we compare the results obtained using the proposed approach with the conventional residual based neural network results. For both the problems, the proposed approach is found to yield better accuracy compared to conventional residual based PINN algorithms. |
| Tasks | Transfer Learning |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02531v1 |
| https://arxiv.org/pdf/1907.02531v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-enhanced-physics-informed |
| Repo | |
| Framework | |
Social Behavioral Phenotyping of Drosophila with a2D-3D Hybrid CNN Framework
| Title | Social Behavioral Phenotyping of Drosophila with a2D-3D Hybrid CNN Framework |
| Authors | Ziping Jiang, Paul L. Chazot, M. Emre Celebi, Danny Crookes, Richard Jiang |
| Abstract | Behavioural phenotyping of Drosophila is an important means in biological and medical research to identify genetic, pathologic or psychologic impact on animal behaviour. |
| Tasks | |
| Published | 2019-03-27 |
| URL | http://arxiv.org/abs/1903.11421v1 |
| http://arxiv.org/pdf/1903.11421v1.pdf | |
| PWC | https://paperswithcode.com/paper/social-behavioral-phenotyping-of-drosophila |
| Repo | |
| Framework | |
Quantifying Urban Canopy Cover with Deep Convolutional Neural Networks
| Title | Quantifying Urban Canopy Cover with Deep Convolutional Neural Networks |
| Authors | Bill Cai, Xiaojiang Li, Carlo Ratti |
| Abstract | Urban canopy cover is important to mitigate the impact of climate change. Yet, existing quantification of urban greenery is either manual and not scalable, or use traditional computer vision methods that are inaccurate. We train deep convolutional neural networks (DCNNs) on datasets used for self-driving cars to estimate urban greenery instead, and find that our semantic segmentation and direct end-to-end estimation method are more accurate and scalable, reducing mean absolute error of estimating the Green View Index (GVI) metric from 10.1% to 4.67%. With the revised DCNN methods, the Treepedia project was able to scale and analyze canopy cover in 22 cities internationally, sparking interest and action in public policy and research fields. |
| Tasks | Self-Driving Cars, Semantic Segmentation |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.02109v1 |
| https://arxiv.org/pdf/1912.02109v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantifying-urban-canopy-cover-with-deep |
| Repo | |
| Framework | |
Automatic learner summary assessment for reading comprehension
| Title | Automatic learner summary assessment for reading comprehension |
| Authors | Menglin Xia, Ekaterina Kochmar, Ted Briscoe |
| Abstract | Automating the assessment of learner summaries provides a useful tool for assessing learner reading comprehension. We present a summarization task for evaluating non-native reading comprehension and propose three novel approaches to automatically assess the learner summaries. We evaluate our models on two datasets we created and show that our models outperform traditional approaches that rely on exact word match on this task. Our best model produces quality assessments close to professional examiners. |
| Tasks | Reading Comprehension |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07555v1 |
| https://arxiv.org/pdf/1906.07555v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-learner-summary-assessment-for-1 |
| Repo | |
| Framework | |
Efficient Learning of Discrete Graphical Models
| Title | Efficient Learning of Discrete Graphical Models |
| Authors | Marc Vuffray, Sidhant Misra, Andrey Y. Lokhov |
| Abstract | Graphical models are useful tools for describing structured high-dimensional probability distributions. Development of efficient algorithms for learning graphical models with least amount of data remains an active research topic. Reconstruction of graphical models that describe the statistics of discrete variables is a particularly challenging problem, for which the maximum likelihood approach is intractable. In this work, we provide the first sample-efficient method based on the Interaction Screening framework that allows one to provably learn fully general discrete factor models with node-specific discrete alphabets and multi-body interactions, specified in an arbitrary basis. We identify a single condition related to model parametrization that leads to rigorous guarantees on the recovery of model structure and parameters in any error norm, and is readily verifiable for a large class of models. Importantly, our bounds make explicit distinction between parameters that are proper to the model and priors used as an input to the algorithm. Finally, we show that the Interaction Screening framework includes all models previously considered in the literature as special cases, and for which our analysis shows a systematic improvement in sample complexity. |
| Tasks | |
| Published | 2019-02-02 |
| URL | http://arxiv.org/abs/1902.00600v1 |
| http://arxiv.org/pdf/1902.00600v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-learning-of-discrete-graphical |
| Repo | |
| Framework | |
