Paper Group ANR 537
A New Method for the Semantic Integration of Multiple OWL Ontologies using Alignments. Kernel Transformer Networks for Compact Spherical Convolution. First-order Adversarial Vulnerability of Neural Networks and Input Dimension. Universal Hypothesis Testing with Kernels: Asymptotically Optimal Tests for Goodness of Fit. Handwriting Recognition in Lo …
A New Method for the Semantic Integration of Multiple OWL Ontologies using Alignments
| Title | A New Method for the Semantic Integration of Multiple OWL Ontologies using Alignments |
| Authors | Inès Osman |
| Abstract | This work is done as part of a master’s thesis project. The goal is to integrate two or more ontologies (of the same or close domains) in a new consistent and coherent OWL ontology to insure semantic interoperability between them. To do this, we have chosen to create a bridge ontology that includes all source ontologies and their bridging axioms in a customized way. In addition, we introduced a new criterion for obtaining an ontology of better quality (having the minimum of semantic/logical conflicts). We have also proposed new terminology and definitions that clarify the unclear and misplaced “integration” and “merging” notions that are randomly used in state-of-the-art works. Finally, we tested and evaluated our OIA2R tool using ontologies and reference alignments of the OAEI campaign. It turned out that it is generic, efficient and powerful enough. |
| Tasks | |
| Published | 2018-10-05 |
| URL | http://arxiv.org/abs/1810.02869v1 |
| http://arxiv.org/pdf/1810.02869v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-method-for-the-semantic-integration-of |
| Repo | |
| Framework | |
Kernel Transformer Networks for Compact Spherical Convolution
| Title | Kernel Transformer Networks for Compact Spherical Convolution |
| Authors | Yu-Chuan Su, Kristen Grauman |
| Abstract | Ideally, 360{\deg} imagery could inherit the deep convolutional neural networks (CNNs) already trained with great success on perspective projection images. However, existing methods to transfer CNNs from perspective to spherical images introduce significant computational costs and/or degradations in accuracy. In this work, we present the Kernel Transformer Network (KTN). KTNs efficiently transfer convolution kernels from perspective images to the equirectangular projection of 360{\deg} images. Given a source CNN for perspective images as input, the KTN produces a function parameterized by a polar angle and kernel as output. Given a novel 360{\deg} image, that function in turn can compute convolutions for arbitrary layers and kernels as would the source CNN on the corresponding tangent plane projections. Distinct from all existing methods, KTNs allow model transfer: the same model can be applied to different source CNNs with the same base architecture. This enables application to multiple recognition tasks without re-training the KTN. Validating our approach with multiple source CNNs and datasets, we show that KTNs improve the state of the art for spherical convolution. KTNs successfully preserve the source CNN’s accuracy, while offering transferability, scalability to typical image resolutions, and, in many cases, a substantially lower memory footprint. |
| Tasks | |
| Published | 2018-12-07 |
| URL | http://arxiv.org/abs/1812.03115v2 |
| http://arxiv.org/pdf/1812.03115v2.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-transformer-networks-for-compact |
| Repo | |
| Framework | |
First-order Adversarial Vulnerability of Neural Networks and Input Dimension
| Title | First-order Adversarial Vulnerability of Neural Networks and Input Dimension |
| Authors | Carl-Johann Simon-Gabriel, Yann Ollivier, Léon Bottou, Bernhard Schölkopf, David Lopez-Paz |
| Abstract | Over the past few years, neural networks were proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions. We show that adversarial vulnerability increases with the gradients of the training objective when viewed as a function of the inputs. Surprisingly, vulnerability does not depend on network topology: for many standard network architectures, we prove that at initialization, the $\ell_1$-norm of these gradients grows as the square root of the input dimension, leaving the networks increasingly vulnerable with growing image size. We empirically show that this dimension dependence persists after either usual or robust training, but gets attenuated with higher regularization. |
| Tasks | |
| Published | 2018-02-05 |
| URL | https://arxiv.org/abs/1802.01421v4 |
| https://arxiv.org/pdf/1802.01421v4.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-vulnerability-of-neural-networks |
| Repo | |
| Framework | |
Universal Hypothesis Testing with Kernels: Asymptotically Optimal Tests for Goodness of Fit
