Paper Group ANR 1356
Modeling and Detection of Future Cyber-Enabled DSM Data Attacks using Supervised Learning. Deep Text-to-Speech System with Seq2Seq Model. Reinforcement Learning Scheduler for Vehicle-to-Vehicle Communications Outside Coverage. Context-aware Active Multi-Step Reinforcement Learning. Comparative Analysis of Automatic Skin Lesion Segmentation with Two …
Modeling and Detection of Future Cyber-Enabled DSM Data Attacks using Supervised Learning
| Title | Modeling and Detection of Future Cyber-Enabled DSM Data Attacks using Supervised Learning |
| Authors | Kostas Hatalis, Parv Venkitasubramaniam, Shalinee Kishore |
| Abstract | Demand-Side Management (DSM) is a vital tool that can be used to ensure power system reliability and stability. In future smart grids, certain portions of a customers load usage could be under automatic control with a cyber-enabled DSM program which selectively schedules loads as a function of electricity prices to improve power balance and grid stability. In such a case, the security of DSM cyberinfrastructure will be critical as advanced metering infrastructure, and communication systems are susceptible to hacking, cyber-attacks. Such attacks, in the form of data injection, can manipulate customer load profiles and cause metering chaos and energy losses in the grid. These attacks are also exacerbated by the feedback mechanism between load management on the consumer side and dynamic price schemes by independent system operators. This work provides a novel methodology for modeling and simulating the nonlinear relationship between load management and real-time pricing. We then investigate the behavior of such a feedback loop under intentional cyber-attacks using our feedback model. We simulate and examine load-price data under different levels of DSM participation with three types of additive attacks: ramp, sudden, and point attacks. We apply change point and supervised learning methods for detection of DSM attacks. Results conclude that while higher levels of DSM participation can exacerbate attacks they also lead to better detection of such attacks. Further analysis of results shows that point attacks are the hardest to detect and supervised learning methods produce results on par or better than sequential detectors. |
| Tasks | |
| Published | 2019-09-27 |
| URL | https://arxiv.org/abs/1909.12894v1 |
| https://arxiv.org/pdf/1909.12894v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-and-detection-of-future-cyber |
| Repo | |
| Framework | |
Deep Text-to-Speech System with Seq2Seq Model
| Title | Deep Text-to-Speech System with Seq2Seq Model |
| Authors | Gary Wang |
| Abstract | Recent trends in neural network based text-to-speech/speech synthesis pipelines have employed recurrent Seq2seq architectures that can synthesize realistic sounding speech directly from text characters. These systems however have complex architectures and takes a substantial amount of time to train. We introduce several modifications to these Seq2seq architectures that allow for faster training time, and also allows us to reduce the complexity of the model architecture at the same time. We show that our proposed model can achieve attention alignment much faster than previous architectures and that good audio quality can be achieved with a model that’s much smaller in size. Sample audio available at https://soundcloud.com/gary-wang-23/sets/tts-samples-for-cmpt-419. |
| Tasks | Speech Synthesis |
| Published | 2019-03-11 |
| URL | http://arxiv.org/abs/1903.07398v1 |
| http://arxiv.org/pdf/1903.07398v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-text-to-speech-system-with-seq2seq-model |
| Repo | |
| Framework | |
Reinforcement Learning Scheduler for Vehicle-to-Vehicle Communications Outside Coverage
| Title | Reinforcement Learning Scheduler for Vehicle-to-Vehicle Communications Outside Coverage |
| Authors | Taylan Şahin, Ramin Khalili, Mate Boban, Adam Wolisz |
| Abstract | Radio resources in vehicle-to-vehicle (V2V) communication can be scheduled either by a centralized scheduler residing in the network (e.g., a base station in case of cellular systems) or a distributed scheduler, where the resources are autonomously selected by the vehicles. The former approach yields a considerably higher resource utilization in case the network coverage is uninterrupted. However, in case of intermittent or out-of-coverage, due to not having input from centralized scheduler, vehicles need to revert to distributed scheduling. Motivated by recent advances in reinforcement learning (RL), we investigate whether a centralized learning scheduler can be taught to efficiently pre-assign the resources to vehicles for out-of-coverage V2V communication. Specifically, we use the actor-critic RL algorithm to train the centralized scheduler to provide non-interfering resources to vehicles before they enter the out-of-coverage area. Our initial results show that a RL-based scheduler can achieve performance as good as or better than the state-of-art distributed scheduler, often outperforming it. Furthermore, the learning process completes within a reasonable time (ranging from a few hundred to a few thousand epochs), thus making the RL-based scheduler a promising solution for V2V communications with intermittent network coverage. |
| Tasks | |
| Published | 2019-04-29 |