Robustness and Imperceptibility Enhancement in Watermarked Images by Color Transformation
| Title | Robustness and Imperceptibility Enhancement in Watermarked Images by Color Transformation |
| Authors | Maedeh Jamali, Mahnoosh Bagheri, Nader Karimi, Shadrokh Samavi |
| Abstract | One of the effective methods for the preservation of copyright ownership of digital media is watermarking. Different watermarking techniques try to set a tradeoff between robustness and transparency of the process. In this research work, we have used color space conversion and frequency transform to achieve high robustness and transparency. Due to the distribution of image information in the RGB domain, we use the YUV color space, which concentrates the visual information in the Y channel. Embedding of the watermark is performed in the DCT coefficients of the specific wavelet subbands. Experimental results show high transparency and robustness of the proposed method. |
| Tasks | |
| Published | 2019-11-02 |
| URL | https://arxiv.org/abs/1911.00772v1 |
| https://arxiv.org/pdf/1911.00772v1.pdf | |
| PWC | https://paperswithcode.com/paper/robustness-and-imperceptibility-enhancement |
| Repo | |
| Framework | |
General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme
| Title | General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme |
| Authors | Tao Sun, Yuejiao Sun, Dongsheng Li, Qing Liao |
| Abstract | The incremental aggregated gradient algorithm is popular in network optimization and machine learning research. However, the current convergence results require the objective function to be strongly convex. And the existing convergence rates are also limited to linear convergence. Due to the mathematical techniques, the stepsize in the algorithm is restricted by the strongly convex constant, which may make the stepsize be very small (the strongly convex constant may be small). In this paper, we propose a general proximal incremental aggregated gradient algorithm, which contains various existing algorithms including the basic incremental aggregated gradient method. Better and new convergence results are proved even with the general scheme. The novel results presented in this paper, which have not appeared in previous literature, include: a general scheme, nonconvex analysis, the sublinear convergence rates of the function values, much larger stepsizes that guarantee the convergence, the convergence when noise exists, the line search strategy of the proximal incremental aggregated gradient algorithm and its convergence. |
| Tasks | |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.05093v1 |
| https://arxiv.org/pdf/1910.05093v1.pdf | |
| PWC | https://paperswithcode.com/paper/general-proximal-incremental-aggregated |
| Repo | |
| Framework | |
Eliminating artefacts in Polarimetric Images using Deep Learning
| Title | Eliminating artefacts in Polarimetric Images using Deep Learning |
| Authors | Dhruv Paranjpye, Ashish Mahabal, A. N. Ramaprakash, Gina Panopoulou, Kieran Cleary, Anthony Readhead, Dmitry Blinov, Kostas Tassis |
| Abstract | Polarization measurements done using Imaging Polarimeters such as the Robotic Polarimeter are very sensitive to the presence of artefacts in images. Artefacts can range from internal reflections in a telescope to satellite trails that could contaminate an area of interest in the image. With the advent of wide-field polarimetry surveys, it is imperative to develop methods that automatically flag artefacts in images. In this paper, we implement a Convolutional Neural Network to identify the most dominant artefacts in the images. We find that our model can successfully classify sources with 98% true positive and 97% true negative rates. Such models, combined with transfer learning, will give us a running start in artefact elimination for near-future surveys like WALOP. |
| Tasks | Transfer Learning |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08327v1 |
| https://arxiv.org/pdf/1911.08327v1.pdf | |
| PWC | https://paperswithcode.com/paper/eliminating-artefacts-in-polarimetric-images |
| Repo | |
| Framework | |
Machine Intelligence at the Edge with Learning Centric Power Allocation
| Title | Machine Intelligence at the Edge with Learning Centric Power Allocation |
| Authors | Shuai Wang, Yik-Chung Wu, Minghua Xia, Rui Wang, H. Vincent Poor |
| Abstract | While machine-type communication (MTC) devices generate considerable amounts of data, they often cannot process the data due to limited energy and computation power. To empower MTC with intelligence, edge machine learning has been proposed. However, power allocation in this paradigm requires maximizing the learning performance instead of the communication throughput, for which the celebrated water-filling and max-min fairness algorithms become inefficient. To this end, this paper proposes learning centric power allocation (LCPA), which provides a new perspective to radio resource allocation in learning driven scenarios. By employing an empirical classification error model that is supported by learning theory, the LCPA is formulated as a nonconvex