April 2, 2020

3499 words 17 mins read

Paper Group ANR 362

Nonparametric inference for interventional effects with multiple mediators. An Evolutionary Deep Learning Method for Short-term Wind Speed Prediction: A Case Study of the Lillgrund Offshore Wind Farm. On the performance of deep learning models for time series classification in streaming. Forecasting Sequential Data using Consistent Koopman Autoenco …

Nonparametric inference for interventional effects with multiple mediators


Title	Nonparametric inference for interventional effects with multiple mediators
Authors	David Benkeser
Abstract	Understanding the pathways whereby an intervention has an effect on an outcome is a common scientific goal. A rich body of literature provides various decompositions of the total intervention effect into pathway specific effects. Interventional direct and indirect effects provide one such decomposition. Existing estimators of these effects are based on parametric models with confidence interval estimation facilitated via the nonparametric bootstrap. We provide theory that allows for more flexible, possibly machine learning-based, estimation techniques to be considered. In particular, we establish weak convergence results that facilitate the construction of closed-form confidence intervals and hypothesis tests. Finally, we demonstrate multiple robustness properties of the proposed estimators. Simulations show that inference based on large-sample theory has adequate small-sample performance. Our work thus provides a means of leveraging modern statistical learning techniques in estimation of interventional mediation effects.
Tasks
Published	2020-01-16
URL	https://arxiv.org/abs/2001.06027v1
PDF	https://arxiv.org/pdf/2001.06027v1.pdf
PWC	https://paperswithcode.com/paper/nonparametric-inference-for-interventional
Repo
Framework

An Evolutionary Deep Learning Method for Short-term Wind Speed Prediction: A Case Study of the Lillgrund Offshore Wind Farm


Title	An Evolutionary Deep Learning Method for Short-term Wind Speed Prediction: A Case Study of the Lillgrund Offshore Wind Farm
Authors	Mehdi Neshat, Meysam Majidi Nezhad, Ehsan Abbasnejad, Lina Bertling Tjernberg, Davide Astiaso Garcia, Bradley Alexander, Markus Wagner
Abstract	Accurate short-term wind speed forecasting is essential for large-scale integration of wind power generation. However, the seasonal and stochastic characteristics of wind speed make forecasting a challenging task. This study uses a new hybrid evolutionary approach that uses a popular evolutionary search algorithm, CMA-ES, to tune the hyper-parameters of two Long short-term memory(LSTM) ANN models for wind prediction. The proposed hybrid approach is trained on data gathered from an offshore wind turbine installed in a Swedish wind farm located in the Baltic Sea. Two forecasting horizons including ten-minutes ahead (absolute short term) and one-hour ahead (short term) are considered in our experiments. Our experimental results indicate that the new approach is superior to five other applied machine learning models, i.e., polynomial neural network (PNN), feed-forward neural network (FNN), nonlinear autoregressive neural network (NAR) and adaptive neuro-fuzzy inference system (ANFIS), as measured by five performance criteria.
Tasks
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09106v1
PDF	https://arxiv.org/pdf/2002.09106v1.pdf
PWC	https://paperswithcode.com/paper/an-evolutionary-deep-learning-method-for
Repo
Framework

On the performance of deep learning models for time series classification in streaming


Title	On the performance of deep learning models for time series classification in streaming
Authors	Pedro Lara-Benítez, Manuel Carranza-García, Francisco Martínez-Álvarez, José C. Riquelme
Abstract	Processing data streams arriving at high speed requires the development of models that can provide fast and accurate predictions. Although deep neural networks are the state-of-the-art for many machine learning tasks, their performance in real-time data streaming scenarios is a research area that has not yet been fully addressed. Nevertheless, there have been recent efforts to adapt complex deep learning models for streaming tasks by reducing their processing rate. The design of the asynchronous dual-pipeline deep learning framework allows to predict over incoming instances and update the model simultaneously using two separate layers. The aim of this work is to assess the performance of different types of deep architectures for data streaming classification using this framework. We evaluate models such as multi-layer perceptrons, recurrent, convolutional and temporal convolutional neural networks over several time-series datasets that are simulated as streams. The obtained results indicate that convolutional architectures achieve a higher performance in terms of accuracy and efficiency.
Tasks	Time Series, Time Series Classification
Published	2020-03-05
URL	https://arxiv.org/abs/2003.02544v1
PDF	https://arxiv.org/pdf/2003.02544v1.pdf
PWC	https://paperswithcode.com/paper/on-the-performance-of-deep-learning-models
Repo
Framework

