Paper Group ANR 1287
Appendix for: Cut-free Calculi and Relational Semantics for Temporal STIT logics. Target-Focused Feature Selection Using a Bayesian Approach. Kernel quadrature with DPPs. Quantum Adversarial Machine Learning. Multi-Objective Autonomous Braking System using Naturalistic Dataset. Perfect reconstruction of sparse signals with piecewise continuous nonc …
Appendix for: Cut-free Calculi and Relational Semantics for Temporal STIT logics
| Title | Appendix for: Cut-free Calculi and Relational Semantics for Temporal STIT logics |
| Authors | Kees van Berkel, Tim Lyon |
| Abstract | This paper is an appendix to the paper “Cut-free Calculi and Relational Semantics for Temporal STIT logics” by Berkel and Lyon, 2019. It provides the completeness proof for the basic STIT logic Ldm (relative to irreflexive, temporal Kripke STIT frames) as well as gives the derivation of the independence of agents axiom for the logic Xstit. |
| Tasks | |
| Published | 2019-02-18 |
| URL | http://arxiv.org/abs/1902.06632v1 |
| http://arxiv.org/pdf/1902.06632v1.pdf | |
| PWC | https://paperswithcode.com/paper/appendix-for-cut-free-calculi-and-relational |
| Repo | |
| Framework | |
Target-Focused Feature Selection Using a Bayesian Approach
| Title | Target-Focused Feature Selection Using a Bayesian Approach |
| Authors | Orpaz Goldstein, Mohammad Kachuee, Kimmo Karkkainen, Majid Sarrafzadeh |
| Abstract | In many real-world scenarios where data is high dimensional, test time acquisition of features is a non-trivial task due to costs associated with feature acquisition and evaluating feature value. The need for highly confident models with an extremely frugal acquisition of features can be addressed by allowing a feature selection method to become target aware. We introduce an approach to feature selection that is based on Bayesian learning, allowing us to report target-specific levels of uncertainty, false positive, and false negative rates. In addition, measuring uncertainty lifts the restriction on feature selection being target agnostic, allowing for feature acquisition based on a single target of focus out of many. We show that acquiring features for a specific target is at least as good as common linear feature selection approaches for small non-sparse datasets, and surpasses these when faced with real-world healthcare data that is larger in scale and in sparseness. |
| Tasks | Feature Selection |
| Published | 2019-09-15 |
| URL | https://arxiv.org/abs/1909.06772v1 |
| https://arxiv.org/pdf/1909.06772v1.pdf | |
| PWC | https://paperswithcode.com/paper/target-focused-feature-selection-using-a |
| Repo | |
| Framework | |
Kernel quadrature with DPPs
| Title | Kernel quadrature with DPPs |
| Authors | Ayoub Belhadji, Rémi Bardenet, Pierre Chainais |
| Abstract | We study quadrature rules for functions from an RKHS, using nodes sampled from a determinantal point process (DPP). DPPs are parametrized by a kernel, and we use a truncated and saturated version of the RKHS kernel. This link between the two kernels, along with DPP machinery, leads to relatively tight bounds on the quadrature error, that depends on the spectrum of the RKHS kernel. Finally, we experimentally compare DPPs to existing kernel-based quadratures such as herding, Bayesian quadrature, or leverage score sampling. Numerical results confirm the interest of DPPs, and even suggest faster rates than our bounds in particular cases. |
| Tasks | |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07832v3 |
| https://arxiv.org/pdf/1906.07832v3.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-quadrature-with-dpps |
| Repo | |
| Framework | |
Quantum Adversarial Machine Learning
| Title | Quantum Adversarial Machine Learning |
| Authors | Sirui Lu, Lu-Ming Duan, Dong-Ling Deng |
| Abstract | Adversarial machine learning is an emerging field that focuses on studying vulnerabilities of machine learning approaches in adversarial settings and developing techniques accordingly to make learning robust to adversarial manipulations. It plays a vital role in various machine learning applications and has attracted tremendous attention across different communities recently. In this paper, we explore different adversarial scenarios in the context of quantum machine learning. We find that, similar to traditional classifiers based on classical neural networks, quantum learning systems are likewise vulnerable to crafted adversarial examples, independent of whether the input data is classical or quantum. In particular, we find that a quantum classifier that achieves nearly the state-of-the-art accuracy can be conclusively deceived by adversarial examples obtained via adding imperceptible perturbations to the original legitimate samples. This is explicitly demonstrated with quantum adversarial learning in different scenarios, including classifying real-life images (e.g., handwritten digit images in the dataset MNIST), learning phases of matter (such as, ferromagnetic/paramagnetic orders and symmetry protected topological phases), and classifying quantum data. Furthermore, we show that based on the information of the adversarial examples at hand, practical defense strategies can be designed to fight against a number of different attacks. Our results uncover the notable vulnerability of quantum machine learning systems to adversarial perturbations, which not only reveals a novel perspective in bridging machine learning and quantum physics in theory but also provides valuable guidance for practical applications of quantum classifiers based on both near-term and future quantum technologies. |
