Paper Group ANR 1010
Real-time Road Traffic Information Detection Through Social Media. Examining the Tip of the Iceberg: A Data Set for Idiom Translation. Understanding the Importance of Single Directions via Representative Substitution. Migrating Knowledge between Physical Scenarios based on Artificial Neural Networks. Automatic Language Identification for Romance La …
Real-time Road Traffic Information Detection Through Social Media
| Title | Real-time Road Traffic Information Detection Through Social Media |
| Authors | Chandra Khatri |
| Abstract | In current study, a mechanism to extract traffic related information such as congestion and incidents from textual data from the internet is proposed. The current source of data is Twitter. As the data being considered is extremely large in size automated models are developed to stream, download, and mine the data in real-time. Furthermore, if any tweet has traffic related information then the models should be able to infer and extract this data. Currently, the data is collected only for United States and a total of 120,000 geo-tagged traffic related tweets are extracted, while six million geo-tagged non-traffic related tweets are retrieved and classification models are trained. Furthermore, this data is used for various kinds of spatial and temporal analysis. A mechanism to calculate level of traffic congestion, safety, and traffic perception for cities in U.S. is proposed. Traffic congestion and safety rankings for the various urban areas are obtained and then they are statistically validated with existing widely adopted rankings. Traffic perception depicts the attitude and perception of people towards the traffic. It is also seen that traffic related data when visualized spatially and temporally provides the same pattern as the actual traffic flows for various urban areas. When visualized at the city level, it is clearly visible that the flow of tweets is similar to flow of vehicles and that the traffic related tweets are representative of traffic within the cities. With all the findings in current study, it is shown that significant amount of traffic related information can be extracted from Twitter and other sources on internet. Furthermore, Twitter and these data sources are freely available and are not bound by spatial and temporal limitations. That is, wherever there is a user there is a potential for data. |
| Tasks | |
| Published | 2018-01-16 |
| URL | http://arxiv.org/abs/1801.05088v1 |
| http://arxiv.org/pdf/1801.05088v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-road-traffic-information-detection |
| Repo | |
| Framework | |
Examining the Tip of the Iceberg: A Data Set for Idiom Translation
| Title | Examining the Tip of the Iceberg: A Data Set for Idiom Translation |
| Authors | Marzieh Fadaee, Arianna Bisazza, Christof Monz |
| Abstract | Neural Machine Translation (NMT) has been widely used in recent years with significant improvements for many language pairs. Although state-of-the-art NMT systems are generating progressively better translations, idiom translation remains one of the open challenges in this field. Idioms, a category of multiword expressions, are an interesting language phenomenon where the overall meaning of the expression cannot be composed from the meanings of its parts. A first important challenge is the lack of dedicated data sets for learning and evaluating idiom translation. In this paper we address this problem by creating the first large-scale data set for idiom translation. Our data set is automatically extracted from a widely used German-English translation corpus and includes, for each language direction, a targeted evaluation set where all sentences contain idioms and a regular training corpus where sentences including idioms are marked. We release this data set and use it to perform preliminary NMT experiments as the first step towards better idiom translation. |
| Tasks | Machine Translation |
| Published | 2018-02-13 |
| URL | http://arxiv.org/abs/1802.04681v1 |
| http://arxiv.org/pdf/1802.04681v1.pdf | |
| PWC | https://paperswithcode.com/paper/examining-the-tip-of-the-iceberg-a-data-set |
| Repo | |
| Framework | |
Understanding the Importance of Single Directions via Representative Substitution
| Title | Understanding the Importance of Single Directions via Representative Substitution |
| Authors | Li Chen, Hailun Ding, Qi Li, Zhuo Li, Jian Peng, Haifeng Li |
