Paper Group ANR 699
On the Initialization of Long Short-Term Memory Networks. Fairness in Reinforcement Learning. Modified online Newton step based on element wise multiplication. Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance. Deep Learning for Over-the-Air Non-Orthogonal Signal Classification. Learning pa …
On the Initialization of Long Short-Term Memory Networks
| Title | On the Initialization of Long Short-Term Memory Networks |
| Authors | Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai, Marc Modat, M. Jorge Cardoso, Sebastien Ourselin, Lauge Sorensen |
| Abstract | Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM) networks. It is based on a normalized random initialization of the network weights that aims at preserving the variance of the network input and output in the same range. The method is applied to standard LSTMs for univariate time series regression and to LSTMs robust to missing values for multivariate disease progression modeling. The results show that in all cases, the proposed initialization method outperforms the state-of-the-art initialization techniques in terms of training convergence and generalization performance of the obtained solution. |
| Tasks | Time Series |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.10454v1 |
| https://arxiv.org/pdf/1912.10454v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-initialization-of-long-short-term |
| Repo | |
| Framework | |
Fairness in Reinforcement Learning
| Title | Fairness in Reinforcement Learning |
| Authors | Paul Weng |
| Abstract | Decision support systems (e.g., for ecological conservation) and autonomous systems (e.g., adaptive controllers in smart cities) start to be deployed in real applications. Although their operations often impact many users or stakeholders, no fairness consideration is generally taken into account in their design, which could lead to completely unfair outcomes for some users or stakeholders. To tackle this issue, we advocate for the use of social welfare functions that encode fairness and present this general novel problem in the context of (deep) reinforcement learning, although it could possibly be extended to other machine learning tasks. |
| Tasks | |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10323v1 |
| https://arxiv.org/pdf/1907.10323v1.pdf | |
| PWC | https://paperswithcode.com/paper/fairness-in-reinforcement-learning-2 |
| Repo | |
| Framework | |
Modified online Newton step based on element wise multiplication
| Title | Modified online Newton step based on element wise multiplication |
| Authors | Charanjeet, Anuj Sharma |
| Abstract | The second order method as Newton Step is a suitable technique in Online Learning to guarantee regret bound. The large data is a challenge in Newton method to store second order matrices as hessian. In this paper, we have proposed an modified online Newton step that store first and second order matrices of dimension m (classes) by d (features). we have used element wise arithmetic operation to retain matrices size same. The modified second order matrix size results in faster computations. Also, the mistake rate is at par with respect to popular methods in literature. The experiments outcome indicate that proposed method could be helpful to handle large multi class datasets in common desktop machines using second order method as Newton step. |
| Tasks | |
| Published | 2019-04-11 |
| URL | http://arxiv.org/abs/1904.05633v2 |
| http://arxiv.org/pdf/1904.05633v2.pdf | |
| PWC | https://paperswithcode.com/paper/modified-online-newton-step-based-on-element |
| Repo | |
| Framework | |
Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance
| Title | Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance |
| Authors | Vinay Uday Prabhu, Dian Ang Yap, Alexander Wang, John Whaley |
| Abstract | Attribute prior avoidance entails subconscious or willful non-modeling of (meta)attributes that datasets are oft born with, such as the 40 semantic facial attributes associated with the CelebA and CelebA-HQ datasets. The consequences of this infirmity, we discover, are especially stark in state-of-the-art deep generative models learned on these datasets that just model the pixel-space measurements, resulting in an inter-attribute bias-laden latent space. This viscerally manifests itself when we perform face manipulation experiments based on latent vector interpolations. In this paper, we address this and propose a post-hoc solution that utilizes an Ising attribute prior learned in the attribute space and showcase its efficacy via qualitative experiments. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.12917v1 |
| https://arxiv.org/pdf/1907.12917v1.pdf | |
| PWC | https://paperswithcode.com/paper/covering-up-bias-in-celeba-like-datasets-with |