| URL | http://arxiv.org/abs/1904.12653v1 |
| http://arxiv.org/pdf/1904.12653v1.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-scheduler-for-vehicle |
| Repo | |
| Framework | |
Context-aware Active Multi-Step Reinforcement Learning
| Title | Context-aware Active Multi-Step Reinforcement Learning |
| Authors | Gang Chen, Dingcheng Li, Ran Xu |
| Abstract | Reinforcement learning has attracted great attention recently, especially policy gradient algorithms, which have been demonstrated on challenging decision making and control tasks. In this paper, we propose an active multi-step TD algorithm with adaptive stepsizes to learn actor and critic. Specifically, our model consists of two components: active stepsize learning and adaptive multi-step TD algorithm. Firstly, we divide the time horizon into chunks and actively select state and action inside each chunk. Then given the selected samples, we propose the adaptive multi-step TD, which generalizes TD($\lambda$), but adaptively switch on/off the backups from future returns of different steps. Particularly, the adaptive multi-step TD introduces a context-aware mechanism, here a binary classifier, which decides whether or not to turn on its future backups based on the context changes. Thus, our model is kind of combination of active learning and multi-step TD algorithm, which has the capacity for learning off-policy without the need of importance sampling. We evaluate our approach on both discrete and continuous space tasks in an off-policy setting respectively, and demonstrate competitive results compared to other reinforcement learning baselines. |
| Tasks | Active Learning, Decision Making |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04107v2 |
| https://arxiv.org/pdf/1911.04107v2.pdf | |
| PWC | https://paperswithcode.com/paper/context-aware-active-multi-step-reinforcement |
| Repo | |
| Framework | |
Comparative Analysis of Automatic Skin Lesion Segmentation with Two Different Implementations
| Title | Comparative Analysis of Automatic Skin Lesion Segmentation with Two Different Implementations |
| Authors | Md. Kamrul Hasan, Basel Alyafi, Fakrul Islam Tushar |
| Abstract | Lesion segmentation from the surrounding skin is the first task for developing automatic Computer-Aided Diagnosis of skin cancer. Variant features of lesion like uneven distribution of color, irregular shape, border and texture make this task challenging. The contribution of this paper is to present and compare two different approaches to skin lesion segmentation. The first approach uses watershed, while the second approach uses mean-shift. Pre-processing steps were performed in both approaches for removing hair and dark borders of microscopic images. The Evaluation of the proposed approaches was performed using Jaccard Index (Intersection over Union or IoU). An additional contribution of this paper is to present pipelines for performing pre-processing and segmentation applying existing segmentation and morphological algorithms which led to promising results. On average, the first approach showed better performance than the second one with average Jaccard Index over 200 ISIC-2017 challenge images are 89.16% and 76.94% respectively. |
| Tasks | Lesion Segmentation |
| Published | 2019-04-05 |
| URL | http://arxiv.org/abs/1904.03075v1 |
| http://arxiv.org/pdf/1904.03075v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparative-analysis-of-automatic-skin-lesion |
| Repo | |
| Framework | |
Robot Sound Interpretation: Combining Sight and Sound in Learning-Based Control
| Title | Robot Sound Interpretation: Combining Sight and Sound in Learning-Based Control |
| Authors | Peixin Chang, Shuijing Liu, Haonan Chen, Katherine Driggs-Campbell |
| Abstract | We explore the interpretation of sound for robot decision-making, inspired by human speech comprehension. While previous methods use natural language processing to translate sound to text, we propose an end-to-end deep neural network which directly learns control polices from images and sound signals. The network is trained using reinforcement learning with auxiliary losses on the sight and sound network branches. We demonstrate our approach on two robots, a TurtleBot3 and a Kuka-IIWA arm, which hear a command word, identify the associated target object, and perform precise control to reach the target. For both systems, we perform ablation studies in simulation to show the effectiveness of our network empirically. We also successfully transfer the policy learned in simulator to a real-world TurtleBot3, which effectively understands word commands, searches for the object, and moves toward that location with more intuitive motion than a traditional motion planner with perfect information. |
| Tasks | Decision Making |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.09172v1 |
| https://arxiv.org/pdf/1909.09172v1.pdf | |
| PWC | https://paperswithcode.com/paper/robot-sound-interpretation-combining-sight |
| Repo | |
| Framework | |
Simulation of neural function in an artificial Hebbian network
| Title | Simulation of neural function in an artificial Hebbian network |
| Authors | J. Campbell Scott, Thomas F. Hayes, Ahmet S. Ozcan, Winfried W. Wilcke |