| Abstract | Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior. The interpretation of individual units, which are neurons in MLPs or convolution kernels in convolutional networks, has been paid much attention given their fundamental role. However, recent research (Morcos et al. 2018) presented a counterintuitive phenomenon, which suggests that an individual unit with high class selectivity, called interpretable units, has poor contributions to generalization of DNNs. In this work, we provide a new perspective to understand this counterintuitive phenomenon, which makes sense when we introduce Representative Substitution (RS). Instead of individually selective units with classes, the RS refers to the independence of a unit’s representations in the same layer without any annotation. Our experiments demonstrate that interpretable units have high RS which are not critical to network’s generalization. The RS provides new insights into the interpretation of DNNs and suggests that we need to focus on the independence and relationship of the representations. |
| Tasks | |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.11053v2 |
| http://arxiv.org/pdf/1811.11053v2.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-the-importance-of-single |
| Repo | |
| Framework | |
Migrating Knowledge between Physical Scenarios based on Artificial Neural Networks
| Title | Migrating Knowledge between Physical Scenarios based on Artificial Neural Networks |
| Authors | Yurui Qu, Li Jing, Yichen Shen, Min Qiu, Marin Soljacic |
| Abstract | Deep learning is known to be data-hungry, which hinders its application in many areas of science when datasets are small. Here, we propose to use transfer learning methods to migrate knowledge between different physical scenarios and significantly improve the prediction accuracy of artificial neural networks trained on a small dataset. This method can help reduce the demand for expensive data by making use of additional inexpensive data. First, we demonstrate that in predicting the transmission from multilayer photonic film, the relative error rate is reduced by 46.8% (26.5%) when the source data comes from 10-layer (8-layer) films and the target data comes from 8-layer (10-layer) films. Second, we show that the relative error rate is decreased by 22% when knowledge is transferred between two very different physical scenarios: transmission from multilayer films and scattering from multilayer nanoparticles. Finally, we propose a multi-task learning method to improve the performance of different physical scenarios simultaneously in which each task only has a small dataset. |
| Tasks | Multi-Task Learning, Transfer Learning |
| Published | 2018-08-27 |
| URL | https://arxiv.org/abs/1809.00972v2 |
| https://arxiv.org/pdf/1809.00972v2.pdf | |
| PWC | https://paperswithcode.com/paper/migrating-knowledge-between-physical |
| Repo | |
| Framework | |
Automatic Language Identification for Romance Languages using Stop Words and Diacritics
| Title | Automatic Language Identification for Romance Languages using Stop Words and Diacritics |
| Authors | Ciprian-Octavian Truică, Julien Velcin, Alexandru Boicea |
| Abstract | Automatic language identification is a natural language processing problem that tries to determine the natural language of a given content. In this paper we present a statistical method for automatic language identification of written text using dictionaries containing stop words and diacritics. We propose different approaches that combine the two dictionaries to accurately determine the language of textual corpora. This method was chosen because stop words and diacritics are very specific to a language, although some languages have some similar words and special characters they are not all common. The languages taken into account were romance languages because they are very similar and usually it is hard to distinguish between them from a computational point of view. We have tested our method using a Twitter corpus and a news article corpus. Both corpora consists of UTF-8 encoded text, so the diacritics could be taken into account, in the case that the text has no diacritics only the stop words are used to determine the language of the text. The experimental results show that the proposed method has an accuracy of over 90% for small texts and over 99.8% for |
| Tasks | Language Identification |
| Published | 2018-06-14 |
| URL | http://arxiv.org/abs/1806.05480v1 |
| http://arxiv.org/pdf/1806.05480v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-language-identification-for-romance |
| Repo | |
| Framework | |
Learning to Explain with Complemental Examples
| Title | Learning to Explain with Complemental Examples |
| Authors | Atsushi Kanehira, Tatsuya Harada |
| Abstract | This paper addresses the generation of explanations with visual examples. Given an input sample, we build a system that not only classifies it to a specific category, but also outputs linguistic explanations and a set of visual examples that render the decision interpretable. Focusing especially on the complementarity of the multimodal information, i.e., linguistic and visual examples, we attempt to achieve it by maximizing the interaction information, which provides a natural definition of complementarity from an information theoretical viewpoint. We propose a novel framework to generate complemental explanations, on which the joint distribution of the variables to explain, and those to be explained is parameterized by three different neural networks: predictor, linguistic explainer, and example selector. Explanation models are trained collaboratively to maximize the interaction information to ensure the generated explanation are complemental to each other for the target. The results of experiments conducted on several datasets demonstrate the effectiveness of the proposed method. |