| Repo | |
| Framework | |
Deep Learning for Over-the-Air Non-Orthogonal Signal Classification
| Title | Deep Learning for Over-the-Air Non-Orthogonal Signal Classification |
| Authors | Tongyang Xu, Izzat Darwazeh |
| Abstract | Non-cooperative communications, where a receiver can automatically distinguish and classify transmitted signal formats prior to detection, are desirable for low-cost and low-latency systems. This work focuses on the deep learning enabled blind classification of multi-carrier signals covering their orthogonal and non-orthogonal varieties. We define two signal groups, in which Type-I includes signals with large feature diversity while Type-II has strong feature similarity. We evaluate time-domain and frequency-domain convolutional neural network (CNN) models in simulation with wireless channel/hardware impairments. Simulation results reveal that the time-domain neural network training is more efficient than its frequency-domain counterpart in terms of classification accuracy and computational complexity. In addition, the time-domain CNN models can classify Type-I signals with high accuracy but reduced performance in Type-II signals because of their high signal feature similarity. Experimental systems are designed and tested, using software defined radio (SDR) devices, operated for different signal formats to form full wireless communication links with line-of-sight and non-line-of-sight scenarios. Testing, using four different time-domain CNN models, showed the pre-trained CNN models to have limited efficiency and utility due to the mismatch between the analytical/simulation and practical/real-world environments. Transfer learning, which is an approach to fine-tune learnt signal features, is applied based on measured over-the-air time-domain signal samples. Experimental results indicate that transfer learning based CNN can efficiently distinguish different signal formats in both line-of-sight and non-line-of-sight scenarios with great accuracy improvement relative to the non-transfer-learning approaches. |
| Tasks | Transfer Learning |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06174v1 |
| https://arxiv.org/pdf/1911.06174v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-over-the-air-non-orthogonal |
| Repo | |
| Framework | |
Learning pairwise Markov network structures using correlation neighborhoods
| Title | Learning pairwise Markov network structures using correlation neighborhoods |
| Authors | Juri Kuronen, Jukka Corander, Johan Pensar |
| Abstract | Markov networks are widely studied and used throughout multivariate statistics and computer science. In particular, the problem of learning the structure of Markov networks from data without invoking chordality assumptions in order to retain expressiveness of the model class has been given a considerable attention in the recent literature, where numerous constraint-based or score-based methods have been introduced. Here we develop a new search algorithm for the network score-optimization that has several computational advantages and scales well to high-dimensional data sets. The key observation behind the algorithm is that the neighborhood of a variable can be efficiently captured using local penalized likelihood ratio (PLR) tests by exploiting an exponential decay of correlations across the neighborhood with an increasing graph-theoretic distance from the focus node. The candidate neighborhoods are then processed by a two-stage hill-climbing (HC) algorithm. Our approach, termed fully as PLRHC-BIC$_{0.5}$, compares favorably against the state-of-the-art methods in all our experiments spanning both low- and high-dimensional networks and a wide range of sample sizes. An efficient implementation of PLRHC-BIC$_{0.5}$ is freely available from the URL: https://github.com/jurikuronen/plrhc. |
| Tasks | |
| Published | 2019-10-30 |
| URL | https://arxiv.org/abs/1910.13832v1 |
| https://arxiv.org/pdf/1910.13832v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-pairwise-markov-network-structures |
| Repo | |
| Framework | |
Accurate Segmentation of Dermoscopic Images based on Local Binary Pattern Clustering
| Title | Accurate Segmentation of Dermoscopic Images based on Local Binary Pattern Clustering |
| Authors | Pedro M. M. Pereira, Rui Fonseca-Pinto, Rui Pedro Paiva, Luis M. N. Tavora, Pedro A. A. Assuncao, Sergio M. M. de Faria |
