Paper Group ANR 554
Fleet Control using Coregionalized Gaussian Process Policy Iteration. Model-Based Reinforcement Learning Exploiting State-Action Equivalence. Two-hidden-layer Feedforward Neural Networks are Universal Approximators: A Constructive Approach. An Unsupervised Bayesian Neural Network for Truth Discovery. Dual Skew Divergence Loss for Neural Machine Tra …
Fleet Control using Coregionalized Gaussian Process Policy Iteration
| Title | Fleet Control using Coregionalized Gaussian Process Policy Iteration |
| Authors | Timothy Verstraeten, Pieter JK Libin, Ann Nowé |
| Abstract | In many settings, as for example wind farms, multiple machines are instantiated to perform the same task, which is called a fleet. The recent advances with respect to the Internet of Things allow control devices and/or machines to connect through cloud-based architectures in order to share information about their status and environment. Such an infrastructure allows seamless data sharing between fleet members, which could greatly improve the sample-efficiency of reinforcement learning techniques. However in practice, these machines, while almost identical in design, have small discrepancies due to production errors or degradation, preventing control algorithms to simply aggregate and employ all fleet data. We propose a novel reinforcement learning method that learns to transfer knowledge between similar fleet members and creates member-specific dynamics models for control. Our algorithm uses Gaussian processes to establish cross-member covariances. This is significantly different from standard transfer learning methods, as the focus is not on sharing information over tasks, but rather over system specifications. We demonstrate our approach on two benchmarks and a realistic wind farm setting. Our method significantly outperforms two baseline approaches, namely individual learning and joint learning where all samples are aggregated, in terms of the median and variance of the results. |
| Tasks | Gaussian Processes, Transfer Learning |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.10121v1 |
| https://arxiv.org/pdf/1911.10121v1.pdf | |
| PWC | https://paperswithcode.com/paper/fleet-control-using-coregionalized-gaussian |
| Repo | |
| Framework | |
Model-Based Reinforcement Learning Exploiting State-Action Equivalence
| Title | Model-Based Reinforcement Learning Exploiting State-Action Equivalence |
| Authors | Mahsa Asadi, Mohammad Sadegh Talebi, Hippolyte Bourel, Odalric-Ambrym Maillard |
| Abstract | Leveraging an equivalence property in the state-space of a Markov Decision Process (MDP) has been investigated in several studies. This paper studies equivalence structure in the reinforcement learning (RL) setup, where transition distributions are no longer assumed to be known. We present a notion of similarity between transition probabilities of various state-action pairs of an MDP, which naturally defines an equivalence structure in the state-action space. We present equivalence-aware confidence sets for the case where the learner knows the underlying structure in advance. These sets are provably smaller than their corresponding equivalence-oblivious counterparts. In the more challenging case of an unknown equivalence structure, we present an algorithm called ApproxEquivalence that seeks to find an (approximate) equivalence structure, and define confidence sets using the approximate equivalence. To illustrate the efficacy of the presented confidence sets, we present C-UCRL, as a natural modification of UCRL2 for RL in undiscounted MDPs. In the case of a known equivalence structure, we show that C-UCRL improves over UCRL2 in terms of regret by a factor of $\sqrt{SA/C}$, in any communicating MDP with $S$ states, $A$ actions, and $C$ classes, which corresponds to a massive improvement when $C \ll SA$. To the best of our knowledge, this is the first work providing regret bounds for RL when an equivalence structure in the MDP is efficiently exploited. In the case of an unknown equivalence structure, we show through numerical experiments that C-UCRL combined with ApproxEquivalence outperforms UCRL2 in ergodic MDPs. |
| Tasks | |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04077v1 |
| https://arxiv.org/pdf/1910.04077v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-based-reinforcement-learning-exploiting |
| Repo | |
| Framework | |
Two-hidden-layer Feedforward Neural Networks are Universal Approximators: A Constructive Approach
| Title | Two-hidden-layer Feedforward Neural Networks are Universal Approximators: A Constructive Approach |
| Authors | Rocio Gonzalez-Diaz, Miguel A. Gutiérrez-Naranjo, Eduardo Paluzo-Hidalgo |