| Tasks | |
| Published | 2018-12-04 |
| URL | https://arxiv.org/abs/1812.01280v2 |
| https://arxiv.org/pdf/1812.01280v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-explain-with-complemental |
| Repo | |
| Framework | |
Depth Not Needed - An Evaluation of RGB-D Feature Encodings for Off-Road Scene Understanding by Convolutional Neural Network
| Title | Depth Not Needed - An Evaluation of RGB-D Feature Encodings for Off-Road Scene Understanding by Convolutional Neural Network |
| Authors | Christopher J. Holder, Toby P. Breckon, Xiong Wei |
| Abstract | Scene understanding for autonomous vehicles is a challenging computer vision task, with recent advances in convolutional neural networks (CNNs) achieving results that notably surpass prior traditional feature driven approaches. However, limited work investigates the application of such methods either within the highly unstructured off-road environment or to RGBD input data. In this work, we take an existing CNN architecture designed to perform semantic segmentation of RGB images of urban road scenes, then adapt and retrain it to perform the same task with multichannel RGBD images obtained under a range of challenging off-road conditions. We compare two different stereo matching algorithms and five different methods of encoding depth information, including disparity, local normal orientation and HHA (horizontal disparity, height above ground plane, angle with gravity), to create a total of ten experimental variations of our dataset, each of which is used to train and test a CNN so that classification performance can be evaluated against a CNN trained using standard RGB input. |
| Tasks | Autonomous Vehicles, Scene Understanding, Semantic Segmentation, Stereo Matching, Stereo Matching Hand |
| Published | 2018-01-04 |
| URL | http://arxiv.org/abs/1801.01235v1 |
| http://arxiv.org/pdf/1801.01235v1.pdf | |
| PWC | https://paperswithcode.com/paper/depth-not-needed-an-evaluation-of-rgb-d |
| Repo | |
| Framework | |
Learning Optimal Resource Allocations in Wireless Systems
| Title | Learning Optimal Resource Allocations in Wireless Systems |
| Authors | Mark Eisen, Clark Zhang, Luiz F. O. Chamon, Daniel D. Lee, Alejandro Ribeiro |
| Abstract | This paper considers the design of optimal resource allocation policies in wireless communication systems which are generically modeled as a functional optimization problem with stochastic constraints. These optimization problems have the structure of a learning problem in which the statistical loss appears as a constraint, motivating the development of learning methodologies to attempt their solution. To handle stochastic constraints, training is undertaken in the dual domain. It is shown that this can be done with small loss of optimality when using near-universal learning parameterizations. In particular, since deep neural networks (DNN) are near-universal their use is advocated and explored. DNNs are trained here with a model-free primal-dual method that simultaneously learns a DNN parametrization of the resource allocation policy and optimizes the primal and dual variables. Numerical simulations demonstrate the strong performance of the proposed approach on a number of common wireless resource allocation problems. |
| Tasks | |
| Published | 2018-07-21 |
| URL | http://arxiv.org/abs/1807.08088v2 |
| http://arxiv.org/pdf/1807.08088v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-optimal-resource-allocations-in |
| Repo | |
| Framework | |
Parallel training of linear models without compromising convergence
| Title | Parallel training of linear models without compromising convergence |
| Authors | Nikolas Ioannou, Celestine Dünner, Kornilios Kourtis, Thomas Parnell |
| Abstract | In this paper we analyze, evaluate, and improve the performance of training generalized linear models on modern CPUs. We start with a state-of-the-art asynchronous parallel training algorithm, identify system-level performance bottlenecks, and apply optimizations that improve data parallelism, cache line locality, and cache line prefetching of the algorithm. These modifications reduce the per-epoch run-time significantly, but take a toll on algorithm convergence in terms of the required number of epochs. To alleviate these shortcomings of our systems-optimized version, we propose a novel, dynamic data partitioning scheme across threads which allows us to approach the convergence of the sequential version. The combined set of optimizations result in a consistent bottom line speedup in convergence of up to 12x compared to the initial asynchronous parallel training algorithm and up to 42x, compared to state of the art implementations (scikit-learn and h2o) on a range of multi-core CPU architectures. |
