Paper Group ANR 871
Socioeconomic Dependencies of Linguistic Patterns in Twitter: A Multivariate Analysis. Training Multi-layer Spiking Neural Networks using NormAD based Spatio-Temporal Error Backpropagation. PromID: human promoter prediction by deep learning. Multiple Instance Learning for ECG Risk Stratification. A Multiclass Multiple Instance Learning Method with …
Socioeconomic Dependencies of Linguistic Patterns in Twitter: A Multivariate Analysis
| Title | Socioeconomic Dependencies of Linguistic Patterns in Twitter: A Multivariate Analysis |
| Authors | Jacob Levy Abitbol, Márton Karsai, Jean-Philippe Magué, Jean-Pierre Chevrot, Eric Fleury |
| Abstract | Our usage of language is not solely reliant on cognition but is arguably determined by myriad external factors leading to a global variability of linguistic patterns. This issue, which lies at the core of sociolinguistics and is backed by many small-scale studies on face-to-face communication, is addressed here by constructing a dataset combining the largest French Twitter corpus to date with detailed socioeconomic maps obtained from national census in France. We show how key linguistic variables measured in individual Twitter streams depend on factors like socioeconomic status, location, time, and the social network of individuals. We found that (i) people of higher socioeconomic status, active to a greater degree during the daytime, use a more standard language; (ii) the southern part of the country is more prone to use more standard language than the northern one, while locally the used variety or dialect is determined by the spatial distribution of socioeconomic status; and (iii) individuals connected in the social network are closer linguistically than disconnected ones, even after the effects of status homophily have been removed. Our results inform sociolinguistic theory and may inspire novel learning methods for the inference of socioeconomic status of people from the way they tweet. |
| Tasks | |
| Published | 2018-04-03 |
| URL | http://arxiv.org/abs/1804.01155v1 |
| http://arxiv.org/pdf/1804.01155v1.pdf | |
| PWC | https://paperswithcode.com/paper/socioeconomic-dependencies-of-linguistic |
| Repo | |
| Framework | |
Training Multi-layer Spiking Neural Networks using NormAD based Spatio-Temporal Error Backpropagation
| Title | Training Multi-layer Spiking Neural Networks using NormAD based Spatio-Temporal Error Backpropagation |
| Authors | Navin Anwani, Bipin Rajendran |
| Abstract | Spiking neural networks (SNNs) have garnered a great amount of interest for supervised and unsupervised learning applications. This paper deals with the problem of training multi-layer feedforward SNNs. The non-linear integrate-and-fire dynamics employed by spiking neurons make it difficult to train SNNs to generate desired spike trains in response to a given input. To tackle this, first the problem of training a multi-layer SNN is formulated as an optimization problem such that its objective function is based on the deviation in membrane potential rather than the spike arrival instants. Then, an optimization method named Normalized Approximate Descent (NormAD), hand-crafted for such non-convex optimization problems, is employed to derive the iterative synaptic weight update rule. Next, it is reformulated to efficiently train multi-layer SNNs, and is shown to be effectively performing spatio-temporal error backpropagation. The learning rule is validated by training $2$-layer SNNs to solve a spike based formulation of the XOR problem as well as training $3$-layer SNNs for generic spike based training problems. Thus, the new algorithm is a key step towards building deep spiking neural networks capable of efficient event-triggered learning. |
| Tasks | |
| Published | 2018-10-23 |
| URL | https://arxiv.org/abs/1811.10678v2 |
| https://arxiv.org/pdf/1811.10678v2.pdf | |
| PWC | https://paperswithcode.com/paper/training-multi-layer-spiking-neural-networks |
| Repo | |
| Framework | |
PromID: human promoter prediction by deep learning
| Title | PromID: human promoter prediction by deep learning |
| Authors | Ramzan Umarov, Hiroyuki Kuwahara, Yu Li, Xin Gao, Victor Solovyev |