| Abstract | It is well known that Artificial Neural Networks are universal approximators. The classical result proves that, given a continuous function on a compact set on an n-dimensional space, then there exists a one-hidden-layer feedforward network which approximates the function. Such result proves the existence, but it does not provide a method for finding it. In this paper, a constructive approach to the proof of this property is given for the case of two-hidden-layer feedforward networks. This approach is based on an approximation of continuous functions by simplicial maps. Once a triangulation of the space is given, a concrete architecture and set of weights can be obtained. The quality of the approximation depends on the refinement of the covering of the space by simplicial complexes. |
| Tasks | |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11457v1 |
| https://arxiv.org/pdf/1907.11457v1.pdf | |
| PWC | https://paperswithcode.com/paper/two-hidden-layer-feedforward-neural-networks |
| Repo | |
| Framework | |
An Unsupervised Bayesian Neural Network for Truth Discovery
| Title | An Unsupervised Bayesian Neural Network for Truth Discovery |
| Authors | Jielong Yang, Wee Peng Tay |
| Abstract | The problem of estimating event truths from conflicting agent opinions is investigated. An autoencoder learns the complex relationships between event truths, agent reliabilities and agent observations. A Bayesian network model is proposed to guide the learning of the autoencoder by modeling the dependence of agent reliabilities corresponding to different data samples. At the same time, it also models the social relationships between agents in the network. The proposed approach is unsupervised and is applicable when ground truth labels of events are unavailable. A variational inference method is used to jointly estimate the hidden variables in the Bayesian network and the parameters in the autoencoder. Simulations and experiments on real data suggest that the proposed method performs better than several other inference methods, including majority voting, the Bayesian Classifier Combination (BCC) method, the Community BCC method, and the recently proposed VISIT method. |
| Tasks | |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10470v1 |
| https://arxiv.org/pdf/1906.10470v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-unsupervised-bayesian-neural-network-for |
| Repo | |
| Framework | |
Dual Skew Divergence Loss for Neural Machine Translation
| Title | Dual Skew Divergence Loss for Neural Machine Translation |
| Authors | Fengshun Xiao, Yingting Wu, Hai Zhao, Rui Wang, Shu Jiang |
| Abstract | For neural sequence model training, maximum likelihood (ML) has been commonly adopted to optimize model parameters with respect to the corresponding objective. However, in the case of sequence prediction tasks like neural machine translation (NMT), training with the ML-based cross entropy loss would often lead to models that overgeneralize and plunge into local optima. In this paper, we propose an extended loss function called dual skew divergence (DSD), which aims to give a better tradeoff between generalization ability and error avoidance during NMT training. Our empirical study indicates that switching to DSD loss after the convergence of ML training helps the model skip the local optimum and stimulates a stable performance improvement. The evaluations on WMT 2014 English-German and English-French translation tasks demonstrate that the proposed loss indeed helps bring about better translation performance than several baselines. |
| Tasks | Machine Translation |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08399v1 |
| https://arxiv.org/pdf/1908.08399v1.pdf | |
| PWC | https://paperswithcode.com/paper/dual-skew-divergence-loss-for-neural-machine-1 |
| Repo | |
| Framework | |
A Zero Attention Model for Personalized Product Search
| Title | A Zero Attention Model for Personalized Product Search |
| Authors | Qingyao Ai, Daniel N. Hill, S. V. N. Vishwanathan, W. Bruce Croft |
| Abstract | Product search is one of the most popular methods for people to discover and purchase products on e-commerce websites. Because personal preferences often have an important influence on the purchase decision of each customer, it is intuitive that personalization should be beneficial for product search engines. While synthetic experiments from previous studies show that purchase histories are useful for identifying the individual intent of each product search session, the effect of personalization on product search in practice, however, remains mostly unknown. In this paper, we formulate the problem of personalized product search and conduct large-scale experiments with search logs sampled from a commercial e-commerce search engine. Results from our preliminary analysis show that the potential of personalization depends on query characteristics, interactions between queries, and user purchase histories. Based on these observations, we propose a Zero Attention Model for product search that automatically determines when and how to personalize a user-query pair via a novel attention mechanism. Empirical results on commercial product search logs show that the proposed model not only significantly outperforms state-of-the-art personalized product retrieval models, but also provides important information on the potential of personalization in each product search session. |