| Tasks | |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.01564v2 |
| http://arxiv.org/pdf/1811.01564v2.pdf | |
| PWC | https://paperswithcode.com/paper/parallel-training-of-linear-models-without |
| Repo | |
| Framework | |
Barrier-Certified Adaptive Reinforcement Learning with Applications to Brushbot Navigation
| Title | Barrier-Certified Adaptive Reinforcement Learning with Applications to Brushbot Navigation |
| Authors | Motoya Ohnishi, Li Wang, Gennaro Notomista, Magnus Egerstedt |
| Abstract | This paper presents a safe learning framework that employs an adaptive model learning algorithm together with barrier certificates for systems with possibly nonstationary agent dynamics. To extract the dynamic structure of the model, we use a sparse optimization technique. We use the learned model in combination with control barrier certificates which constrain policies (feedback controllers) in order to maintain safety, which refers to avoiding particular undesirable regions of the state space. Under certain conditions, recovery of safety in the sense of Lyapunov stability after violations of safety due to the nonstationarity is guaranteed. In addition, we reformulate an action-value function approximation to make any kernel-based nonlinear function estimation method applicable to our adaptive learning framework. Lastly, solutions to the barrier-certified policy optimization are guaranteed to be globally optimal, ensuring the greedy policy improvement under mild conditions. The resulting framework is validated via simulations of a quadrotor, which has previously been used under stationarity assumptions in the safe learnings literature, and is then tested on a real robot, the brushbot, whose dynamics is unknown, highly complex and nonstationary. |
| Tasks | |
| Published | 2018-01-29 |
| URL | https://arxiv.org/abs/1801.09627v3 |
| https://arxiv.org/pdf/1801.09627v3.pdf | |
| PWC | https://paperswithcode.com/paper/barrier-certified-adaptive-reinforcement |
| Repo | |
| Framework | |
Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks
| Title | Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks |
| Authors | Max Schwarzer, Bryce Rogan, Yadong Ruan, Zhengming Song, Diana Y. Lee, Allon G. Percus, Viet T. Chau, Bryan A. Moore, Esteban Rougier, Hari S. Viswanathan, Gowri Srinivasan |
| Abstract | We propose a machine learning approach to address a key challenge in materials science: predicting how fractures propagate in brittle materials under stress, and how these materials ultimately fail. Our methods use deep learning and train on simulation data from high-fidelity models, emulating the results of these models while avoiding the overwhelming computational demands associated with running a statistically significant sample of simulations. We employ a graph convolutional network that recognizes features of the fracturing material and a recurrent neural network that models the evolution of these features, along with a novel form of data augmentation that compensates for the modest size of our training data. We simultaneously generate predictions for qualitatively distinct material properties. Results on fracture damage and length are within 3% of their simulated values, and results on time to material failure, which is notoriously difficult to predict even with high-fidelity models, are within approximately 15% of simulated values. Once trained, our neural networks generate predictions within seconds, rather than the hours needed to run a single simulation. |
| Tasks | Data Augmentation |
| Published | 2018-10-14 |
| URL | http://arxiv.org/abs/1810.06118v3 |
| http://arxiv.org/pdf/1810.06118v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-fail-predicting-fracture |
| Repo | |
| Framework | |
Concentration bounds for empirical conditional value-at-risk: The unbounded case
| Title | Concentration bounds for empirical conditional value-at-risk: The unbounded case |
| Authors | Ravi Kumar Kolla, Prashanth L. A., Sanjay P. Bhat, Krishna Jagannathan |
| Abstract | In several real-world applications involving decision making under uncertainty, the traditional expected value objective may not be suitable, as it may be necessary to control losses in the case of a rare but extreme event. Conditional Value-at-Risk (CVaR) is a popular risk measure for modeling the aforementioned objective. We consider the problem of estimating CVaR from i.i.d. samples of an unbounded random variable, which is either sub-Gaussian or sub-exponential. We derive a novel one-sided concentration bound for a natural sample-based CVaR estimator in this setting. Our bound relies on a concentration result for a quantile-based estimator for Value-at-Risk (VaR), which may be of independent interest. |