| Tasks | Quantum Machine Learning |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/2001.00030v1 |
| https://arxiv.org/pdf/2001.00030v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-adversarial-machine-learning |
| Repo | |
| Framework | |
Multi-Objective Autonomous Braking System using Naturalistic Dataset
| Title | Multi-Objective Autonomous Braking System using Naturalistic Dataset |
| Authors | Rafael Vasquez, Bilal Farooq |
| Abstract | A deep reinforcement learning based multi-objective autonomous braking system is presented. The design of the system is formulated in a continuous action space and seeks to maximize both pedestrian safety and perception as well as passenger comfort. The vehicle agent is trained against a large naturalistic dataset containing pedestrian road-crossing trials in which respondents walked across a road under various traffic conditions within an interactive virtual reality environment. The policy for brake control is learned through computer simulation using two reinforcement learning methods i.e. Proximal Policy Optimization and Deep Deterministic Policy Gradient and the efficiency of each are compared. Results show that the system is able to reduce the negative influence on passenger comfort by half while maintaining safe braking operation. |
| Tasks | |
| Published | 2019-04-15 |
| URL | https://arxiv.org/abs/1904.07705v2 |
| https://arxiv.org/pdf/1904.07705v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-objective-autonomous-braking-system |
| Repo | |
| Framework | |
Perfect reconstruction of sparse signals with piecewise continuous nonconvex penalties and nonconvexity control
| Title | Perfect reconstruction of sparse signals with piecewise continuous nonconvex penalties and nonconvexity control |
| Authors | Ayaka Sakata, Tomoyuki Obuchi |
| Abstract | We consider compressed sensing formulated as a minimization problem of nonconvex sparse penalties, Smoothly Clipped Absolute deviation (SCAD) and Minimax Concave Penalty (MCP). The nonconvexity of these penalties is controlled by nonconvexity parameters, and L1 penalty is contained as a limit with respect to these parameters. The analytically derived reconstruction limit overcomes that of L1 and the algorithmic limit in the Bayes-optimal setting, when the nonconvexity parameters have suitable values. For the practical usage, we apply the approximate message passing (AMP) to these nonconvex penalties. We show that the performance of AMP is considerably improved by controlling nonconvexity parameters. |
| Tasks | |
| Published | 2019-02-20 |
| URL | http://arxiv.org/abs/1902.07436v1 |
| http://arxiv.org/pdf/1902.07436v1.pdf | |
| PWC | https://paperswithcode.com/paper/perfect-reconstruction-of-sparse-signals-with |
| Repo | |
| Framework | |
Text2Math: End-to-end Parsing Text into Math Expressions
| Title | Text2Math: End-to-end Parsing Text into Math Expressions |
| Authors | Yanyan Zou, Wei Lu |
| Abstract | We propose Text2Math, a model for semantically parsing text into math expressions. The model can be used to solve different math related problems including arithmetic word problems and equation parsing problems. Unlike previous approaches, we tackle the problem from an end-to-end structured prediction perspective where our algorithm aims to predict the complete math expression at once as a tree structure, where minimal manual efforts are involved in the process. Empirical results on benchmark datasets demonstrate the efficacy of our approach. |
| Tasks | Structured Prediction |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06571v1 |
| https://arxiv.org/pdf/1910.06571v1.pdf | |
| PWC | https://paperswithcode.com/paper/text2math-end-to-end-parsing-text-into-math |
| Repo | |
| Framework | |
Improving Visual Recognition using Ambient Sound for Supervision
| Title | Improving Visual Recognition using Ambient Sound for Supervision |
| Authors | Rohan Mahadev, Hongyu Lu |
| Abstract | Our brains combine vision and hearing to create a more elaborate interpretation of the world. When the visual input is insufficient, a rich panoply of sounds can be used to describe our surroundings. Since more than 1,000 hours of videos are uploaded to the internet everyday, it is arduous, if not impossible, to manually annotate these videos. Therefore, incorporating audio along with visual data without annotations is crucial for leveraging this explosion of data for recognizing and understanding objects and scenes. Owens,et.al suggest that a rich representation of the physical world can be learned by using a convolutional neural network to predict sound textures associated with a given video frame. We attempt to reproduce the claims from their experiments, of which the code is not publicly available. In addition, we propose improvements in the pretext task that result in better performance in other downstream computer vision tasks. |
| Tasks | |
| Published | 2019-12-25 |
| URL | https://arxiv.org/abs/1912.11659v1 |
| https://arxiv.org/pdf/1912.11659v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-visual-recognition-using-ambient |
| Repo | |
| Framework | |
Non-rigid Registration Method between 3D CT Liver Data and 2D Ultrasonic Images based on Demons Model
