Paper Group ANR 1730
Risk Structures: Towards Engineering Risk-aware Autonomous Systems. Deep Built-Structure Counting in Satellite Imagery Using Attention Based Re-Weighting. Unsupervised Feature Learning for Environmental Sound Classification Using Weighted Cycle-Consistent Generative Adversarial Network. The capacity of feedforward neural networks. Hyperspectral Ima …
Risk Structures: Towards Engineering Risk-aware Autonomous Systems
| Title | Risk Structures: Towards Engineering Risk-aware Autonomous Systems |
| Authors | Mario Gleirscher |
| Abstract | Inspired by widely-used techniques of causal modelling in risk, failure, and accident analysis, this work discusses a compositional framework for risk modelling. Risk models capture fragments of the space of risky events likely to occur when operating a machine in a given environment. Moreover, one can build such models into machines such as autonomous robots, to equip them with the ability of risk-aware perception, monitoring, decision making, and control. With the notion of a risk factor as the modelling primitive, the framework provides several means to construct and shape risk models. Relational and algebraic properties are investigated and proofs support the validity and consistency of these properties over the corresponding models. Several examples throughout the discussion illustrate the applicability of the concepts. Overall, this work focuses on the qualitative treatment of risk with the outlook of transferring these results to probabilistic refinements of the discussed framework. |
| Tasks | Decision Making |
| Published | 2019-04-23 |
| URL | http://arxiv.org/abs/1904.10386v1 |
| http://arxiv.org/pdf/1904.10386v1.pdf | |
| PWC | https://paperswithcode.com/paper/risk-structures-towards-engineering-risk |
| Repo | |
| Framework | |
Deep Built-Structure Counting in Satellite Imagery Using Attention Based Re-Weighting
| Title | Deep Built-Structure Counting in Satellite Imagery Using Attention Based Re-Weighting |
| Authors | Anza Shakeel, Waqas Sultani, Mohsen Ali |
| Abstract | In this paper, we attempt to address the challenging problem of counting built-structures in the satellite imagery. Building density is a more accurate estimate of the population density, urban area expansion and its impact on the environment, than the built-up area segmentation. However, building shape variances, overlapping boundaries, and variant densities make this a complex task. To tackle this difficult problem, we propose a deep learning based regression technique for counting built-structures in satellite imagery. Our proposed framework intelligently combines features from different regions of satellite image using attention based re-weighting techniques. Multiple parallel convolutional networks are designed to capture information at different granulates. These features are combined into the FusionNet which is trained to weigh features from different granularity differently, allowing us to predict a precise building count. To train and evaluate the proposed method, we put forward a new large-scale and challenging built-structure-count dataset. Our dataset is constructed by collecting satellite imagery from diverse geographical areas (planes, urban centers, deserts, etc.,) across the globe (Asia, Europe, North America, and Africa) and captures the wide density of built structures. Detailed experimental results and analysis validate the proposed technique. FusionNet has Mean Absolute Error of 3.65 and R-squared measure of 88% over the testing data. Finally, we perform the test on the 274:3 ? 103 m2 of the unseen region, with the error of 19 buildings off the 656 buildings in that area. |
| Tasks | |
| Published | 2019-04-01 |
| URL | http://arxiv.org/abs/1904.00674v1 |
| http://arxiv.org/pdf/1904.00674v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-built-structure-counting-in-satellite |
| Repo | |
| Framework | |
Unsupervised Feature Learning for Environmental Sound Classification Using Weighted Cycle-Consistent Generative Adversarial Network
| Title | Unsupervised Feature Learning for Environmental Sound Classification Using Weighted Cycle-Consistent Generative Adversarial Network |
| Authors | Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich |
| Abstract | In this paper we propose a novel environmental sound classification approach incorporating unsupervised feature learning from codebook via spherical $K$-Means++ algorithm and a new architecture for high-level data augmentation. The audio signal is transformed into a 2D representation using a discrete wavelet transform (DWT). The DWT spectrograms are then augmented by a novel architecture for cycle-consistent generative adversarial network. This high-level augmentation bootstraps generated spectrograms in both intra and inter class manners by translating structural features from sample to sample. A codebook is built by coding the DWT spectrograms with the speeded-up robust feature detector (SURF) and the K-Means++ algorithm. The Random Forest is our final learning algorithm which learns the environmental sound classification task from the clustered codewords in the codebook. Experimental results in four benchmarking environmental sound datasets (ESC-10, ESC-50, UrbanSound8k, and DCASE-2017) have shown that the proposed classification approach outperforms the state-of-the-art classifiers in the scope, including advanced and dense convolutional neural networks such as AlexNet and GoogLeNet, improving the classification rate between 3.51% and 14.34%, depending on the dataset. |
| Tasks | Data Augmentation, Environmental Sound Classification |
| Published | 2019-04-08 |
| URL | https://arxiv.org/abs/1904.04221v2 |
| https://arxiv.org/pdf/1904.04221v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-feature-learning-for |
| Repo | |
| Framework | |
The capacity of feedforward neural networks
| Title | The capacity of feedforward neural networks |
| Authors | Pierre Baldi, Roman Vershynin |
| Abstract | A long standing open problem in the theory of neural networks is the development of quantitative methods to estimate and compare the capabilities of different architectures. Here we define the capacity of an architecture by the binary logarithm of the number of functions it can compute, as the synaptic weights are varied. The capacity provides an upper bound on the number of bits that can be extracted from the training data and stored in the architecture during learning. We study the capacity of layered, fully-connected, architectures of linear threshold neurons with $L$ layers of size $n_1,n_2, \ldots, n_L$ and show that in essence the capacity is given by a cubic polynomial in the layer sizes: $C(n_1,\ldots, n_L)=\sum_{k=1}^{L-1} \min(n_1,\ldots,n_k)n_kn_{k+1}$, where layers that are smaller than all previous layers act as bottlenecks. In proving the main result, we also develop new techniques (multiplexing, enrichment, and stacking) as well as new bounds on the capacity of finite sets. We use the main result to identify architectures with maximal or minimal capacity under a number of natural constraints. This leads to the notion of structural regularization for deep architectures. While in general, everything else being equal, shallow networks compute more functions than deep networks, the functions computed by deep networks are more regular and “interesting”. |
| Tasks | |
| Published | 2019-01-02 |
| URL | http://arxiv.org/abs/1901.00434v2 |
| http://arxiv.org/pdf/1901.00434v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-capacity-of-feedforward-neural-networks |
| Repo | |
| Framework | |
Hyperspectral Image Classification with Deep Metric Learning and Conditional Random Field
| Title | Hyperspectral Image Classification with Deep Metric Learning and Conditional Random Field |
| Authors | Yi Liang, Xin Zhao, Alan J. X. Guo, Fei Zhu |
| Abstract | To improve the classification performance in the context of hyperspectral image processing, many works have been developed based on two common strategies, namely the spatial-spectral information integration and the utilization of neural networks. However, both strategies typically require more training data than the classical algorithms, aggregating the shortage of labeled samples. In this letter, we propose a novel framework that organically combines the spectrum-based deep metric learning model and the conditional random field algorithm. The deep metric learning model is supervised by the center loss to produce spectrum-based features that gather more tightly in Euclidean space within classes. The conditional random field with Gaussian edge potentials, which is firstly proposed for image segmentation tasks, is introduced to give the pixel-wise classification over the hyperspectral image by utilizing both the geographical distances between pixels and the Euclidean distances between the features produced by the deep metric learning model. The proposed framework is trained by spectral pixels at the deep metric learning stage and utilizes the half handcrafted spatial features at the conditional random field stage. This settlement alleviates the shortage of training data to some extent. Experiments on two real hyperspectral images demonstrate the advantages of the proposed method in terms of both classification accuracy and computation cost. |
| Tasks | Hyperspectral Image Classification, Image Classification, Metric Learning, Semantic Segmentation |
| Published | 2019-03-04 |
| URL | https://arxiv.org/abs/1903.06258v2 |
| https://arxiv.org/pdf/1903.06258v2.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-image-classification-with-deep |
| Repo | |
| Framework | |
Fourier Neural Networks: A Comparative Study
| Title | Fourier Neural Networks: A Comparative Study |