| Tasks | |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11322v1 |
| https://arxiv.org/pdf/1908.11322v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-zero-attention-model-for-personalized |
| Repo | |
| Framework | |
Hiding Data in Images Using Cryptography and Deep Neural Network
| Title | Hiding Data in Images Using Cryptography and Deep Neural Network |
| Authors | Kartik Sharma, Ashutosh Aggarwal, Tanay Singhania, Deepak Gupta, Ashish Khanna |
| Abstract | Steganography is an art of obscuring data inside another quotidian file of similar or varying types. Hiding data has always been of significant importance to digital forensics. Previously, steganography has been combined with cryptography and neural networks separately. Whereas, this research combines steganography, cryptography with the neural networks all together to hide an image inside another container image of the larger or same size. Although the cryptographic technique used is quite simple, but is effective when convoluted with deep neural nets. Other steganography techniques involve hiding data efficiently, but in a uniform pattern which makes it less secure. This method targets both the challenges and make data hiding secure and non-uniform. |
| Tasks | |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.10413v1 |
| https://arxiv.org/pdf/1912.10413v1.pdf | |
| PWC | https://paperswithcode.com/paper/hiding-data-in-images-using-cryptography-and |
| Repo | |
| Framework | |
Underwater Fish Detection with Weak Multi-Domain Supervision
| Title | Underwater Fish Detection with Weak Multi-Domain Supervision |
| Authors | Dmitry A. Konovalov, Alzayat Saleh, Michael Bradley, Mangalam Sankupellay, Simone Marini, Marcus Sheaves |
| Abstract | Given a sufficiently large training dataset, it is relatively easy to train a modern convolution neural network (CNN) as a required image classifier. However, for the task of fish classification and/or fish detection, if a CNN was trained to detect or classify particular fish species in particular background habitats, the same CNN exhibits much lower accuracy when applied to new/unseen fish species and/or fish habitats. Therefore, in practice, the CNN needs to be continuously fine-tuned to improve its classification accuracy to handle new project-specific fish species or habitats. In this work we present a labelling-efficient method of training a CNN-based fish-detector (the Xception CNN was used as the base) on relatively small numbers (4,000) of project-domain underwater fish/no-fish images from 20 different habitats. Additionally, 17,000 of known negative (that is, missing fish) general-domain (VOC2012) above-water images were used. Two publicly available fish-domain datasets supplied additional 27,000 of above-water and underwater positive/fish images. By using this multi-domain collection of images, the trained Xception-based binary (fish/not-fish) classifier achieved 0.17% false-positives and 0.61% false-negatives on the project’s 20,000 negative and 16,000 positive holdout test images, respectively. The area under the ROC curve (AUC) was 99.94%. |
| Tasks | Fish Detection |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1905.10708v2 |
| https://arxiv.org/pdf/1905.10708v2.pdf | |
| PWC | https://paperswithcode.com/paper/underwater-fish-detection-with-weak-multi |
| Repo | |
| Framework | |
Automating Agential Reasoning: Proof-Calculi and Syntactic Decidability for STIT Logics
| Title | Automating Agential Reasoning: Proof-Calculi and Syntactic Decidability for STIT Logics |
| Authors | Tim Lyon, Kees van Berkel |
| Abstract | This work provides proof-search algorithms and automated counter-model extraction for a class of STIT logics. With this, we answer an open problem concerning syntactic decision procedures and cut-free calculi for STIT logics. A new class of cut-free complete labelled sequent calculi G3LdmL^m_n, for multi-agent STIT with at most n-many choices, is introduced. We refine the calculi G3LdmL^m_n through the use of propagation rules and demonstrate the admissibility of their structural rules, resulting in auxiliary calculi Ldm^m_nL. In the single-agent case, we show that the refined calculi Ldm^m_nL derive theorems within a restricted class of (forestlike) sequents, allowing us to provide proof-search algorithms that decide single-agent STIT logics. We prove that the proof-search algorithms are correct and terminate. |
| Tasks | |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11360v4 |
| https://arxiv.org/pdf/1908.11360v4.pdf | |
| PWC | https://paperswithcode.com/paper/automating-agential-reasoning-proof-calculi |
| Repo | |
| Framework | |
A gray-box model for a probabilistic estimate of regional ground magnetic perturbations: Enhancing the NOAA operational Geospace model with machine learning
| Title | A gray-box model for a probabilistic estimate of regional ground magnetic perturbations: Enhancing the NOAA operational Geospace model with machine learning |
| Authors | Enrico Camporeale, M. D. Cash, H. J. Singer, C. C. Balch, Z. Huang, G. Toth |