| Title | Non-rigid Registration Method between 3D CT Liver Data and 2D Ultrasonic Images based on Demons Model |
| Authors | Shuo Huang, Ke wu, Xiaolin Meng, Cheng Li |
| Abstract | The non-rigid registration between CT data and ultrasonic images of liver can facilitate the diagnosis and treatment, which has been widely studied in recent years. To improve the registration accuracy of the Demons model on the non-rigid registration between 3D CT liver data and 2D ultrasonic images, a novel boundary extraction and enhancement method based on radial directional local intuitionistic fuzzy entropy in the polar coordinates has been put forward, and a new registration workflow has been provided. Experiments show that our method can acquire high-accuracy registration results. Experiments also show that the accuracy of the results of our method is higher than that of the original Demons method and the Demons method using simulated ultrasonic image by Field II. The operation time of our registration workflow is about 30 seconds, and it can be used in the surgery. |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/2001.00035v1 |
| https://arxiv.org/pdf/2001.00035v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-rigid-registration-method-between-3d-ct |
| Repo | |
| Framework | |
Destination-aware Adaptive Traffic Flow Rule Aggregation in Software-Defined Networks
| Title | Destination-aware Adaptive Traffic Flow Rule Aggregation in Software-Defined Networks |
| Authors | Trung V. Phan, Mehrdad Hajizadeh, Nguyen Tuan Khai, Thomas Bauschert |
| Abstract | In this paper, we propose a destination-aware adaptive traffic flow rule aggregation (DATA) mechanism for facilitating traffic flow monitoring in SDN-based networks. This method adapts the number of flow table entries in SDN switches according to the level of detail of traffic flow information that other mechanisms (e.g. for traffic engineering, traffic monitoring, intrusion detection) require. It also prevents performance degradation of the SDN switches by keeping the number of flow table entries well below a critical level. This level is not preset as a hard threshold but learned during operation by using a machine-learning based algorithm. The DATA method is implemented within a RESTful application (DATA App) which monitors and analyzes the ongoing network traffic and provides instructions to the SDN controller to adapt the traffic flow matching strategies accordingly. A thorough performance evaluation of DATA is conducted in an SDN emulation environment. The results show that—compared to the default behavior of common SDN controllers—the proposed DATA approach yields significant SDN switch performance improvements while still providing detailed traffic flow information on demand. |
| Tasks | Intrusion Detection |
| Published | 2019-09-07 |
| URL | https://arxiv.org/abs/1909.03059v1 |
| https://arxiv.org/pdf/1909.03059v1.pdf | |
| PWC | https://paperswithcode.com/paper/destination-aware-adaptive-traffic-flow-rule |
| Repo | |
| Framework | |
Analysis of SparseHash: an efficient embedding of set-similarity via sparse projections
| Title | Analysis of SparseHash: an efficient embedding of set-similarity via sparse projections |
| Authors | Diego Valsesia, Sophie Marie Fosson, Chiara Ravazzi, Tiziano Bianchi, Enrico Magli |
| Abstract | Embeddings provide compact representations of signals in order to perform efficient inference in a wide variety of tasks. In particular, random projections are common tools to construct Euclidean distance-preserving embeddings, while hashing techniques are extensively used to embed set-similarity metrics, such as the Jaccard coefficient. In this letter, we theoretically prove that a class of random projections based on sparse matrices, called SparseHash, can preserve the Jaccard coefficient between the supports of sparse signals, which can be used to estimate set similarities. Moreover, besides the analysis, we provide an efficient implementation and we test the performance in several numerical experiments, both on synthetic and real datasets. |
| Tasks | |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.01802v1 |
| https://arxiv.org/pdf/1909.01802v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-sparsehash-an-efficient-embedding |
| Repo | |
| Framework | |
Adversarial Deep Learning for Over-the-Air Spectrum Poisoning Attacks
| Title | Adversarial Deep Learning for Over-the-Air Spectrum Poisoning Attacks |
| Authors | Yalin E. Sagduyu, Yi Shi, Tugba Erpek |
| Abstract | An adversarial deep learning approach is presented to launch over-the-air spectrum poisoning attacks. A transmitter applies deep learning on its spectrum sensing results to predict idle time slots for data transmission. In the meantime, an adversary learns the transmitter’s behavior (exploratory attack) by building another deep neural network to predict when transmissions will succeed. The adversary falsifies (poisons) the transmitter’s spectrum sensing data over the air by transmitting during the short spectrum sensing period of the transmitter. Depending on whether the transmitter uses the sensing results as test data to make transmit decisions or as training data to retrain its deep neural network, either it is fooled into making incorrect decisions (evasion attack), or the transmitter’s algorithm is retrained incorrectly for future decisions (causative attack). Both attacks are energy efficient and hard to detect (stealth) compared to jamming the long data transmission period, and substantially reduce the throughput. A dynamic defense is designed for the transmitter that deliberately makes a small number of incorrect transmissions (selected by the confidence score on channel classification) to manipulate the adversary’s training data. This defense effectively fools the adversary (if any) and helps the transmitter sustain its throughput with or without an adversary present. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00500v1 |