| Authors | Abylay Zhumekenov, Malika Uteuliyeva, Olzhas Kabdolov, Rustem Takhanov, Zhenisbek Assylbekov, Alejandro J. Castro |
| Abstract | We review neural network architectures which were motivated by Fourier series and integrals and which are referred to as Fourier neural networks. These networks are empirically evaluated in synthetic and real-world tasks. Neither of them outperforms the standard neural network with sigmoid activation function in the real-world tasks. All neural networks, both Fourier and the standard one, empirically demonstrate lower approximation error than the truncated Fourier series when it comes to an approximation of a known function of multiple variables. |
| Tasks | |
| Published | 2019-02-08 |
| URL | http://arxiv.org/abs/1902.03011v1 |
| http://arxiv.org/pdf/1902.03011v1.pdf | |
| PWC | https://paperswithcode.com/paper/fourier-neural-networks-a-comparative-study |
| Repo | |
| Framework | |
Norms for Beneficial A.I.: A Computational Analysis of the Societal Value Alignment Problem
| Title | Norms for Beneficial A.I.: A Computational Analysis of the Societal Value Alignment Problem |
| Authors | Pedro Fernandes, Francisco C. Santos, Manuel Lopes |
| Abstract | The rise of artificial intelligence (A.I.) based systems has the potential to benefit adopters and society as a whole. However, these systems may also enclose potential conflicts and unintended consequences. Notably, people will only adopt an A.I. system if it confers them an advantage, at which point non-adopters might push for a strong regulation if that advantage for adopters is at a cost for them. Here we propose a stochastic game theoretical model for these conflicts. We frame our results under the current discussion on ethical A.I. and the conflict between individual and societal gains, the societal value alignment problem. We test the arising equilibria in the adoption of A.I. technology under different norms followed by artificial agents, their ensuing benefits, and the emergent levels of wealth inequality. We show that without any regulation, purely selfish A.I. systems will have the strongest advantage, even when a utilitarian A.I. provides a more significant benefit for the individual and the society. Nevertheless, we show that it is possible to develop human conscious A.I. systems that reach an equilibrium where the gains for the adopters are not at a cost for non-adopters while increasing the overall fitness and lowering inequality. However, as shown, a self-organized adoption of such policies would require external regulation. |
| Tasks | |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1907.03843v1 |
| https://arxiv.org/pdf/1907.03843v1.pdf | |
| PWC | https://paperswithcode.com/paper/norms-for-beneficial-ai-a-computational |
| Repo | |
| Framework | |
On Designing Machine Learning Models for Malicious Network Traffic Classification
| Title | On Designing Machine Learning Models for Malicious Network Traffic Classification |
| Authors | Talha Ongun, Timothy Sakharaov, Simona Boboila, Alina Oprea, Tina Eliassi-Rad |
| Abstract | Machine learning (ML) started to become widely deployed in cyber security settings for shortening the detection cycle of cyber attacks. To date, most ML-based systems are either proprietary or make specific choices of feature representations and machine learning models. The success of these techniques is difficult to assess as public benchmark datasets are currently unavailable. In this paper, we provide concrete guidelines and recommendations for using supervised ML in cyber security. As a case study, we consider the problem of botnet detection from network traffic data. Among our findings we highlight that: (1) feature representations should take into consideration attack characteristics; (2) ensemble models are well-suited to handle class imbalance; (3) the granularity of ground truth plays an important role in the success of these methods. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04846v1 |
| https://arxiv.org/pdf/1907.04846v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-designing-machine-learning-models-for |
| Repo | |
| Framework | |
A Machine Learning based Robust Prediction Model for Real-life Mobile Phone Data
| Title | A Machine Learning based Robust Prediction Model for Real-life Mobile Phone Data |
| Authors | Iqbal H. Sarker |
| Abstract | Real-life mobile phone data may contain noisy instances, which is a fundamental issue for building a prediction model with many potential negative consequences. The complexity of the inferred model may increase, may arise overfitting problem, and thereby the overall prediction accuracy of the model may decrease. In this paper, we address these issues and present a robust prediction model for real-life mobile phone data of individual users, in order to improve the prediction accuracy of the model. In our robust model, we first effectively identify and eliminate the noisy instances from the training dataset by determining a dynamic noise threshold using naive Bayes classifier and laplace estimator, which may differ from user-to-user according to their unique behavioral patterns. After that, we employ the most popular rule-based machine learning classification technique, i.e., decision tree, on the noise-free quality dataset to build the prediction model. Experimental results on the real-life mobile phone datasets (e.g., phone call log) of individual mobile phone users, show the effectiveness of our robust model in terms of precision, recall and f-measure. |