| Abstract | We present a novel algorithm that predicts the probability that time derivative of the horizontal component of the ground magnetic field $dB/dt$ exceeds a specified threshold at a given location. This quantity provides important information that is physically relevant to Geomagnetically Induced Currents (GIC), which are electric currents induced by sudden changes of the Earth’s magnetic field due to Space Weather events. The model follows a ‘gray-box’ approach by combining the output of a physics-based model with a machine learning approach. Specifically, we use the University of Michigan’s Geospace model, that is operational at the NOAA Space Weather Prediction Center, with a boosted ensemble of classification trees. We discuss in detail the issue of combining a large dataset of ground-based measurements ($\sim$ 20 years) with a limited set of simulation runs ($\sim$ 2 years) by developing a surrogate model for the years in which simulation runs are not available. We also discuss the problem of re-calibrating the output of the decision tree to obtain reliable probabilities. The performance of the model is assessed by typical metrics for probabilistic forecasts: Probability of Detection and False Detection, True Skill Score, Heidke Skill Score, and Receiver Operating Characteristic curve. |
| Tasks | |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.01038v1 |
| https://arxiv.org/pdf/1912.01038v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-gray-box-model-for-a-probabilistic-estimate |
| Repo | |
| Framework | |
The Expressivity and Training of Deep Neural Networks: toward the Edge of Chaos?
| Title | The Expressivity and Training of Deep Neural Networks: toward the Edge of Chaos? |
| Authors | Gege Zhang, Gangwei Li, Ningwei Shen, Weidong Zhang |
| Abstract | Expressivity is one of the most significant issues in assessing neural networks. In this paper, we provide a quantitative analysis of the expressivity for the deep neural network (DNN) from its dynamic model, where the Hilbert space is employed to analyze the convergence and criticality. We study the feature mapping of several widely used activation functions obtained by Hermite polynomials, and find sharp declines or even saddle points in the feature space, which stagnate the information transfer in DNNs. We then present a new activation function design based on the Hermite polynomials for better utilization of spatial representation. Moreover, we analyze the information transfer of DNNs, emphasizing the convergence problem caused by the mismatch between input and topological structure. We also study the effects of input perturbations and regularization operators on critical expressivity. Our theoretical analysis reveals that DNNs use spatial domains for information representation and evolve to the edge of chaos as depth increases. In actual training, whether a particular network can ultimately arrive the edge of chaos depends on its ability to overcome convergence and pass information to the required network depth. Finally, we demonstrate the empirical performance of the proposed hypothesis via multivariate time series prediction and image classification examples. |
| Tasks | Image Classification, Time Series, Time Series Prediction |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.04970v2 |
| https://arxiv.org/pdf/1910.04970v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-expressivity-and-training-of-deep-neural |
| Repo | |
| Framework | |
Learning the Representations of Moist Convection with Convolutional Neural Networks
| Title | Learning the Representations of Moist Convection with Convolutional Neural Networks |
| Authors | Shih-Wen Tsou, Chun-Yian Su, Chien-Ming Wu |
| Abstract | The representations of atmospheric moist convection in general circulation models have been one of the most challenging tasks due to its complexity in physical processes, and the interaction between processes under different time/spatial scales. This study proposes a new method to predict the effects of moist convection on the environment using convolutional neural networks. With the help of considering the gradient of physical fields between adjacent grids in the grey zone resolution, the effects of moist convection predicted by the convolutional neural networks are more realistic compared to the effects predicted by other machine learning models. The result also suggests that the method proposed in this study has the potential to replace the conventional cumulus parameterization in the general circulation models. |
| Tasks | |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09614v1 |
| https://arxiv.org/pdf/1905.09614v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-the-representations-of-moist |
| Repo | |
| Framework | |
NPA: Neural News Recommendation with Personalized Attention
| Title | NPA: Neural News Recommendation with Personalized Attention |
| Authors | Chuhan Wu, Fangzhao Wu, Mingxiao An, Jianqiang Huang, Yongfeng Huang, Xing Xie |