| Abstract | Segmentation is a key stage in dermoscopic image processing, where the accuracy of the border line that defines skin lesions is of utmost importance for subsequent algorithms (e.g., classification) and computer-aided early diagnosis of serious medical conditions. This paper proposes a novel segmentation method based on Local Binary Patterns (LBP), where LBP and K-Means clustering are combined to achieve a detailed delineation in dermoscopic images. In comparison with usual dermatologist-like segmentation (i.e., the available ground-truth), the proposed method is capable of finding more realistic borders of skin lesions, i.e., with much more detail. The results also exhibit reduced variability amongst different performance measures and they are consistent across different images. The proposed method can be applied for cell-based like segmentation adapted to the lesion border growing specificities. Hence, the method is suitable to follow the growth dynamics associated with the lesion border geometry in skin melanocytic images. |
| Tasks | |
| Published | 2019-02-17 |
| URL | http://arxiv.org/abs/1902.06347v3 |
| http://arxiv.org/pdf/1902.06347v3.pdf | |
| PWC | https://paperswithcode.com/paper/accurate-segmentation-of-dermoscopic-images |
| Repo | |
| Framework | |
Discovering Conditionally Salient Features with Statistical Guarantees
| Title | Discovering Conditionally Salient Features with Statistical Guarantees |
| Authors | Jaime Roquero Gimenez, James Zou |
| Abstract | The goal of feature selection is to identify important features that are relevant to explain an outcome variable. Most of the work in this domain has focused on identifying globally relevant features, which are features that are related to the outcome using evidence across the entire dataset. We study a more fine-grained statistical problem: conditional feature selection, where a feature may be relevant depending on the values of the other features. For example in genetic association studies, variant $A$ could be associated with the phenotype in the entire dataset, but conditioned on variant $B$ being present it might be independent of the phenotype. In this sense, variant $A$ is globally relevant, but conditioned on $B$ it is no longer locally relevant in that region of the feature space. We present a generalization of the knockoff procedure that performs conditional feature selection while controlling a generalization of the false discovery rate (FDR) to the conditional setting. By exploiting the feature/response model-free framework of the knockoffs, the quality of the statistical FDR guarantee is not degraded even when we perform conditional feature selections. We implement this method and present an algorithm that automatically partitions the feature space such that it enhances the differences between selected sets in different regions, and validate the statistical theoretical results with experiments. |
| Tasks | Feature Selection |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12177v1 |
| https://arxiv.org/pdf/1905.12177v1.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-conditionally-salient-features |
| Repo | |
| Framework | |
Convolutional Neural Network for Multipath Detection in GNSS Receivers
| Title | Convolutional Neural Network for Multipath Detection in GNSS Receivers |
| Authors | Evgenii Munin, Antoine Blais, Nicolas Couellan |
| Abstract | Global Navigation Satellite System (GNSS) signals are subject to different kinds of events causing significant errors in positioning. This work explores the application of Machine Learning (ML) methods of anomaly detection applied to GNSS receiver signals. More specifically, our study focuses on multipath contamination, using samples of the correlator output signal. The GPS L1 C/A signal data is used and sourced directly from the correlator output. To extract the important features and patterns from such data, we use deep convolutional neural networks (CNN), which have proven to be efficient in image analysis in particular. To take advantage of CNN, the correlator output signal is mapped as a 2D input image and fed to the convolutional layers of a neural network. The network automatically extracts the relevant features from the input samples and proceeds with the multipath detection. We train the CNN using synthetic signals. To optimize the model architecture with respect to the GNSS correlator complexity, the evaluation of the CNN performance is done as a function of the number of correlator output points. |
| Tasks | Anomaly Detection |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02347v1 |
| https://arxiv.org/pdf/1911.02347v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-network-for-multipath |
| Repo | |
| Framework | |
Speed Invariant Time Surface for Learning to Detect Corner Points with Event-Based Cameras
| Title | Speed Invariant Time Surface for Learning to Detect Corner Points with Event-Based Cameras |
| Authors | Jacques Manderscheid, Amos Sironi, Nicolas Bourdis, Davide Migliore, Vincent Lepetit |