| Tasks | |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.07588v1 |
| http://arxiv.org/pdf/1902.07588v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-based-robust-prediction |
| Repo | |
| Framework | |
Towards a Robust Aerial Cinematography Platform: Localizing and Tracking Moving Targets in Unstructured Environments
| Title | Towards a Robust Aerial Cinematography Platform: Localizing and Tracking Moving Targets in Unstructured Environments |
| Authors | Rogerio Bonatti, Cherie Ho, Wenshan Wang, Sanjiban Choudhury, Sebastian Scherer |
| Abstract | The use of drones for aerial cinematography has revolutionized several applications and industries that require live and dynamic camera viewpoints such as entertainment, sports, and security. However, safely controlling a drone while filming a moving target usually requires multiple expert human operators; hence the need for an autonomous cinematographer. Current approaches have severe real-life limitations such as requiring fully scripted scenes, high-precision motion-capture systems or GPS tags to localize targets, and prior maps of the environment to avoid obstacles and plan for occlusion. In this work, we overcome such limitations and propose a complete system for aerial cinematography that combines: (1) a vision-based algorithm for target localization; (2) a real-time incremental 3D signed-distance map algorithm for occlusion and safety computation; and (3) a real-time camera motion planner that optimizes smoothness, collisions, occlusions and artistic guidelines. We evaluate robustness and real-time performance in series of field experiments and simulations by tracking dynamic targets moving through unknown, unstructured environments. Finally, we verify that despite removing previous limitations, our system achieves state-of-the-art performance. Videos of the system in action can be seen at https://youtu.be/ZE9MnCVmumc |
| Tasks | Motion Capture, Pose Estimation |
| Published | 2019-04-04 |
| URL | https://arxiv.org/abs/1904.02319v2 |
| https://arxiv.org/pdf/1904.02319v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-robust-aerial-cinematography |
| Repo | |
| Framework | |
A model for prohibition and obligation dilemmas generation in virtual environments
| Title | A model for prohibition and obligation dilemmas generation in virtual environments |
| Authors | Azzeddine Benabbou, Domitile Lourdeaux, Dominique Lenne |
| Abstract | Under the project Maccoy Critical, we would like to train individuals, in virtual environments, to handle critical situations such as dilemmas. These latter refer to situations where there is no ``good’’ solution. In other words, situations that lead to negative consequences whichever choice is made. Our objective is to use Knowledge Models to extract necessary properties for dilemmas to emerge. To do so, our approach consists in developing a Scenario Orchestration System that generates dilemma situations dynamically without having to write them beforehand. In this paper we present this approach and expose a proof of concept of the generation process. | |
| Tasks | |
| Published | 2019-01-17 |
| URL | http://arxiv.org/abs/1901.09790v1 |
| http://arxiv.org/pdf/1901.09790v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-model-for-prohibition-and-obligation |
| Repo | |
| Framework | |
Acoustic scene analysis with multi-head attention networks
| Title | Acoustic scene analysis with multi-head attention networks |
| Authors | Weimin Wang, Weiran Wang, Ming Sun, Chao Wang |
| Abstract | Acoustic Scene Classification (ASC) is a challenging task, as a single scene may involve multiple events that contain complex sound patterns. For example, a cooking scene may contain several sound sources including silverware clinking, chopping, frying, etc. What complicates ASC more is that classes of different activities could have overlapping sounds patterns (e.g. both cooking and dishwashing could have silverware clinking sound). In this paper, we propose a multi-head attention network to model the complex temporal input structures for ASC. The proposed network takes the audio’s time-frequency representation as input, and it leverages standard VGG plus LSTM layers to extract high-level feature representation. Further more, it applies multiple attention heads to summarize various patterns of sound events into fixed dimensional representation, for the purpose of final scene classification. The whole network is trained in an end-to-end fashion with back-propagation. Experimental results confirm that our model discovers meaningful sound patterns through the attention mechanism, without using explicit supervision in the alignment. We evaluated our proposed model using DCASE 2018 Task 5 dataset, and achieved competitive performance on par with previous winner’s results. |