| Abstract | Artificial neural networks have diverged far from their early inspiration in neurology. In spite of their technological and commercial success, they have several shortcomings, most notably the need for a large number of training examples and the resulting computation resources required for iterative learning. Here we describe an approach to neurological network simulation, both architectural and algorithmic, that adheres more closely to established biological principles and overcomes some of the shortcomings of conventional networks. |
| Tasks | |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.01088v1 |
| https://arxiv.org/pdf/1912.01088v1.pdf | |
| PWC | https://paperswithcode.com/paper/simulation-of-neural-function-in-an |
| Repo | |
| Framework | |
Tensor-variate Mixture of Experts
| Title | Tensor-variate Mixture of Experts |
| Authors | Noémie Jaquier, Robert Haschke, Sylvain Calinon |
| Abstract | When data are organized in matrices or arrays of higher dimensions (tensors), classical regression methods first transform these data into vectors, therefore ignoring the underlying structure of the data and increasing the dimensionality of the problem. This flattening operation typically leads to overfitting when only few training data is available. In this paper, we present a mixture of experts model that exploits tensorial representations for regression of tensor-valued data. The proposed formulation takes into account the underlying structure of the data and remains efficient when few training data are available. Evaluation on artificially generated data, as well as offline and real-time experiments recognizing hand movements from tactile myography prove the effectiveness of the proposed approach. |
| Tasks | |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.11104v2 |
| http://arxiv.org/pdf/1902.11104v2.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-variate-mixture-of-experts |
| Repo | |
| Framework | |
Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model
| Title | Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model |
| Authors | Wenhan Xiong, Jingfei Du, William Yang Wang, Veselin Stoyanov |
| Abstract | Recent breakthroughs of pretrained language models have shown the effectiveness of self-supervised learning for a wide range of natural language processing (NLP) tasks. In addition to standard syntactic and semantic NLP tasks, pretrained models achieve strong improvements on tasks that involve real-world knowledge, suggesting that large-scale language modeling could be an implicit method to capture knowledge. In this work, we further investigate the extent to which pretrained models such as BERT capture knowledge using a zero-shot fact completion task. Moreover, we propose a simple yet effective weakly supervised pretraining objective, which explicitly forces the model to incorporate knowledge about real-world entities. Models trained with our new objective yield significant improvements on the fact completion task. When applied to downstream tasks, our model consistently outperforms BERT on four entity-related question answering datasets (i.e., WebQuestions, TriviaQA, SearchQA and Quasar-T) with an average 2.7 F1 improvements and a standard fine-grained entity typing dataset (i.e., FIGER) with 5.7 accuracy gains. |
| Tasks | Entity Typing, Language Modelling, Question Answering |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09637v1 |
| https://arxiv.org/pdf/1912.09637v1.pdf | |
| PWC | https://paperswithcode.com/paper/pretrained-encyclopedia-weakly-supervised-1 |
| Repo | |
| Framework | |
Adaptive Modulation and Coding based on Reinforcement Learning for 5G Networks
| Title | Adaptive Modulation and Coding based on Reinforcement Learning for 5G Networks |
| Authors | Mateus P. Mota, Daniel C. Araujo, Francisco Hugo Costa Neto, Andre L. F. de Almeida, F. Rodrigo P. Cavalcanti |
| Abstract | We design a self-exploratory reinforcement learning (RL) framework, based on the Q-learning algorithm, that enables the base station (BS) to choose a suitable modulation and coding scheme (MCS) that maximizes the spectral efficiency while maintaining a low block error rate (BLER). In this framework, the BS chooses the MCS based on the channel quality indicator (CQI) reported by the user equipment (UE). A transmission is made with the chosen MCS and the results of this transmission are converted by the BS into rewards that the BS uses to learn the suitable mapping from CQI to MCS. Comparing with a conventional fixed look-up table and the outer loop link adaptation, the proposed framework achieves superior performance in terms of spectral efficiency and BLER. |
| Tasks | Q-Learning |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1912.04030v1 |
| https://arxiv.org/pdf/1912.04030v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-modulation-and-coding-based-on |
| Repo | |
| Framework | |
Asymptotics of Reinforcement Learning with Neural Networks
| Title | Asymptotics of Reinforcement Learning with Neural Networks |
| Authors | Justin Sirignano, Konstantinos Spiliopoulos |
| Abstract | We prove that a single-layer neural network trained with the Q-learning algorithm converges in distribution to a random ordinary differential equation as the size of the model and the number of training steps become large. Analysis of the limit differential equation shows that it has a unique stationary solution which is the solution of the Bellman equation, thus giving the optimal control for the problem. In addition, we study the convergence of the limit differential equation to the stationary solution. As a by-product of our analysis, we obtain the limiting behavior of single-layer neural networks when trained on i.i.d. data with stochastic gradient descent under the widely-used Xavier initialization. |