| Abstract | We propose a learning approach to corner detection for event-based cameras that is stable even under fast and abrupt motions. Event-based cameras offer high temporal resolution, power efficiency, and high dynamic range. However, the properties of event-based data are very different compared to standard intensity images, and simple extensions of corner detection methods designed for these images do not perform well on event-based data. We first introduce an efficient way to compute a time surface that is invariant to the speed of the objects. We then show that we can train a Random Forest to recognize events generated by a moving corner from our time surface. Random Forests are also extremely efficient, and therefore a good choice to deal with the high capture frequency of event-based cameras —our implementation processes up to 1.6Mev/s on a single CPU. Thanks to our time surface formulation and this learning approach, our method is significantly more robust to abrupt changes of direction of the corners compared to previous ones. Our method also naturally assigns a confidence score for the corners, which can be useful for postprocessing. Moreover, we introduce a high-resolution dataset suitable for quantitative evaluation and comparison of corner detection methods for event-based cameras. We call our approach SILC, for Speed Invariant Learned Corners, and compare it to the state-of-the-art with extensive experiments, showing better performance. |
| Tasks | |
| Published | 2019-03-27 |
| URL | http://arxiv.org/abs/1903.11332v2 |
| http://arxiv.org/pdf/1903.11332v2.pdf | |
| PWC | https://paperswithcode.com/paper/speed-invariant-time-surface-for-learning-to |
| Repo | |
| Framework | |
Detecting Point Outliers Using Prune-based Outlier Factor (PLOF)
| Title | Detecting Point Outliers Using Prune-based Outlier Factor (PLOF) |
| Authors | Kasra Babaei, ZhiYuan Chen, Tomas Maul |
| Abstract | Outlier detection (also known as anomaly detection or deviation detection) is a process of detecting data points in which their patterns deviate significantly from others. It is common to have outliers in industry applications, which could be generated by different causes such as human error, fraudulent activities, or system failure. Recently, density-based methods have shown promising results, particularly among which Local Outlier Factor (LOF) is arguably dominating. However, one of the major drawbacks of LOF is that it is computationally expensive. Motivated by the mentioned problem, this research presents a novel pruning-based procedure in which the execution time of LOF is reduced while the performance is maintained. A novel Prune-based Local Outlier Factor (PLOF) approach is proposed, in which prior to employing LOF, outlierness of each data instance is measured. Next, based on a threshold, data instances that require further investigation are separated and LOF score is only computed for these points. Extensive experiments have been conducted and results are promising. Comparison experiments with the original LOF and two state-of-the-art variants of LOF have shown that PLOF produces higher accuracy and precision while reducing execution time. |
| Tasks | Anomaly Detection, Outlier Detection |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.01654v1 |
| https://arxiv.org/pdf/1911.01654v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-point-outliers-using-prune-based |
| Repo | |
| Framework | |
Real-Time Sensor Anomaly Detection and Recovery in Connected Automated Vehicle Sensors
| Title | Real-Time Sensor Anomaly Detection and Recovery in Connected Automated Vehicle Sensors |
| Authors | Yiyang Wang, Neda Masoud, Anahita Khojandi |
| Abstract | In this paper we propose a novel observer-based method to improve the safety and security of connected and automated vehicle (CAV) transportation. The proposed method combines model-based signal filtering and anomaly detection methods. Specifically, we use adaptive extended Kalman filter (AEKF) to smooth sensor readings of a CAV based on a nonlinear car-following model. Using the car-following model the subject vehicle (i.e., the following vehicle) utilizes the leading vehicle’s information to detect sensor anomalies by employing previously-trained One Class Support Vector Machine (OCSVM) models. This approach allows the AEKF to estimate the state of a vehicle not only based on the vehicle’s location and speed, but also by taking into account the state of the surrounding traffic. A communication time delay factor is considered in the car-following model to make it more suitable for real-world applications. Our experiments show that compared with the AEKF with a traditional $\chi^2$-detector, our proposed method achieves a better anomaly detection performance. We also demonstrate that a larger time delay factor has a negative impact on the overall detection performance. |