| Abstract | News recommendation is very important to help users find interested news and alleviate information overload. Different users usually have different interests and the same user may have various interests. Thus, different users may click the same news article with attention on different aspects. In this paper, we propose a neural news recommendation model with personalized attention (NPA). The core of our approach is a news representation model and a user representation model. In the news representation model we use a CNN network to learn hidden representations of news articles based on their titles. In the user representation model we learn the representations of users based on the representations of their clicked news articles. Since different words and different news articles may have different informativeness for representing news and users, we propose to apply both word- and news-level attention mechanism to help our model attend to important words and news articles. In addition, the same news article and the same word may have different informativeness for different users. Thus, we propose a personalized attention network which exploits the embedding of user ID to generate the query vector for the word- and news-level attentions. Extensive experiments are conducted on a real-world news recommendation dataset collected from MSN news, and the results validate the effectiveness of our approach on news recommendation. |
| Tasks | |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05559v1 |
| https://arxiv.org/pdf/1907.05559v1.pdf | |
| PWC | https://paperswithcode.com/paper/npa-neural-news-recommendation-with |
| Repo | |
| Framework | |
Towards Automatic Annotation for Semantic Segmentation in Drone Videos
| Title | Towards Automatic Annotation for Semantic Segmentation in Drone Videos |
| Authors | Alina Marcu, Dragos Costea, Vlad Licaret, Marius Leordeanu |
| Abstract | Semantic segmentation is a crucial task for robot navigation and safety. However, it requires huge amounts of pixelwise annotations to yield accurate results. While recent progress in computer vision algorithms has been heavily boosted by large ground-level datasets, the labeling time has hampered progress in low altitude UAV applications, mostly due to the difficulty imposed by large object scales and pose variations. Motivated by the lack of a large video aerial dataset, we introduce a new one, with high resolution (4K) images and manually-annotated dense labels every 50 frames. To help the video labeling process, we make an important step towards automatic annotation and propose SegProp, an iterative flow-based method with geometric constrains to propagate the semantic labels to frames that lack human annotations. This results in a dataset with more than 50k annotated frames - the largest of its kind, to the best of our knowledge. Our experiments show that SegProp surpasses current state-of-the-art label propagation methods by a significant margin. Furthermore, when training a semantic segmentation deep neural net using the automatically annotated frames, we obtain a compelling overall performance boost at test time of 16.8% mean F-measure over a baseline trained only with manually-labeled frames. Our Ruralscapes dataset, the label propagation code and a fast segmentation tool are available at our website: https://sites.google.com/site/aerialimageunderstanding/ |
| Tasks | Robot Navigation, Semantic Segmentation |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.10026v1 |
| https://arxiv.org/pdf/1910.10026v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-automatic-annotation-for-semantic |
| Repo | |
| Framework | |
MREAK : Morphological Retina Keypoint Descriptor
| Title | MREAK : Morphological Retina Keypoint Descriptor |
| Authors | Himanshu Vaghela, Manan Oza, Sudhir Bagul |
| Abstract | A variety of computer vision applications depend on the efficiency of image matching algorithms used. Various descriptors are designed to detect and match features in images. Deployment of this algorithms in mobile applications creates a need for low computation time. Binary descriptors requires less computation time than float-point based descriptors because of the intensity comparison between pairs of sample points and comparing after creating a binary string. In order to decrease time complexity, quality of keypoints matched is often compromised. We propose a keypoint descriptor named Morphological Retina Keypoint Descriptor (MREAK) inspired by the function of human pupil which dilates and constricts responding to the amount of light. By using morphological operators of opening and closing and modifying the retinal sampling pattern accordingly, an increase in the number of accurately matched keypoints is observed. Our results show that matched keypoints are more efficient than FREAK descriptor and requires low computation time than various descriptors like SIFT, BRISK and SURF. |
| Tasks | |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.08213v1 |
| http://arxiv.org/pdf/1901.08213v1.pdf | |
| PWC | https://paperswithcode.com/paper/mreak-morphological-retina-keypoint |
| Repo | |
| Framework | |