| Tasks | Q-Learning |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.07304v1 |
| https://arxiv.org/pdf/1911.07304v1.pdf | |
| PWC | https://paperswithcode.com/paper/asymptotics-of-reinforcement-learning-with |
| Repo | |
| Framework | |
UFRGS Participation on the WMT Biomedical Translation Shared Task
| Title | UFRGS Participation on the WMT Biomedical Translation Shared Task |
| Authors | Felipe Soares, Karin Becker |
| Abstract | This paper describes the machine translation systems developed by the Universidade Federal do Rio Grande do Sul (UFRGS) team for the biomedical translation shared task. Our systems are based on statistical machine translation and neural machine translation, using the Moses and OpenNMT toolkits, respectively. We participated in four translation directions for the English/Spanish and English/Portuguese language pairs. To create our training data, we concatenated several parallel corpora, both from in-domain and out-of-domain sources, as well as terminological resources from UMLS. Our systems achieved the best BLEU scores according to the official shared task evaluation. |
| Tasks | Machine Translation |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.01855v1 |
| https://arxiv.org/pdf/1905.01855v1.pdf | |
| PWC | https://paperswithcode.com/paper/ufrgs-participation-on-the-wmt-biomedical-1 |
| Repo | |
| Framework | |
Oracle inequalities for square root analysis estimators with application to total variation penalties
| Title | Oracle inequalities for square root analysis estimators with application to total variation penalties |
| Authors | Francesco Ortelli, Sara van de Geer |
| Abstract | Through the direct study of the analysis estimator we derive oracle inequalities with fast and slow rates by adapting the arguments involving projections by Dalalyan, Hebiri and Lederer (2017). We then extend the theory to the square root analysis estimator. Finally, we focus on (square root) total variation regularized estimators on graphs and obtain constant-friendly rates, which, up to log-terms, match previous results obtained by entropy calculations. We also obtain an oracle inequality for the (square root) total variation regularized estimator over the cycle graph. |
| Tasks | |
| Published | 2019-02-28 |
| URL | https://arxiv.org/abs/1902.11192v2 |
| https://arxiv.org/pdf/1902.11192v2.pdf | |
| PWC | https://paperswithcode.com/paper/oracle-inequalities-for-square-root-analysis |
| Repo | |
| Framework | |
Mixing autoencoder with classifier: conceptual data visualization
| Title | Mixing autoencoder with classifier: conceptual data visualization |
| Authors | Pitoyo Hartono |
| Abstract | In this short paper, a neural network that is able to form a low dimensional topological hidden representation is explained. The neural network can be trained as an autoencoder, a classifier or mix of both, and produces different low dimensional topological map for each of them. When it is trained as an autoencoder, the inherent topological structure of the data can be visualized, while when it is trained as a classifier, the topological structure is further constrained by the concept, for example the labels the data, hence the visualization is not only structural but also conceptual. The proposed neural network significantly differ from many dimensional reduction models, primarily in its ability to execute both supervised and unsupervised dimensional reduction. The neural network allows multi perspective visualization of the data, and thus giving more flexibility in data analysis. This paper is supported by preliminary but intuitive visualization experiments. |
| Tasks | |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01137v3 |
| https://arxiv.org/pdf/1912.01137v3.pdf | |
| PWC | https://paperswithcode.com/paper/mixing-autoencoder-with-classifier-conceptual |
| Repo | |
| Framework | |
On the relation between structured $d$-DNNFs and SDDs
| Title | On the relation between structured $d$-DNNFs and SDDs |
| Authors | Beate Bollig, Martin Farenholtz |
| Abstract | Structured $d$-DNNFs and SDDs are restricted negation normal form circuits used in knowledge compilation as target languages into which propositional theories are compiled. Structuredness is imposed by so-called vtrees. By definition SDDs are restricted structured $d$-DNNFs. Beame and Liew (2015) as well as Bova and Szeider (2017) mentioned the question whether structured $d$-DNNFs are really more general than SDDs w.r.t. polynomial-size representations (w.r.t. the number of Boolean variables the represented functions are defined on.) The main result in the paper is the proof that a function can be represented by SDDs of polynomial size if the function and its complement have polynomial-size structured $d$-DNNFs that respect the same vtree. |
| Tasks | |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.01430v1 |
| https://arxiv.org/pdf/1912.01430v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-relation-between-structured-d-dnnfs |
| Repo | |
| Framework | |