| Tasks | Decision Making, Decision Making Under Uncertainty |
| Published | 2018-08-06 |
| URL | http://arxiv.org/abs/1808.01739v1 |
| http://arxiv.org/pdf/1808.01739v1.pdf | |
| PWC | https://paperswithcode.com/paper/concentration-bounds-for-empirical |
| Repo | |
| Framework | |
Ocean Eddy Identification and Tracking using Neural Networks
| Title | Ocean Eddy Identification and Tracking using Neural Networks |
| Authors | Katharina Franz, Ribana Roscher, Andres Milioto, Susanne Wenzel, Jürgen Kusche |
| Abstract | Global climate change plays an essential role in our daily life. Mesoscale ocean eddies have a significant impact on global warming, since they affect the ocean dynamics, the energy as well as the mass transports of ocean circulation. From satellite altimetry we can derive high-resolution, global maps containing ocean signals with dominating coherent eddy structures. The aim of this study is the development and evaluation of a deep-learning based approach for the analysis of eddies. In detail, we develop an eddy identification and tracking framework with two different approaches that are mainly based on feature learning with convolutional neural networks. Furthermore, state-of-the-art image processing tools and object tracking methods are used to support the eddy tracking. In contrast to previous methods, our framework is able to learn a representation of the data in which eddies can be detected and tracked in more objective and robust way. We show the detection and tracking results on sea level anomalies (SLA) data from the area of Australia and the East Australia current, and compare our two eddy detection and tracking approaches to identify the most robust and objective method. |
| Tasks | Object Tracking |
| Published | 2018-03-20 |
| URL | http://arxiv.org/abs/1803.07436v2 |
| http://arxiv.org/pdf/1803.07436v2.pdf | |
| PWC | https://paperswithcode.com/paper/ocean-eddy-identification-and-tracking-using |
| Repo | |
| Framework | |
Playing against Nature: causal discovery for decision making under uncertainty
| Title | Playing against Nature: causal discovery for decision making under uncertainty |
| Authors | M. Gonzalez-Soto, L. E. Sucar, H. J. Escalante |
| Abstract | We consider decision problems under uncertainty where the options available to a decision maker and the resulting outcome are related through a causal mechanism which is unknown to the decision maker. We ask how a decision maker can learn about this causal mechanism through sequential decision making as well as using current causal knowledge inside each round in order to make better choices had she not considered causal knowledge and propose a decision making procedure in which an agent holds \textit{beliefs} about her environment which are used to make a choice and are updated using the observed outcome. As proof of concept, we present an implementation of this causal decision making model and apply it in a simple scenario. We show that the model achieves a performance similar to the classic Q-learning while it also acquires a causal model of the environment. |
| Tasks | Causal Discovery, Decision Making, Decision Making Under Uncertainty, Q-Learning |
| Published | 2018-07-03 |
| URL | http://arxiv.org/abs/1807.01268v1 |
| http://arxiv.org/pdf/1807.01268v1.pdf | |
| PWC | https://paperswithcode.com/paper/playing-against-nature-causal-discovery-for |
| Repo | |
| Framework | |
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
| Title | Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations |
| Authors | Tianlu Wang, Jieyu Zhao, Mark Yatskar, Kai-Wei Chang, Vicente Ordonez |
| Abstract | In this work, we present a framework to measure and mitigate intrinsic biases with respect to protected variables –such as gender– in visual recognition tasks. We show that trained models significantly amplify the association of target labels with gender beyond what one would expect from biased datasets. Surprisingly, we show that even when datasets are balanced such that each label co-occurs equally with each gender, learned models amplify the association between labels and gender, as much as if data had not been balanced! To mitigate this, we adopt an adversarial approach to remove unwanted features corresponding to protected variables from intermediate representations in a deep neural network – and provide a detailed analysis of its effectiveness. Experiments on two datasets: the COCO dataset (objects), and the imSitu dataset (actions), show reductions in gender bias amplification while maintaining most of the accuracy of the original models. |
| Tasks | Temporal Action Localization |
| Published | 2018-11-20 |
| URL | https://arxiv.org/abs/1811.08489v4 |
| https://arxiv.org/pdf/1811.08489v4.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-removal-of-gender-from-deep-image |
| Repo | |
| Framework | |