nonsmooth optimization problem, and is solved by majorization minimization (MM) framework. To get deeper insights into LCPA, asymptotic analysis shows that the transmit powers are inversely proportional to the channel gain, and scale exponentially with the learning parameters. This is in contrast to traditional power allocations where quality of wireless channels is the only consideration. Last but not least, to enable LCPA in large-scale settings, two optimization algorithms, termed mirror-prox LCPA and accelerated LCPA, are further proposed. Extensive numerical results demonstrate that the proposed LCPA algorithms outperform traditional power allocation algorithms, and the large-scale algorithms reduce the computation time by orders of magnitude compared with MM-based LCPA but still achieve competing learning performance. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04922v1 |
| https://arxiv.org/pdf/1911.04922v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-intelligence-at-the-edge-with |
| Repo | |
| Framework | |
CFOF: A Concentration Free Measure for Anomaly Detection
| Title | CFOF: A Concentration Free Measure for Anomaly Detection |
| Authors | Fabrizio Angiulli |
| Abstract | We present a novel notion of outlier, called the Concentration Free Outlier Factor, or CFOF. As a main contribution, we formalize the notion of concentration of outlier scores and theoretically prove that CFOF does not concentrate in the Euclidean space for any arbitrary large dimensionality. To the best of our knowledge, there are no other proposals of data analysis measures related to the Euclidean distance for which it has been provided theoretical evidence that they are immune to the concentration effect. We determine the closed form of the distribution of CFOF scores in arbitrarily large dimensionalities and show that the CFOF score of a point depends on its squared norm standard score and on the kurtosis of the data distribution, thus providing a clear and statistically founded characterization of this notion. Moreover, we leverage this closed form to provide evidence that the definition does not suffer of the hubness problem affecting other measures. We prove that the number of CFOF outliers coming from each cluster is proportional to cluster size and kurtosis, a property that we call semi-locality. We determine that semi-locality characterizes existing reverse nearest neighbor-based outlier definitions, thus clarifying the exact nature of their observed local behavior. We also formally prove that classical distance-based and density-based outliers concentrate both for bounded and unbounded sample sizes and for fixed and variable values of the neighborhood parameter. We introduce the fast-CFOF algorithm for detecting outliers in large high-dimensional dataset. The algorithm has linear cost, supports multi-resolution analysis, and is embarrassingly parallel. Experiments highlight that the technique is able to efficiently process huge datasets and to deal even with large values of the neighborhood parameter, to avoid concentration, and to obtain excellent accuracy. |
| Tasks | Anomaly Detection |
| Published | 2019-01-14 |
| URL | https://arxiv.org/abs/1901.04992v2 |
| https://arxiv.org/pdf/1901.04992v2.pdf | |
| PWC | https://paperswithcode.com/paper/cfof-a-concentration-free-measure-for-anomaly |
| Repo | |
| Framework | |
Low-Depth Optical Neural Networks
| Title | Low-Depth Optical Neural Networks |
| Authors | Xiao-Ming Zhang, Man-Hong Yung |
| Abstract | Optical neural network (ONN) is emerging as an attractive proposal for machine-learning applications, enabling high-speed computation with low-energy consumption. However, there are several challenges in applying ONN for industrial applications, including the realization of activation functions and maintaining stability. In particular, the stability of ONNs decrease with the circuit depth, limiting the scalability of the ONNs for practical uses. Here we demonstrate how to compress the circuit depth of ONN to scale only logarithmically, leading to an exponential gain in terms of noise robustness. Our low-depth (LD) ONN is based on an architecture, called Optical CompuTing Of dot-Product UnitS (OCTOPUS), which can also be applied individually as a linear perceptron for solving classification problems. Using the standard data set of Letter Recognition, we present numerical evidence showing that LD-ONN can exhibit a significant gain in noise robustness, compared with a previous ONN proposal based on singular-value decomposition [Nature Photonics 11, 441 (2017)]. |
| Tasks | |
| Published | 2019-04-03 |
| URL | https://arxiv.org/abs/1904.02165v2 |
| https://arxiv.org/pdf/1904.02165v2.pdf | |
| PWC | https://paperswithcode.com/paper/low-depth-optical-neural-networks |
| Repo | |
| Framework | |
Analysis of the Synergy between Modularity and Autonomy in an Artificial Intelligence Based Fleet Competition
| Title | Analysis of the Synergy between Modularity and Autonomy in an Artificial Intelligence Based Fleet Competition |
| Authors | Xingyu Li, Mainak Mitra, Bogdan I. Epureanu |