Forecasting Sequential Data using Consistent Koopman Autoencoders


Title	Forecasting Sequential Data using Consistent Koopman Autoencoders
Authors	Omri Azencot, N. Benjamin Erichson, Vanessa Lin, Michael W. Mahoney
Abstract	Recurrent neural networks are widely used on time series data, yet such models often ignore the underlying physical structures in such sequences. A new class of physically-based methods related to Koopman theory has been introduced, offering an alternative for processing nonlinear dynamical systems. In this work, we propose a novel Consistent Koopman Autoencoder model which, unlike the majority of existing work, leverages the forward and backward dynamics. Key to our approach is a new analysis that unravels the interplay between consistent dynamics and their associated Koopman operators. Our network is interpretable from a physical viewpoint and its computational requirements are comparable to other baselines. We evaluate our method on a wide range of high-dimensional and short-term dependent problems. The datasets include nonlinear oscillators, sea surface temperature data, and fluid flows on a curved domain. The results show that our model yields accurate estimates for significant prediction horizons, while being robust to noise.
Tasks	Time Series
Published	2020-03-04
URL	https://arxiv.org/abs/2003.02236v1
PDF	https://arxiv.org/pdf/2003.02236v1.pdf
PWC	https://paperswithcode.com/paper/forecasting-sequential-data-using-consistent
Repo
Framework

Wind speed prediction using a hybrid model of the multi-layer perceptron and whale optimization algorithm


Title	Wind speed prediction using a hybrid model of the multi-layer perceptron and whale optimization algorithm
Authors	Saeed Samadianfard, Sajjad Hashemi, Katayoun Kargar, Mojtaba Izadyar, Ali Mostafaeipour, Amir Mosavi, Narjes Nabipour, Shahaboddin Shamshirband
Abstract	Wind power as a renewable source of energy, has numerous economic, environmental and social benefits. In order to enhance and control renewable wind power, it is vital to utilize models that predict wind speed with high accuracy. Due to neglecting of requirement and significance of data preprocessing and disregarding the inadequacy of using a single predicting model, many traditional models have poor performance in wind speed prediction. In the current study, for predicting wind speed at target stations in the north of Iran, the combination of a multi-layer perceptron model (MLP) with the Whale Optimization Algorithm (WOA) used to build new method (MLP-WOA) with a limited set of data (2004-2014). Then, the MLP-WOA model was utilized at each of the ten target stations, with the nine stations for training and tenth station for testing (namely: Astara, Bandar-E-Anzali, Rasht, Manjil, Jirandeh, Talesh, Kiyashahr, Lahijan, Masuleh, and Deylaman) to increase the accuracy of the subsequent hybrid model. The capability of the hybrid model in wind speed forecasting at each target station was compared with the MLP model without the WOA optimizer. To determine definite results, numerous statistical performances were utilized. For all ten target stations, the MLP-WOA model had precise outcomes than the standalone MLP model. The hybrid model had acceptable performances with lower amounts of the RMSE, SI and RE parameters and higher values of NSE, WI, and KGE parameters. It was concluded that the WOA optimization algorithm can improve the prediction accuracy of MLP model and may be recommended for accurate wind speed prediction.
Tasks
Published	2020-02-14
URL	https://arxiv.org/abs/2002.06226v1
PDF	https://arxiv.org/pdf/2002.06226v1.pdf
PWC	https://paperswithcode.com/paper/wind-speed-prediction-using-a-hybrid-model-of
Repo
Framework

Reinforcement Learning Based Vehicle-cell Association Algorithm for Highly Mobile Millimeter Wave Communication


Title	Reinforcement Learning Based Vehicle-cell Association Algorithm for Highly Mobile Millimeter Wave Communication
Authors	Hamza Khan, Anis Elgabli, Sumudu Samarakoon, Mehdi Bennis, Choong Seon Hong
Abstract	Vehicle-to-everything (V2X) communication is a growing area of communication with a variety of use cases. This paper investigates the problem of vehicle-cell association in millimeter wave (mmWave) communication networks. The aim is to maximize the time average rate per vehicular user (VUE) while ensuring a target minimum rate for all VUEs with low signaling overhead. We first formulate the user (vehicle) association problem as a discrete non-convex optimization problem. Then, by leveraging tools from machine learning, specifically distributed deep reinforcement learning (DDRL) and the asynchronous actor critic algorithm (A3C), we propose a low complexity algorithm that approximates the solution of the proposed optimization problem. The proposed DDRL-based algorithm endows every road side unit (RSU) with a local RL agent that selects a local action based on the observed input state. Actions of different RSUs are forwarded to a central entity, that computes a global reward which is then fed back to RSUs. It is shown that each independently trained RL performs the vehicle-RSU association action with low control overhead and less computational complexity compared to running an online complex algorithm to solve the non-convex optimization problem. Finally, simulation results show that the proposed solution achieves up to 15% gains in terms of sum rate and 20% reduction in VUE outages compared to several baseline designs.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.07915v1
PDF	https://arxiv.org/pdf/2001.07915v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-based-vehicle-cell
Repo
Framework