| Abstract | Computational identification of promoters is notoriously difficult as human genes often have unique promoter sequences that provide regulation of transcription and interaction with transcription initiation complex. While there are many attempts to develop computational promoter identification methods, we have no reliable tool to analyze long genomic sequences. In this work we further develop our deep learning approach that was relatively successful to discriminate short promoter and non-promoter sequences. Instead of focusing on the classification accuracy, in this work we predict the exact positions of the TSS inside the genomic sequences testing every possible location. We studied human promoters to find effective regions for discrimination and built corresponding deep learning models. These models use adaptively constructed negative set which iteratively improves the models discriminative ability. The developed promoter identification models significantly outperform the previously developed promoter prediction programs by considerably reducing the number of false positive predictions. The best model we have built has recall 0.76, precision 0.77 and MCC 0.76, while the next best tool FPROM achieved precision 0.48 and MCC 0.60 for the recall of 0.75. Our method is available at http://www.cbrc.kaust.edu.sa/PromID/. |
| Tasks | |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.01414v1 |
| http://arxiv.org/pdf/1810.01414v1.pdf | |
| PWC | https://paperswithcode.com/paper/promid-human-promoter-prediction-by-deep |
| Repo | |
| Framework | |
Multiple Instance Learning for ECG Risk Stratification
| Title | Multiple Instance Learning for ECG Risk Stratification |
| Authors | Divya Shanmugam, Davis Blalock, John Guttag |
| Abstract | Patients who suffer an acute coronary syndrome are at elevated risk for adverse cardiovascular events such as myocardial infarction and cardiovascular death. Accurate assessment of this risk is crucial to their course of care. We focus on estimating a patient’s risk of cardiovascular death after an acute coronary syndrome based on a patient’s raw electrocardiogram (ECG) signal. Learning from this signal is challenging for two reasons: 1) positive examples signifying a downstream cardiovascular event are scarce, causing drastic class imbalance, and 2) each patient’s ECG signal consists of thousands of heartbeats, accompanied by a single label for the downstream outcome. Machine learning has been previously applied to this task, but most approaches rely on hand-crafted features and domain knowledge. We propose a method that learns a representation from the raw ECG signal by using a multiple instance learning framework. We present a learned risk score for cardiovascular death that outperforms existing risk metrics in predicting cardiovascular death within 30, 60, 90, and 365 days on a dataset of 5000 patients. |
| Tasks | Ecg Risk Stratification, Multiple Instance Learning |
| Published | 2018-12-02 |
| URL | https://arxiv.org/abs/1812.00475v4 |
| https://arxiv.org/pdf/1812.00475v4.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-instance-learning-for-ecg-risk |
| Repo | |
| Framework | |
A Multiclass Multiple Instance Learning Method with Exact Likelihood
| Title | A Multiclass Multiple Instance Learning Method with Exact Likelihood |
| Authors | Xi-Lin Li |
| Abstract | We study a multiclass multiple instance learning (MIL) problem where the labels only suggest whether any instance of a class exists or does not exist in a training sample or example. No further information, e.g., the number of instances of each class, relative locations or orders of all instances in a training sample, is exploited. Such a weak supervision learning problem can be exactly solved by maximizing the model likelihood fitting given observations, and finds applications to tasks like multiple object detection and localization for image understanding. We discuss its relationship to the classic classification problem, the traditional MIL, and connectionist temporal classification (CTC). We use image recognition as the example task to develop our method, although it is applicable to data with higher or lower dimensions without much modification. Experimental results show that our method can be used to learn all convolutional neural networks for solving real-world multiple object detection and localization tasks with weak annotations, e.g., transcribing house number sequences from the Google street view imagery dataset. |
| Tasks | Multiple Instance Learning, Object Detection |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1811.12346v2 |
| http://arxiv.org/pdf/1811.12346v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-with-labels-of-existing-and |
| Repo | |
| Framework | |
Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision
| Title | Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision |
| Authors | Sanjeel Parekh, Alexey Ozerov, Slim Essid, Ngoc Duong, Patrick Pérez, Gaël Richard |
| Abstract | We tackle the problem of audiovisual scene analysis for weakly-labeled data. To this end, we build upon our previous audiovisual representation learning framework to perform object classification in noisy acoustic environments and integrate audio source enhancement capability. This is made possible by a novel use of non-negative matrix factorization for the audio modality. Our approach is founded on the multiple instance learning paradigm. Its effectiveness is established through experiments over a challenging dataset of music instrument performance videos. We also show encouraging visual object localization results. |
| Tasks | Multiple Instance Learning, Object Classification, Object Localization, Representation Learning |
| Published | 2018-11-09 |
| URL | http://arxiv.org/abs/1811.04000v1 |
| http://arxiv.org/pdf/1811.04000v1.pdf | |
| PWC | https://paperswithcode.com/paper/identify-locate-and-separate-audio-visual |
| Repo | |
| Framework | |
A Study of EV BMS Cyber Security Based on Neural Network SOC Prediction
| Title | A Study of EV BMS Cyber Security Based on Neural Network SOC Prediction |
| Authors | Syed Rahman, Haneen Aburub, Yemeserach Mekonnen, Arif I. Sarwat |
| Abstract | Recent changes to greenhouse gas emission policies are catalyzing the electric vehicle (EV) market making it readily accessible to consumers. While there are challenges that arise with dense deployment of EVs, one of the major future concerns is cyber security threat. In this paper, cyber security threats in the form of tampering with EV battery’s State of Charge (SOC) was explored. A Back Propagation (BP) Neural Network (NN) was trained and tested based on experimental data to estimate SOC of battery under normal operation and cyber-attack scenarios. NeuralWare software was used to run scenarios. Different statistic metrics of the predicted values were compared against the actual values of the specific battery tested to measure the stability and accuracy of the proposed BP network under different operating conditions. The results showed that BP NN was able to capture and detect the false entries due to a cyber-attack on its network. |
| Tasks | |
| Published | 2018-06-07 |
| URL | http://arxiv.org/abs/1806.02714v1 |
| http://arxiv.org/pdf/1806.02714v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-study-of-ev-bms-cyber-security-based-on |
| Repo | |
| Framework | |
Testing Global Constraints
| Title | Testing Global Constraints |
| Authors | Aurélie Massart, Valentin Rombouts, Pierre Schaus |
| Abstract | Every Constraint Programming (CP) solver exposes a library of constraints for solving combinatorial problems. In order to be useful, CP solvers need to be bug-free. Therefore the testing of the solver is crucial to make developers and users confident. We present a Java library allowing any JVM based solver to test that the implementations of the individual constraints are correct. The library can be used in a test suite executed in a continuous integration tool or it can also be used to discover minimalist instances violating some properties (arc-consistency, etc) in order to help the developer to identify the origin of the problem using standard debuggers. |
| Tasks | |
| Published | 2018-07-11 |
| URL | http://arxiv.org/abs/1807.03975v1 |
| http://arxiv.org/pdf/1807.03975v1.pdf | |
| PWC | https://paperswithcode.com/paper/testing-global-constraints |
| Repo | |
| Framework | |
Adversarial Examples from Cryptographic Pseudo-Random Generators
| Title | Adversarial Examples from Cryptographic Pseudo-Random Generators |
| Authors | Sébastien Bubeck, Yin Tat Lee, Eric Price, Ilya Razenshteyn |
| Abstract | In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805.10204) we argued that adversarial examples in machine learning might be due to an inherent computational hardness of the problem. More precisely, we constructed a binary classification task for which (i) a robust classifier exists; yet no non-trivial accuracy can be obtained with an efficient algorithm in (ii) the statistical query model. In the present paper we significantly strengthen both (i) and (ii): we now construct a task which admits (i’) a maximally robust classifier (that is it can tolerate perturbations of size comparable to the size of the examples themselves); and moreover we prove computational hardness of learning this task under (ii’) a standard cryptographic assumption. |
| Tasks | |