| Title | Universal Hypothesis Testing with Kernels: Asymptotically Optimal Tests for Goodness of Fit |
| Authors | Shengyu Zhu, Biao Chen, Pengfei Yang, Zhitang Chen |
| Abstract | We characterize the asymptotic performance of nonparametric goodness of fit testing. The exponential decay rate of the type-II error probability is used as the asymptotic performance metric, and a test is optimal if it achieves the maximum rate subject to a constant level constraint on the type-I error probability. We show that two classes of Maximum Mean Discrepancy (MMD) based tests attain this optimality on $\mathbb R^d$, while the quadratic-time Kernel Stein Discrepancy (KSD) based tests achieve the maximum exponential decay rate under a relaxed level constraint. Under the same performance metric, we proceed to show that the quadratic-time MMD based two-sample tests are also optimal for general two-sample problems, provided that kernels are bounded continuous and characteristic. Key to our approach are Sanov’s theorem from large deviation theory and the weak metrizable properties of the MMD and KSD. |
| Tasks | |
| Published | 2018-02-21 |
| URL | http://arxiv.org/abs/1802.07581v3 |
| http://arxiv.org/pdf/1802.07581v3.pdf | |
| PWC | https://paperswithcode.com/paper/universal-hypothesis-testing-with-kernels |
| Repo | |
| Framework | |
Handwriting Recognition in Low-resource Scripts using Adversarial Learning
| Title | Handwriting Recognition in Low-resource Scripts using Adversarial Learning |
| Authors | Ayan Kumar Bhunia, Abhirup Das, Ankan Kumar Bhunia, Perla Sai Raj Kishore, Partha Pratim Roy |
| Abstract | Handwritten Word Recognition and Spotting is a challenging field dealing with handwritten text possessing irregular and complex shapes. The design of deep neural network models makes it necessary to extend training datasets in order to introduce variations and increase the number of samples; word-retrieval is therefore very difficult in low-resource scripts. Much of the existing literature comprises preprocessing strategies which are seldom sufficient to cover all possible variations. We propose the Adversarial Feature Deformation Module (AFDM) that learns ways to elastically warp extracted features in a scalable manner. The AFDM is inserted between intermediate layers and trained alternatively with the original framework, boosting its capability to better learn highly informative features rather than trivial ones. We test our meta-framework, which is built on top of popular word-spotting and word-recognition frameworks and enhanced by the AFDM, not only on extensive Latin word datasets but also sparser Indic scripts. We record results for varying training data sizes, and observe that our enhanced network generalizes much better in the low-data regime; the overall word-error rates and mAP scores are observed to improve as well. |
| Tasks | |
| Published | 2018-11-04 |
| URL | http://arxiv.org/abs/1811.01396v5 |
| http://arxiv.org/pdf/1811.01396v5.pdf | |
| PWC | https://paperswithcode.com/paper/handwriting-recognition-in-low-resource |
| Repo | |
| Framework | |
Spherical Convolutional Neural Network for 3D Point Clouds
| Title | Spherical Convolutional Neural Network for 3D Point Clouds |
| Authors | Huan Lei, Naveed Akhtar, Ajmal Mian |
| Abstract | We propose a neural network for 3D point cloud processing that exploits `spherical’ convolution kernels and octree partitioning of space. The proposed metric-based spherical kernels systematically quantize point neighborhoods to identify local geometric structures in data, while maintaining the properties of translation-invariance and asymmetry. The network architecture itself is guided by octree data structuring that takes full advantage of the sparse nature of irregular point clouds. We specify spherical kernels with the help of neurons in each layer that in turn are associated with spatial locations. We exploit this association to avert dynamic kernel generation during network training, that enables efficient learning with high resolution point clouds. We demonstrate the utility of the spherical convolutional neural network for 3D object classification on standard benchmark datasets. | |
| Tasks | 3D Object Classification, Object Classification |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.07872v2 |
| http://arxiv.org/pdf/1805.07872v2.pdf | |
| PWC | https://paperswithcode.com/paper/spherical-convolutional-neural-network-for-3d |
| Repo | |
| Framework | |
Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation
| Title | Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation |
| Authors | Jiaxin Gu, Ce Li, Baochang Zhang, Jungong Han, Xianbin Cao, Jianzhuang Liu, David Doermann |