Performance Evaluation of Advanced Deep Learning Architectures for Offline Handwritten Character Recognition


Title	Performance Evaluation of Advanced Deep Learning Architectures for Offline Handwritten Character Recognition
Authors	Moazam Soomro, Muhammad Ali Farooq, Rana Hammad Raza
Abstract	This paper presents a hand-written character recognition comparison and performance evaluation for robust and precise classification of different hand-written characters. The system utilizes advanced multilayer deep neural network by collecting features from raw pixel values. The hidden layers stack deep hierarchies of non-linear features since learning complex features from conventional neural networks is very challenging. Two state of the art deep learning architectures were used which includes Caffe AlexNet and GoogleNet models in NVIDIA DIGITS.The frameworks were trained and tested on two different datasets for incorporating diversity and complexity. One of them is the publicly available dataset i.e. Chars74K comprising of 7705 characters and has upper and lowercase English alphabets, along with numerical digits. While the other dataset created locally consists of 4320 characters. The local dataset consists of 62 classes and was created by 40 subjects. It also consists upper and lowercase English alphabets, along with numerical digits. The overall dataset is divided in the ratio of 80% for training and 20% for testing phase. The time required for training phase is approximately 90 minutes. For validation part, the results obtained were compared with the groundtruth. The accuracy level achieved with AlexNet was 77.77% and 88.89% with Google Net. The higher accuracy level of GoogleNet is due to its unique combination of inception modules, each including pooling, convolutions at various scales and concatenation procedures.
Tasks
Published	2020-03-15
URL	https://arxiv.org/abs/2003.06794v1
PDF	https://arxiv.org/pdf/2003.06794v1.pdf
PWC	https://paperswithcode.com/paper/performance-evaluation-of-advanced-deep
Repo
Framework

Learn to Predict Sets Using Feed-Forward Neural Networks


Title	Learn to Predict Sets Using Feed-Forward Neural Networks
Authors	Hamid Rezatofighi, Roman Kaskman, Farbod T. Motlagh, Qinfeng Shi, Anton Milan, Daniel Cremers, Laura Leal-Taixé, Ian Reid
Abstract	This paper addresses the task of set prediction using deep feed-forward neural networks. A set is a collection of elements which is invariant under permutation and the size of a set is not fixed in advance. Many real-world problems, such as image tagging and object detection, have outputs that are naturally expressed as sets of entities. This creates a challenge for traditional deep neural networks which naturally deal with structured outputs such as vectors, matrices or tensors. We present a novel approach for learning to predict sets with unknown permutation and cardinality using deep neural networks. In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality. Depending on the problem under consideration, we define different training models for set prediction using deep neural networks. We demonstrate the validity of our set formulations on relevant vision problems such as: 1)multi-label image classification where we achieve state-of-the-art performance on the PASCAL VOC and MS COCO datasets, 2) object detection, for which our formulation outperforms state-of-the-art detectors such as Faster R-CNN and YOLO v3, and 3) a complex CAPTCHA test, where we observe that, surprisingly, our set-based network acquired the ability of mimicking arithmetics without any rules being coded.
Tasks	Image Classification, Object Detection
Published	2020-01-30
URL	https://arxiv.org/abs/2001.11845v1
PDF	https://arxiv.org/pdf/2001.11845v1.pdf
PWC	https://paperswithcode.com/paper/learn-to-predict-sets-using-feed-forward
Repo
Framework

An End-to-End Geometric Deficiency Elimination Algorithm for 3D Meshes


Title	An End-to-End Geometric Deficiency Elimination Algorithm for 3D Meshes
Authors	Bingtao Ma, Hongsen Liu, Liangliang Nan, Yang Cong
Abstract	The 3D mesh is an important representation of geometric data. In the generation of mesh data, geometric deficiencies (e.g., duplicate elements, degenerate faces, isolated vertices, self-intersection, and inner faces) are unavoidable and may violate the topology structure of an object. In this paper, we propose an effective and efficient geometric deficiency elimination algorithm for 3D meshes. Specifically, duplicate elements can be eliminated by assessing the occurrence times of vertices or faces, degenerate faces can be removed according to the outer product of two edges; since isolated vertices do not appear in any face vertices, they can be deleted directly; self-intersecting faces are detected using an AABB tree and remeshed afterward; by simulating whether multiple random rays that shoot from a face can reach infinity, we can judge whether the surface is an inner face, then decide to delete it or not. Experiments on ModelNet40 dataset illustrate that our method can eliminate the deficiencies of the 3D mesh thoroughly.
Tasks
Published	2020-03-14
URL	https://arxiv.org/abs/2003.06535v1
PDF	https://arxiv.org/pdf/2003.06535v1.pdf
PWC	https://paperswithcode.com/paper/an-end-to-end-geometric-deficiency
Repo
Framework