| Published | 2018-11-15 |
| URL | http://arxiv.org/abs/1811.06418v1 |
| http://arxiv.org/pdf/1811.06418v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-examples-from-cryptographic |
| Repo | |
| Framework | |
Don’t forget, there is more than forgetting: new metrics for Continual Learning
| Title | Don’t forget, there is more than forgetting: new metrics for Continual Learning |
| Authors | Natalia Díaz-Rodríguez, Vincenzo Lomonaco, David Filliat, Davide Maltoni |
| Abstract | Continual learning consists of algorithms that learn from a stream of data/tasks continuously and adaptively thought time, enabling the incremental development of ever more complex knowledge and skills. The lack of consensus in evaluating continual learning algorithms and the almost exclusive focus on forgetting motivate us to propose a more comprehensive set of implementation independent metrics accounting for several factors we believe have practical implications worth considering in the deployment of real AI systems that learn continually: accuracy or performance over time, backward and forward knowledge transfer, memory overhead as well as computational efficiency. Drawing inspiration from the standard Multi-Attribute Value Theory (MAVT) we further propose to fuse these metrics into a single score for ranking purposes and we evaluate our proposal with five continual learning strategies on the iCIFAR-100 continual learning benchmark. |
| Tasks | Continual Learning, Transfer Learning |
| Published | 2018-10-31 |
| URL | http://arxiv.org/abs/1810.13166v1 |
| http://arxiv.org/pdf/1810.13166v1.pdf | |
| PWC | https://paperswithcode.com/paper/dont-forget-there-is-more-than-forgetting-new |
| Repo | |
| Framework | |
Analysis of Evolutionary Algorithms in Dynamic and Stochastic Environments
| Title | Analysis of Evolutionary Algorithms in Dynamic and Stochastic Environments |
| Authors | Vahid Roostapour, Mojgan Pourhassan, Frank Neumann |
| Abstract | Many real-world optimization problems occur in environments that change dynamically or involve stochastic components. Evolutionary algorithms and other bio-inspired algorithms have been widely applied to dynamic and stochastic problems. This survey gives an overview of major theoretical developments in the area of runtime analysis for these problems. We review recent theoretical studies of evolutionary algorithms and ant colony optimization for problems where the objective functions or the constraints change over time. Furthermore, we consider stochastic problems under various noise models and point out some directions for future research. |
| Tasks | |
| Published | 2018-06-22 |
| URL | http://arxiv.org/abs/1806.08547v1 |
| http://arxiv.org/pdf/1806.08547v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-evolutionary-algorithms-in |
| Repo | |
| Framework | |
Emergent Communication through Negotiation
| Title | Emergent Communication through Negotiation |
| Authors | Kris Cao, Angeliki Lazaridou, Marc Lanctot, Joel Z Leibo, Karl Tuyls, Stephen Clark |
| Abstract | Multi-agent reinforcement learning offers a way to study how communication could emerge in communities of agents needing to solve specific problems. In this paper, we study the emergence of communication in the negotiation environment, a semi-cooperative model of agent interaction. We introduce two communication protocols – one grounded in the semantics of the game, and one which is \textit{a priori} ungrounded and is a form of cheap talk. We show that self-interested agents can use the pre-grounded communication channel to negotiate fairly, but are unable to effectively use the ungrounded channel. However, prosocial agents do learn to use cheap talk to find an optimal negotiating strategy, suggesting that cooperation is necessary for language to emerge. We also study communication behaviour in a setting where one agent interacts with agents in a community with different levels of prosociality and show how agent identifiability can aid negotiation. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2018-04-11 |
| URL | http://arxiv.org/abs/1804.03980v1 |
| http://arxiv.org/pdf/1804.03980v1.pdf | |
| PWC | https://paperswithcode.com/paper/emergent-communication-through-negotiation |
| Repo | |
| Framework | |
POLO: a POLicy-based Optimization library
| Title | POLO: a POLicy-based Optimization library |
| Authors | Arda Aytekin, Martin Biel, Mikael Johansson |