| Abstract | The advancement of deep convolutional neural networks (DCNNs) has driven significant improvement in the accuracy of recognition systems for many computer vision tasks. However, their practical applications are often restricted in resource-constrained environments. In this paper, we introduce projection convolutional neural networks (PCNNs) with a discrete back propagation via projection (DBPP) to improve the performance of binarized neural networks (BNNs). The contributions of our paper include: 1) for the first time, the projection function is exploited to efficiently solve the discrete back propagation problem, which leads to a new highly compressed CNNs (termed PCNNs); 2) by exploiting multiple projections, we learn a set of diverse quantized kernels that compress the full-precision kernels in a more efficient way than those proposed previously; 3) PCNNs achieve the best classification performance compared to other state-of-the-art BNNs on the ImageNet and CIFAR datasets. |
| Tasks | |
| Published | 2018-11-30 |
| URL | http://arxiv.org/abs/1811.12755v2 |
| http://arxiv.org/pdf/1811.12755v2.pdf | |
| PWC | https://paperswithcode.com/paper/projection-convolutional-neural-networks-for |
| Repo | |
| Framework | |
Interpreting CNNs via Decision Trees
| Title | Interpreting CNNs via Decision Trees |
| Authors | Quanshi Zhang, Yu Yang, Haotian Ma, Ying Nian Wu |
| Abstract | This paper aims to quantitatively explain rationales of each prediction that is made by a pre-trained convolutional neural network (CNN). We propose to learn a decision tree, which clarifies the specific reason for each prediction made by the CNN at the semantic level. I.e., the decision tree decomposes feature representations in high conv-layers of the CNN into elementary concepts of object parts. In this way, the decision tree tells people which object parts activate which filters for the prediction and how much they contribute to the prediction score. Such semantic and quantitative explanations for CNN predictions have specific values beyond the traditional pixel-level analysis of CNNs. More specifically, our method mines all potential decision modes of the CNN, where each mode represents a common case of how the CNN uses object parts for prediction. The decision tree organizes all potential decision modes in a coarse-to-fine manner to explain CNN predictions at different fine-grained levels. Experiments have demonstrated the effectiveness of the proposed method. |
| Tasks | |
| Published | 2018-02-01 |
| URL | http://arxiv.org/abs/1802.00121v2 |
| http://arxiv.org/pdf/1802.00121v2.pdf | |
| PWC | https://paperswithcode.com/paper/interpreting-cnns-via-decision-trees |
| Repo | |
| Framework | |
Artificial Intelligence Assisted Power Grid Hardening in Response to Extreme Weather Events
| Title | Artificial Intelligence Assisted Power Grid Hardening in Response to Extreme Weather Events |
| Authors | Rozhin Eskandarpour, Amin Khodaei, A. Paaso, N. M. Abdullah |
| Abstract | In this paper, an artificial intelligence based grid hardening model is proposed with the objective of improving power grid resilience in response to extreme weather events. At first, a machine learning model is proposed to predict the component states (either operational or outage) in response to the extreme event. Then, these predictions are fed into a hardening model, which determines strategic locations for placement of distributed generation (DG) units. In contrast to existing literature in hardening and resilience enhancement, this paper co-optimizes grid economic and resilience objectives by considering the intricate dependencies of the two. The numerical simulations on the standard IEEE 118-bus test system illustrate the merits and applicability of the proposed hardening model. The results indicate that the proposed hardening model through decentralized and distributed local energy resources can produce a more robust solution that can protect the system significantly against multiple component outages due to an extreme event. |
| Tasks | |
| Published | 2018-10-05 |
| URL | http://arxiv.org/abs/1810.02866v1 |
| http://arxiv.org/pdf/1810.02866v1.pdf | |
| PWC | https://paperswithcode.com/paper/artificial-intelligence-assisted-power-grid |
| Repo | |
| Framework | |
Deep learning for comprehensive forecasting of Alzheimer’s Disease progression
| Title | Deep learning for comprehensive forecasting of Alzheimer’s Disease progression |
| Authors | Charles K. Fisher, Aaron M. Smith, Jonathan R. Walsh, the Coalition Against Major Diseases |