| Abstract | A novel approach is provided for evaluating the benefits and burdens from vehicle modularity in fleets/units through the analysis of a game theoretical model of the competition between autonomous vehicle fleets in an attacker-defender game. We present an approach to obtain the heuristic operational strategies through fitting a decision tree on high-fidelity simulation results of an intelligent agent-based model. A multi-stage game theoretical model is also created for decision making considering military resources and impacts of past decisions. Nash equilibria of the operational strategy are revealed, and their characteristics are explored. The benefits of fleet modularity are also analyzed by comparing the results of the decision making process under diverse operational situations. |
| Tasks | Decision Making |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01405v1 |
| https://arxiv.org/pdf/1907.01405v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-the-synergy-between-modularity |
| Repo | |
| Framework | |
Online Second Price Auction with Semi-bandit Feedback Under the Non-Stationary Setting
| Title | Online Second Price Auction with Semi-bandit Feedback Under the Non-Stationary Setting |
| Authors | Haoyu Zhao, Wei Chen |
| Abstract | In this paper, we study the non-stationary online second price auction problem. We assume that the seller is selling the same type of items in $T$ rounds by the second price auction, and she can set the reserve price in each round. In each round, the bidders draw their private values from a joint distribution unknown to the seller. Then, the seller announced the reserve price in this round. Next, bidders with private values higher than the announced reserve price in that round will report their values to the seller as their bids. The bidder with the highest bid larger than the reserved price would win the item and she will pay to the seller the price equal to the second-highest bid or the reserve price, whichever is larger. The seller wants to maximize her total revenue during the time horizon $T$ while learning the distribution of private values over time. The problem is more challenging than the standard online learning scenario since the private value distribution is non-stationary, meaning that the distribution of bidders’ private values may change over time, and we need to use the \emph{non-stationary regret} to measure the performance of our algorithm. To our knowledge, this paper is the first to study the repeated auction in the non-stationary setting theoretically. Our algorithm achieves the non-stationary regret upper bound $\tilde{\mathcal{O}}(\min{\sqrt{\mathcal S T}, \bar{\mathcal{V}}^{\frac{1}{3}}T^{\frac{2}{3}}})$, where $\mathcal S$ is the number of switches in the distribution, and $\bar{\mathcal{V}}$ is the sum of total variation, and $\mathcal S$ and $\bar{\mathcal{V}}$ are not needed to be known by the algorithm. We also prove regret lower bounds $\Omega(\sqrt{\mathcal S T})$ in the switching case and $\Omega(\bar{\mathcal{V}}^{\frac{1}{3}}T^{\frac{2}{3}})$ in the dynamic case, showing that our algorithm has nearly optimal \emph{non-stationary regret}. |
| Tasks | |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.05949v1 |
| https://arxiv.org/pdf/1911.05949v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-second-price-auction-with-semi-bandit |
| Repo | |
| Framework | |
Actions Speak Louder Than (Pass)words: Passive Authentication of Smartphone Users via Deep Temporal Features
| Title | Actions Speak Louder Than (Pass)words: Passive Authentication of Smartphone Users via Deep Temporal Features |
| Authors | Debayan Deb, Arun Ross, Anil K. Jain, Kwaku Prakah-Asante, K. Venkatesh Prasad |
| Abstract | Prevailing user authentication schemes on smartphones rely on explicit user interaction, where a user types in a passcode or presents a biometric cue such as face, fingerprint, or iris. In addition to being cumbersome and obtrusive to the users, such authentication mechanisms pose security and privacy concerns. Passive authentication systems can tackle these challenges by frequently and unobtrusively monitoring the user’s interaction with the device. In this paper, we propose a Siamese Long Short-Term Memory network architecture for passive authentication, where users can be verified without requiring any explicit authentication step. We acquired a dataset comprising of measurements from 30 smartphone sensor modalities for 37 users. We evaluate our approach on 8 dominant modalities, namely, keystroke dynamics, GPS location, accelerometer, gyroscope, magnetometer, linear accelerometer, gravity, and rotation sensors. Experimental results find that, within 3 seconds, a genuine user can be correctly verified 97.15% of the time at a false accept rate of 0.1%. |
| Tasks | |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1901.05107v1 |
| http://arxiv.org/pdf/1901.05107v1.pdf | |
| PWC | https://paperswithcode.com/paper/actions-speak-louder-than-passwords-passive |
| Repo | |
| Framework | |