Hand-Priming in Object Localization for Assistive Egocentric Vision


Title	Hand-Priming in Object Localization for Assistive Egocentric Vision
Authors	Kyungjun Lee, Abhinav Shrivastava, Hernisa Kacorri
Abstract	Egocentric vision holds great promises for increasing access to visual information and improving the quality of life for people with visual impairments, with object recognition being one of the daily challenges for this population. While we strive to improve recognition performance, it remains difficult to identify which object is of interest to the user; the object may not even be included in the frame due to challenges in camera aiming without visual feedback. Also, gaze information, commonly used to infer the area of interest in egocentric vision, is often not dependable. However, blind users often tend to include their hand either interacting with the object that they wish to recognize or simply placing it in proximity for better camera aiming. We propose localization models that leverage the presence of the hand as the contextual information for priming the center area of the object of interest. In our approach, hand segmentation is fed to either the entire localization network or its last convolutional layers. Using egocentric datasets from sighted and blind individuals, we show that the hand-priming achieves higher precision than other approaches, such as fine-tuning, multi-class, and multi-task learning, which also encode hand-object interactions in localization.
Tasks	Hand Segmentation, Multi-Task Learning, Object Localization, Object Recognition
Published	2020-02-28
URL	https://arxiv.org/abs/2002.12557v1
PDF	https://arxiv.org/pdf/2002.12557v1.pdf
PWC	https://paperswithcode.com/paper/hand-priming-in-object-localization-for
Repo
Framework

Reward Design in Cooperative Multi-agent Reinforcement Learning for Packet Routing


Title	Reward Design in Cooperative Multi-agent Reinforcement Learning for Packet Routing
Authors	Hangyu Mao, Zhibo Gong, Zhen Xiao
Abstract	In cooperative multi-agent reinforcement learning (MARL), how to design a suitable reward signal to accelerate learning and stabilize convergence is a critical problem. The global reward signal assigns the same global reward to all agents without distinguishing their contributions, while the local reward signal provides different local rewards to each agent based solely on individual behavior. Both of the two reward assignment approaches have some shortcomings: the former might encourage lazy agents, while the latter might produce selfish agents. In this paper, we study reward design problem in cooperative MARL based on packet routing environments. Firstly, we show that the above two reward signals are prone to produce suboptimal policies. Then, inspired by some observations and considerations, we design some mixed reward signals, which are off-the-shelf to learn better policies. Finally, we turn the mixed reward signals into the adaptive counterparts, which achieve best results in our experiments. Other reward signals are also discussed in this paper. As reward design is a very fundamental problem in RL and especially in MARL, we hope that MARL researchers can rethink the rewards used in their systems.
Tasks	Multi-agent Reinforcement Learning
Published	2020-03-05
URL	https://arxiv.org/abs/2003.03433v1
PDF	https://arxiv.org/pdf/2003.03433v1.pdf
PWC	https://paperswithcode.com/paper/reward-design-in-cooperative-multi-agent-1
Repo
Framework

Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition


Title	Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition
Authors	Jens Bayer, David Münch, Michael Arens
Abstract	Living in a complex world like ours makes it unacceptable that a practical implementation of a machine learning system assumes a closed world. Therefore, it is necessary for such a learning-based system in a real world environment, to be aware of its own capabilities and limits and to be able to distinguish between confident and unconfident results of the inference, especially if the sample cannot be explained by the underlying distribution. This knowledge is particularly essential in safety-critical environments and tasks e.g. self-driving cars or medical applications. Towards this end, we transfer image-based Out-of-Distribution (OoD)-methods to graph-based data and show the applicability in action recognition. The contribution of this work is (i) the examination of the portability of recent image-based OoD-detectors for graph-based input data, (ii) a Metric Learning-based approach to detect OoD-samples, and (iii) the introduction of a novel semi-synthetic action recognition dataset. The evaluation shows that image-based OoD-methods can be applied to graph-based data. Additionally, there is a gap between the performance on intraclass and intradataset results. First methods as the examined baseline or ODIN provide reasonable results. More sophisticated network architectures - in contrast to their image-based application - were surpassed in the intradataset comparison and even lead to less classification accuracy.
Tasks	Metric Learning, Self-Driving Cars, Temporal Action Localization
Published	2020-03-03
URL	https://arxiv.org/abs/2003.01719v1
PDF	https://arxiv.org/pdf/2003.01719v1.pdf
PWC	https://paperswithcode.com/paper/image-based-ood-detector-principles-on-graph
Repo
Framework