| Abstract | Most approaches to machine learning from electronic health data can only predict a single endpoint. Here, we present an alternative that uses unsupervised deep learning to simulate detailed patient trajectories. We use data comprising 18-month trajectories of 44 clinical variables from 1908 patients with Mild Cognitive Impairment or Alzheimer’s Disease to train a model for personalized forecasting of disease progression. We simulate synthetic patient data including the evolution of each sub-component of cognitive exams, laboratory tests, and their associations with baseline clinical characteristics, generating both predictions and their confidence intervals. Our unsupervised model predicts changes in total ADAS-Cog scores with the same accuracy as specifically trained supervised models and identifies sub-components associated with word recall as predictive of progression. The ability to simultaneously simulate dozens of patient characteristics is a crucial step towards personalized medicine for Alzheimer’s Disease. |
| Tasks | |
| Published | 2018-07-10 |
| URL | http://arxiv.org/abs/1807.03876v2 |
| http://arxiv.org/pdf/1807.03876v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-comprehensive-forecasting |
| Repo | |
| Framework | |
Probabilistic Programming with Densities in SlicStan: Efficient, Flexible and Deterministic
| Title | Probabilistic Programming with Densities in SlicStan: Efficient, Flexible and Deterministic |
| Authors | Maria I. Gorinova, Andrew D. Gordon, Charles Sutton |
| Abstract | Stan is a probabilistic programming language that has been increasingly used for real-world scalable projects. However, to make practical inference possible, the language sacrifices some of its usability by adopting a block syntax, which lacks compositionality and flexible user-defined functions. Moreover, the semantics of the language has been mainly given in terms of intuition about implementation, and has not been formalised. This paper provides a formal treatment of the Stan language, and introduces the probabilistic programming language SlicStan — a compositional, self-optimising version of Stan. Our main contributions are: (1) the formalisation of a core subset of Stan through an operational density-based semantics; (2) the design and semantics of the Stan-like language SlicStan, which facilities better code reuse and abstraction through its compositional syntax, more flexible functions, and information-flow type system; and (3) a formal, semantic-preserving procedure for translating SlicStan to Stan. |
| Tasks | Probabilistic Programming |
| Published | 2018-11-02 |
| URL | http://arxiv.org/abs/1811.00890v1 |
| http://arxiv.org/pdf/1811.00890v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-programming-with-densities-in |
| Repo | |
| Framework | |
The Classification of Cropping Patterns Based on Regional Climate Classification Using Decision Tree Approach
| Title | The Classification of Cropping Patterns Based on Regional Climate Classification Using Decision Tree Approach |
| Authors | T. A. Munandar, Sumiati |
| Abstract | Nowadays, agricultural field is experiencing problems related to climate change that result in the changing patterns in cropping season, especially for paddy and coarse grains, pulses roots and Tuber (CGPRT/Palawija) crops. The cropping patterns of rice and CGPRT crops highly depend on the availability of rainfall throughout the year. The changing and shifting of the rainy season result in the changing cropping seasons. It is important to find out the cropping patterns of paddy and CGPRT crops based on monthly rainfall pattern in every area. The Oldeman’s method which is usually used in the classification of of cropping patterns of paddy and CGPRT crops is considered less able to determine the cropping patterns because it requires to see the rainfall data throughout the year. This research proposes an alternative solution to determine the cropping pattern of paddy and CGPRT crops based on the pattern of rainfall in the area using decision tree approach. There were three algorithms, namely, J48, RandomTree and REPTree, tested to determine the best algorithm used in the process of the classification of the cropping pattern in the area. The results showed that J48 algorithm has a higher classification accuracy than RandomTree and REPTree for 48%, 42.67% and 38.67%, respectively. Meanwhile, the results of data testing into the decision tree rule indicate that most of the areas in DKI Jakarta are suggested to apply the cropping pattern of 1 paddy cropping and 1 CGRPT cropping (1 PS + 1 PL). While in Banten, there are three cropping patterns that can be applied, they are, 1 paddy cropping and 1 CGPRT cropping (1 PS + 1 PL), 3 short-period paddy croppings or 2 paddy croppings and 1 CGPRT cropping (3 short-period PS or 2 PS + 1 PL) and 2 paddy croppings and 1 CGPRT cropping (2 PS + 1 PL). |
| Tasks | |
| Published | 2018-03-26 |
| URL | http://arxiv.org/abs/1803.11259v1 |
| http://arxiv.org/pdf/1803.11259v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-classification-of-cropping-patterns-based |
| Repo | |
| Framework | |
Towards Dependability Metrics for Neural Networks
| Title | Towards Dependability Metrics for Neural Networks |