| Tasks | Acoustic Scene Classification, Scene Classification |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.08961v1 |
| https://arxiv.org/pdf/1909.08961v1.pdf | |
| PWC | https://paperswithcode.com/paper/acoustic-scene-analysis-with-multi-head |
| Repo | |
| Framework | |
DeePCCI: Deep Learning-based Passive Congestion Control Identification
| Title | DeePCCI: Deep Learning-based Passive Congestion Control Identification |
| Authors | Constantin Sander, Jan Rüth, Oliver Hohlfeld, Klaus Wehrle |
| Abstract | Transport protocols use congestion control to avoid overloading a network. Nowadays, different congestion control variants exist that influence performance. Studying their use is thus relevant, but it is hard to identify which variant is used. While passive identification approaches exist, these require detailed domain knowledge and often also rely on outdated assumptions about how congestion control operates and what data is accessible. We present DeePCCI, a passive, deep learning-based congestion control identification approach which does not need any domain knowledge other than training traffic of a congestion control variant. By only using packet arrival data, it is also directly applicable to encrypted (transport header) traffic. DeePCCI is therefore more easily extendable and can also be used with QUIC. |
| Tasks | |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02323v1 |
| https://arxiv.org/pdf/1907.02323v1.pdf | |
| PWC | https://paperswithcode.com/paper/deepcci-deep-learning-based-passive |
| Repo | |
| Framework | |
Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations
| Title | Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations |
| Authors | Rao Muhammad Umer, Gian Luca Foresti, Christian Micheloni |
| Abstract | Single Image Super-Resolution (SISR) aims to generate a high-resolution (HR) image of a given low-resolution (LR) image. The most of existing convolutional neural network (CNN) based SISR methods usually take an assumption that a LR image is only bicubicly down-sampled version of an HR image. However, the true degradation (i.e. the LR image is a bicubicly downsampled, blurred and noisy version of an HR image) of a LR image goes beyond the widely used bicubic assumption, which makes the SISR problem highly ill-posed nature of inverse problems. To address this issue, we propose a deep SISR network that works for blur kernels of different sizes, and different noise levels in an unified residual CNN-based denoiser network, which significantly improves a practical CNN-based super-resolver for real applications. Extensive experimental results on synthetic LR datasets and real images demonstrate that our proposed method not only can produce better results on more realistic degradation but also computational efficient to practical SISR applications. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03748v1 |
| https://arxiv.org/pdf/1909.03748v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-super-resolution-network-for-single |
| Repo | |
| Framework | |
Classifying Vietnamese Disease Outbreak Reports with Important Sentences and Rich Features
| Title | Classifying Vietnamese Disease Outbreak Reports with Important Sentences and Rich Features |
| Authors | Son Doan, Nguyen Thi Ngoc Vinh, Tu Minh Phuong |
| Abstract | Text classification is an important field of research from mid 90s up to now. It has many applications, one of them is in Web-based biosurveillance systems which identify and summarize online disease outbreak reports. In this paper we focus on classifying Vietnamese disease outbreak reports. We investigate important properties of disease outbreak reports, e.g., sentences containing names of outbreak disease, locations. Evaluation on 10-time 10- fold cross-validation using the Support Vector Machine algorithm shows that using sentences containing disease outbreak names with its preceding/following sentences in combination with location features achieve the best F-score with 86.67% - an improvement of 0.38% in comparison to using all raw text. Our results suggest that using important sentences and rich feature can improve performance of Vietnamese disease outbreak text classification. |
| Tasks | Text Classification |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09883v1 |
| https://arxiv.org/pdf/1911.09883v1.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-vietnamese-disease-outbreak |
| Repo | |
| Framework | |