| https://arxiv.org/pdf/1911.00500v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-deep-learning-for-over-the-air |
| Repo | |
| Framework | |
TEST: an End-to-End Network Traffic Examination and Identification Framework Based on Spatio-Temporal Features Extraction
| Title | TEST: an End-to-End Network Traffic Examination and Identification Framework Based on Spatio-Temporal Features Extraction |
| Authors | Yi Zeng, Zihao Qi, Wencheng Chen, Yanzhe Huang, Xingxin Zheng, Han Qiu |
| Abstract | With more encrypted network traffic gets involved in the Internet, how to effectively identify network traffic has become a top priority in the field. Accurate identification of the network traffic is the footstone of basic network services, say QoE, bandwidth allocation, and IDS. Previous identification methods either cannot deal with encrypted traffics or require experts to select tons of features to attain a relatively decent accuracy.In this paper, we present a Deep Learning based end-to-end network traffic identification framework, termed TEST, to avoid the aforementioned problems. CNN and LSTM are combined and implemented to help the machine automatically extract features from both special and time-related features of the raw traffic. The presented framework has two layers of structure, which made it possible to attain a remarkable accuracy on both encrypted traffic classification and intrusion detection tasks. The experimental results demonstrate that our model can outperform previous methods with a state-of-the-art accuracy of 99.98%. |
| Tasks | Intrusion Detection |
| Published | 2019-08-26 |
| URL | https://arxiv.org/abs/1908.10271v1 |
| https://arxiv.org/pdf/1908.10271v1.pdf | |
| PWC | https://paperswithcode.com/paper/test-an-end-to-end-network-traffic |
| Repo | |
| Framework | |
Surreal: Complex-Valued Deep Learning as Principled Transformations on a Rotational Lie Group
| Title | Surreal: Complex-Valued Deep Learning as Principled Transformations on a Rotational Lie Group |
| Authors | Rudrasis Chakraborty, Yifei Xing, Stella Yu |
| Abstract | Complex-valued deep learning has attracted increasing attention in recent years, due to its versatility and ability to capture more information. However, the lack of well-defined complex-valued operations remains a bottleneck for further advancement. In this work, we propose a geometric way to define deep neural networks on the space of complex numbers by utilizing weighted Fr'echet mean. We mathematically prove the viability of our algorithm. We also define basic building blocks such as convolution, non-linearity, and residual connections tailored for the space of complex numbers. To demonstrate the effectiveness of our proposed model, we compare our complex-valued network comprehensively with its real state-of-the-art counterpart on the MSTAR classification task and achieve better performance, while utilizing less than 1% of the parameters. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.11334v1 |
| https://arxiv.org/pdf/1910.11334v1.pdf | |
| PWC | https://paperswithcode.com/paper/surreal-complex-valued-deep-learning-as |
| Repo | |
| Framework | |
Automatic Relevance Determination Bayesian Neural Networks for Credit Card Default Modelling
| Title | Automatic Relevance Determination Bayesian Neural Networks for Credit Card Default Modelling |
| Authors | Rendani Mbuvha, Illyes Boulkaibet, Tshilidzi Marwala |
| Abstract | Credit risk modelling is an integral part of the global financial system. While there has been great attention paid to neural network models for credit default prediction, such models often lack the required interpretation mechanisms and measures of the uncertainty around their predictions. This work develops and compares Bayesian Neural Networks(BNNs) for credit card default modelling. This includes a BNNs trained by Gaussian approximation and the first implementation of BNNs trained by Hybrid Monte Carlo(HMC) in credit risk modelling. The results on the Taiwan Credit Dataset show that BNNs with Automatic Relevance Determination(ARD) outperform normal BNNs without ARD. The results also show that BNNs trained by Gaussian approximation display similar predictive performance to those trained by the HMC. The results further show that BNN with ARD can be used to draw inferences about the relative importance of different features thus critically aiding decision makers in explaining model output to consumers. The robustness of this result is reinforced by high levels of congruence between the features identified as important using the two different approaches for training BNNs. |
| Tasks | |
| Published | 2019-06-14 |
| URL | https://arxiv.org/abs/1906.06382v1 |
| https://arxiv.org/pdf/1906.06382v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-relevance-determination-bayesian |
| Repo | |
| Framework | |