| Abstract | We present POLO — a C++ library for large-scale parallel optimization research that emphasizes ease-of-use, flexibility and efficiency in algorithm design. It uses multiple inheritance and template programming to decompose algorithms into essential policies and facilitate code reuse. With its clear separation between algorithm and execution policies, it provides researchers with a simple and powerful platform for prototyping ideas, evaluating them on different parallel computing architectures and hardware platforms, and generating compact and efficient production code. A C-API is included for customization and data loading in high-level languages. POLO enables users to move seamlessly from serial to multi-threaded shared-memory and multi-node distributed-memory executors. We demonstrate how POLO allows users to implement state-of-the-art asynchronous parallel optimization algorithms in just a few lines of code and report experiment results from shared and distributed-memory computing architectures. We provide both POLO and POLO.jl, a wrapper around POLO written in the Julia language, at https://github.com/pologrp under the permissive MIT license. |
| Tasks | |
| Published | 2018-10-08 |
| URL | http://arxiv.org/abs/1810.03417v1 |
| http://arxiv.org/pdf/1810.03417v1.pdf | |
| PWC | https://paperswithcode.com/paper/polo-a-policy-based-optimization-library |
| Repo | |
| Framework | |
Signal recognition and background suppression by matched filters and neural networks for Tunka-Rex
| Title | Signal recognition and background suppression by matched filters and neural networks for Tunka-Rex |
| Authors | D. Shipilov, P. A. Bezyazeekov, N. M. Budnev, D. Chernykh, O. Fedorov, O. A. Gress, A. Haungs, R. Hiller, T. Huege, Y. Kazarina, M. Kleifges, E. E. Korosteleva, D. Kostunin, L. A. Kuzmichev, V. Lenok, N. Lubsandorzhiev, T. Marshalkina, R. Monkhoev, E. Osipova, A. Pakhorukov, L. Pankov, V. V. Prosin, F. G. Schröder, A. Zagorodnikov |
| Abstract | The Tunka Radio Extension (Tunka-Rex) is a digital antenna array, which measures the radio emission of the cosmic-ray air-showers in the frequency band of 30-80 MHz. Tunka-Rex is co-located with TAIGA experiment in Siberia and consists of 63 antennas, 57 of them are in a densely instrumented area of about 1 km\textsuperscript{2}. In the present work we discuss the improvements of the signal reconstruction applied for the Tunka-Rex. At the first stage we implemented matched filtering using averaged signals as template. The simulation study has shown that matched filtering allows one to decrease the threshold of signal detection and increase its purity. However, the maximum performance of matched filtering is achievable only in case of white noise, while in reality the noise is not fully random due to different reasons. To recognize hidden features of the noise and treat them, we decided to use convolutional neural network with autoencoder architecture. Taking the recorded trace as an input, the autoencoder returns denoised trace, i.e. removes all signal-unrelated amplitudes. We present the comparison between standard method of signal reconstruction, matched filtering and autoencoder, and discuss the prospects of application of neural networks for lowering the threshold of digital antenna arrays for cosmic-ray detection. |
| Tasks | |
| Published | 2018-12-08 |
| URL | https://arxiv.org/abs/1812.03347v2 |
| https://arxiv.org/pdf/1812.03347v2.pdf | |
| PWC | https://paperswithcode.com/paper/signal-recognition-and-background-suppression |
| Repo | |
| Framework | |
An Acceleration Scheme for Memory Limited, Streaming PCA
| Title | An Acceleration Scheme for Memory Limited, Streaming PCA |
| Authors | Salaheddin Alakkari, John Dingliana |
| Abstract | In this paper, we propose an acceleration scheme for online memory-limited PCA methods. Our scheme converges to the first $k>1$ eigenvectors in a single data pass. We provide empirical convergence results of our scheme based on the spiked covariance model. Our scheme does not require any predefined parameters such as the eigengap and hence is well facilitated for streaming data scenarios. Furthermore, we apply our scheme to challenging time-varying systems where online PCA methods fail to converge. Specifically, we discuss a family of time-varying systems that are based on Molecular Dynamics simulations where batch PCA converges to the actual analytic solution of such systems. |
| Tasks | |
| Published | 2018-07-17 |
| URL | http://arxiv.org/abs/1807.06530v1 |
| http://arxiv.org/pdf/1807.06530v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-acceleration-scheme-for-memory-limited |
| Repo | |
| Framework | |