| Authors | Chih-Hong Cheng, Georg Nührenberg, Chung-Hao Huang, Harald Ruess, Hirotoshi Yasuoka |
| Abstract | Artificial neural networks (NN) are instrumental in realizing highly-automated driving functionality. An overarching challenge is to identify best safety engineering practices for NN and other learning-enabled components. In particular, there is an urgent need for an adequate set of metrics for measuring all-important NN dependability attributes. We address this challenge by proposing a number of NN-specific and efficiently computable metrics for measuring NN dependability attributes including robustness, interpretability, completeness, and correctness. |
| Tasks | |
| Published | 2018-06-06 |
| URL | http://arxiv.org/abs/1806.02338v2 |
| http://arxiv.org/pdf/1806.02338v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-dependability-metrics-for-neural |
| Repo | |
| Framework | |
Number of Connected Components in a Graph: Estimation via Counting Patterns
| Title | Number of Connected Components in a Graph: Estimation via Counting Patterns |
| Authors | Ashish Khetan, Harshay Shah, Sewoong Oh |
| Abstract | Due to the limited resources and the scale of the graphs in modern datasets, we often get to observe a sampled subgraph of a larger original graph of interest, whether it is the worldwide web that has been crawled or social connections that have been surveyed. Inferring a global property of the original graph from such a sampled subgraph is of a fundamental interest. In this work, we focus on estimating the number of connected components. It is a challenging problem and, for general graphs, little is known about the connection between the observed subgraph and the number of connected components of the original graph. In order to make this connection, we propose a highly redundant and large-dimensional representation of the subgraph, which at first glance seems counter-intuitive. A subgraph is represented by the counts of patterns, known as network motifs. This representation is crucial in introducing a novel estimator for the number of connected components for general graphs, under the knowledge of the spectral gap of the original graph. The connection is made precise via the Schatten $k$-norms of the graph Laplacian and the spectral representation of the number of connected components. We provide a guarantee on the resulting mean squared error that characterizes the bias variance tradeoff. Experiments on synthetic and real-world graphs suggest that we improve upon competing algorithms for graphs with spectral gaps bounded away from zero. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://arxiv.org/abs/1812.00139v1 |
| http://arxiv.org/pdf/1812.00139v1.pdf | |
| PWC | https://paperswithcode.com/paper/number-of-connected-components-in-a-graph |
| Repo | |
| Framework | |
Proportional Volume Sampling and Approximation Algorithms for A-Optimal Design
| Title | Proportional Volume Sampling and Approximation Algorithms for A-Optimal Design |
| Authors | Aleksandar Nikolov, Mohit Singh, Uthaipon Tao Tantipongpipat |
| Abstract | We study the optimal design problems where the goal is to choose a set of linear measurements to obtain the most accurate estimate of an unknown vector in $d$ dimensions. We study the $A$-optimal design variant where the objective is to minimize the average variance of the error in the maximum likelihood estimate of the vector being measured. The problem also finds applications in sensor placement in wireless networks, sparse least squares regression, feature selection for $k$-means clustering, and matrix approximation. In this paper, we introduce proportional volume sampling to obtain improved approximation algorithms for $A$-optimal design. Our main result is to obtain improved approximation algorithms for the $A$-optimal design problem by introducing the proportional volume sampling algorithm. Our results nearly optimal bounds in the asymptotic regime when the number of measurements done, $k$, is significantly more than the dimension $d$. We also give first approximation algorithms when $k$ is small including when $k=d$. The proportional volume-sampling algorithm also gives approximation algorithms for other optimal design objectives such as $D$-optimal design and generalized ratio objective matching or improving previous best known results. Interestingly, we show that a similar guarantee cannot be obtained for the $E$-optimal design problem. We also show that the $A$-optimal design problem is NP-hard to approximate within a fixed constant when $k=d$. |
| Tasks | Feature Selection |
| Published | 2018-02-22 |
| URL | http://arxiv.org/abs/1802.08318v5 |
| http://arxiv.org/pdf/1802.08318v5.pdf | |
| PWC | https://paperswithcode.com/paper/proportional-volume-sampling-and |
| Repo | |
| Framework | |