FRSign: A Large-Scale Traffic Light Dataset for Autonomous Trains


Title	FRSign: A Large-Scale Traffic Light Dataset for Autonomous Trains
Authors	Jeanine Harb, Nicolas Rébéna, Raphaël Chosidow, Grégoire Roblin, Roman Potarusov, Hatem Hajri
Abstract	In the realm of autonomous transportation, there have been many initiatives for open-sourcing self-driving cars datasets, but much less for alternative methods of transportation such as trains. In this paper, we aim to bridge the gap by introducing FRSign, a large-scale and accurate dataset for vision-based railway traffic light detection and recognition. Our recordings were made on selected running trains in France and benefited from carefully hand-labeled annotations. An illustrative dataset which corresponds to ten percent of the acquired data to date is published in open source with the paper. It contains more than 100,000 images illustrating six types of French railway traffic lights and their possible color combinations, together with the relevant information regarding their acquisition such as date, time, sensor parameters, and bounding boxes. This dataset is published in open-source at the address \url{https://frsign.irt-systemx.fr}. We compare, analyze various properties of the dataset and provide metrics to express its variability. We also discuss specific challenges and particularities related to autonomous trains in comparison to autonomous cars.
Tasks	Self-Driving Cars
Published	2020-02-05
URL	https://arxiv.org/abs/2002.05665v1
PDF	https://arxiv.org/pdf/2002.05665v1.pdf
PWC	https://paperswithcode.com/paper/frsign-a-large-scale-traffic-light-dataset
Repo
Framework

General-Purpose Communicative Function Recognition using a Hierarchical Network with Cascading Outputs and Maximum a Posteriori Path Estimation


Title	General-Purpose Communicative Function Recognition using a Hierarchical Network with Cascading Outputs and Maximum a Posteriori Path Estimation
Authors	Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
Abstract	ISO 24617-2, the standard for dialog act annotation, defines a hierarchically organized set of general-purpose communicative functions. The automatic recognition of these functions, although practically unexplored, is relevant for a dialog system, since they provide cues regarding the intention behind the segments and how they should be interpreted. In this paper, we explore the recognition of general-purpose communicative functions in the DialogBank, which is a reference set of dialogs annotated according to the standard. To do so, we adapt a state-of-the-art approach on flat dialog act recognition to deal with the hierarchical classification problem. More specifically, we propose the use of a hierarchical network with cascading outputs and maximum a posteriori path estimation to predict the communicative function at each level of the hierarchy, preserve the dependencies between the functions in the path, and decide at which level to stop. Furthermore, since the amount of dialogs in the DialogBank is reduced, we rely both on additional dialogs annotated using mapping processes and on transfer learning to improve performance. The results of our experiments show that the hierarchical approach outperforms a flat one and that maximum a posteriori estimation outperforms an iterative prediction approach based on masking.
Tasks	Transfer Learning
Published	2020-03-07
URL	https://arxiv.org/abs/2003.03556v1
PDF	https://arxiv.org/pdf/2003.03556v1.pdf
PWC	https://paperswithcode.com/paper/general-purpose-communicative-function
Repo
Framework

Subjective Knowledge and Reasoning about Agents in Multi-Agent Systems


Title	Subjective Knowledge and Reasoning about Agents in Multi-Agent Systems
Authors	Shikha Singh, Deepak Khemani
Abstract	Though a lot of work in multi-agent systems is focused on reasoning about knowledge and beliefs of artificial agents, an explicit representation and reasoning about the presence/absence of agents, especially in the scenarios where agents may be unaware of other agents joining in or going offline in a multi-agent system, leading to partial knowledge/asymmetric knowledge of the agents is mostly overlooked by the MAS community. Such scenarios lay the foundations of cases where an agent can influence other agents’ mental states by (mis)informing them about the presence/absence of collaborators or adversaries. In this paper, we investigate how Kripke structure-based epistemic models can be extended to express the above notion based on an agent’s subjective knowledge and we discuss the challenges that come along.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.08016v1
PDF	https://arxiv.org/pdf/2001.08016v1.pdf
PWC	https://paperswithcode.com/paper/subjective-knowledge-and-reasoning-about
Repo
Framework