| Tasks | Anomaly Detection |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01531v1 |
| https://arxiv.org/pdf/1911.01531v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-sensor-anomaly-detection-and |
| Repo | |
| Framework | |
Unexpected Effects of Online K-means Clustering
| Title | Unexpected Effects of Online K-means Clustering |
| Authors | Michal Moshkovitz |
| Abstract | In this paper we study k-means clustering in the online setting. In the offline setting the main parameters are number of centers, k, and size of the dataset, n. Performance guarantees are given as a function of these parameters. In the online setting new factors come into place: the ordering of the dataset and whether n is known in advance or not. One of the main results of this paper is the discovery that these new factors have dramatic effects on the quality of the clustering algorithms. For example, for constant k: (1) $\Omega(n)$ centers are needed if the order is arbitrary, (2) if the order is random and n is unknown in advance, the number of centers reduces to $\Theta(logn)$, and (3) if n is known, then the number of centers reduces to a constant. For different values of the new factors, we show upper and lower bounds that are exactly the same up to a constant, thus achieving optimal bounds. |
| Tasks | |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.06818v1 |
| https://arxiv.org/pdf/1908.06818v1.pdf | |
| PWC | https://paperswithcode.com/paper/unexpected-effects-of-online-k-means |
| Repo | |
| Framework | |
Destruction of Image Steganography using Generative Adversarial Networks
| Title | Destruction of Image Steganography using Generative Adversarial Networks |
| Authors | Isaac Corley, Jonathan Lwowski, Justin Hoffman |
| Abstract | Digital image steganalysis, or the detection of image steganography, has been studied in depth for years and is driven by Advanced Persistent Threat (APT) groups’, such as APT37 Reaper, utilization of steganographic techniques to transmit additional malware to perform further post-exploitation activity on a compromised host. However, many steganalysis algorithms are constrained to work with only a subset of all possible images in the wild or are known to produce a high false positive rate. This results in blocking any suspected image being an unreasonable policy. A more feasible policy is to filter suspicious images prior to reception by the host machine. However, how does one optimally filter specifically to obfuscate or remove image steganography while avoiding degradation of visual image quality in the case that detection of the image was a false positive? We propose the Deep Digital Steganography Purifier (DDSP), a Generative Adversarial Network (GAN) which is optimized to destroy steganographic content without compromising the perceptual quality of the original image. As verified by experimental results, our model is capable of providing a high rate of destruction of steganographic image content while maintaining a high visual quality in comparison to other state-of-the-art filtering methods. Additionally, we test the transfer learning capability of generalizing to to obfuscate real malware payloads embedded into different image file formats and types using an unseen steganographic algorithm and prove that our model can in fact be deployed to provide adequate results. |
| Tasks | Image Steganography, Transfer Learning |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.10070v1 |
| https://arxiv.org/pdf/1912.10070v1.pdf | |
| PWC | https://paperswithcode.com/paper/destruction-of-image-steganography-using |
| Repo | |
| Framework | |
Modeling Global Syntactic Variation in English Using Dialect Classification
| Title | Modeling Global Syntactic Variation in English Using Dialect Classification |
| Authors | Jonathan Dunn |
| Abstract | This paper evaluates global-scale dialect identification for 14 national varieties of English as a means for studying syntactic variation. The paper makes three main contributions: (i) introducing data-driven language mapping as a method for selecting the inventory of national varieties to include in the task; (ii) producing a large and dynamic set of syntactic features using grammar induction rather than focusing on a few hand-selected features such as function words; and (iii) comparing models across both web corpora and social media corpora in order to measure the robustness of syntactic variation across registers. |
| Tasks | |
| Published | 2019-04-11 |
| URL | http://arxiv.org/abs/1904.05527v1 |
| http://arxiv.org/pdf/1904.05527v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-global-syntactic-variation-in |
| Repo | |
| Framework | |
