October 19, 2019

3161 words 15 mins read

Paper Group ANR 282

Approximate Dynamic Programming for Planning a Ride-Sharing System using Autonomous Fleets of Electric Vehicles. Non-Rigid Image Registration Using Self-Supervised Fully Convolutional Networks without Training Data. VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution. Optimal Parameter Choices via Precise Black-Box Analysis. …


Title	Approximate Dynamic Programming for Planning a Ride-Sharing System using Autonomous Fleets of Electric Vehicles
Authors	Lina Al-Kanj, Juliana Nascimento, Warren B. Powell
Abstract	Within a decade, almost every major auto company, along with fleet operators such as Uber, have announced plans to put autonomous vehicles on the road. At the same time, electric vehicles are quickly emerging as a next-generation technology that is cost effective, in addition to offering the benefits of reducing the carbon footprint. The combination of a centrally managed fleet of driverless vehicles, along with the operating characteristics of electric vehicles, is creating a transformative new technology that offers significant cost savings with high service levels. This problem involves a dispatch problem for assigning riders to cars, a surge pricing problem for deciding on the price per trip and a planning problem for deciding on the fleet size. We use approximate dynamic programming to develop high-quality operational dispatch strategies to determine which car is best for a particular trip, when a car should be recharged, and when it should be re-positioned to a different zone which offers a higher density of trips. We prove that the value functions are monotone in the battery and time dimensions and use hierarchical aggregation to get better estimates of the value functions with a small number of observations. Then, surge pricing is discussed using an adaptive learning approach to decide on the price for each trip. Finally, we discuss the fleet size problem which depends on the previous two problems.
Tasks	Autonomous Vehicles
Published	2018-10-18
URL	http://arxiv.org/abs/1810.08124v2
PDF	http://arxiv.org/pdf/1810.08124v2.pdf
PWC	https://paperswithcode.com/paper/approximate-dynamic-programming-for-planning
Repo
Framework

Non-Rigid Image Registration Using Self-Supervised Fully Convolutional Networks without Training Data


Title	Non-Rigid Image Registration Using Self-Supervised Fully Convolutional Networks without Training Data
Authors	Hongming Li, Yong Fan
Abstract	A novel non-rigid image registration algorithm is built upon fully convolutional networks (FCNs) to optimize and learn spatial transformations between pairs of images to be registered in a self-supervised learning framework. Different from most existing deep learning based image registration methods that learn spatial transformations from training data with known corresponding spatial transformations, our method directly estimates spatial transformations between pairs of images by maximizing an image-wise similarity metric between fixed and deformed moving images, similar to conventional image registration algorithms. The image registration is implemented in a multi-resolution image registration framework to jointly optimize and learn spatial transformations and FCNs at different spatial resolutions with deep self-supervision through typical feedforward and backpropagation computation. The proposed method has been evaluated for registering 3D structural brain magnetic resonance (MR) images and obtained better performance than state-of-the-art image registration algorithms.
Tasks	Image Registration
Published	2018-01-11
URL	http://arxiv.org/abs/1801.04012v1
PDF	http://arxiv.org/pdf/1801.04012v1.pdf
PWC	https://paperswithcode.com/paper/non-rigid-image-registration-using-self
Repo
Framework

VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution


Title	VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution
Authors	Rui Wang, Jeff Clune, Kenneth O. Stanley
Abstract	Recent advances in deep neuroevolution have demonstrated that evolutionary algorithms, such as evolution strategies (ES) and genetic algorithms (GA), can scale to train deep neural networks to solve difficult reinforcement learning (RL) problems. However, it remains a challenge to analyze and interpret the underlying process of neuroevolution in such high dimensions. To begin to address this challenge, this paper presents an interactive data visualization tool called VINE (Visual Inspector for NeuroEvolution) aimed at helping neuroevolution researchers and end-users better understand and explore this family of algorithms. VINE works seamlessly with a breadth of neuroevolution algorithms, including ES and GA, and addresses the difficulty of observing the underlying dynamics of the learning process through an interactive visualization of the evolving agent’s behavior characterizations over generations. As neuroevolution scales to neural networks with millions or more connections, visualization tools like VINE that offer fresh insight into the underlying dynamics of evolution become increasingly valuable and important for inspiring new innovations and applications.
Tasks
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01141v1
PDF	http://arxiv.org/pdf/1805.01141v1.pdf
PWC	https://paperswithcode.com/paper/vine-an-open-source-interactive-data
Repo
Framework

Optimal Parameter Choices via Precise Black-Box Analysis


Title	Optimal Parameter Choices via Precise Black-Box Analysis
Authors	Benjamin Doerr, Carola Doerr, Jing Yang
Abstract	It has been observed that some working principles of evolutionary algorithms, in particular, the influence of the parameters, cannot be understood from results on the asymptotic order of the runtime, but only from more precise results. In this work, we complement the emerging topic of precise runtime analysis with a first precise complexity theoretic result. Our vision is that the interplay between algorithm analysis and complexity theory becomes a fruitful tool also for analyses more precise than asymptotic orders of magnitude. As particular result, we prove that the unary unbiased black-box complexity of the OneMax benchmark function class is $n \ln(n) - cn \pm o(n)$ for a constant $c$ which is between $0.2539$ and $0.2665$. This runtime can be achieved with a simple (1+1)-type algorithm using a fitness-dependent mutation strength. When translated into the fixed-budget perspective, our algorithm finds solutions which are roughly 13% closer to the optimum than those of the best previously known algorithms. To prove our results, we formulate several new versions of the variable drift theorems, which also might be of independent interest.
Tasks
Published	2018-07-09
URL	http://arxiv.org/abs/1807.03403v2
PDF	http://arxiv.org/pdf/1807.03403v2.pdf
PWC	https://paperswithcode.com/paper/optimal-parameter-choices-via-precise-black
Repo
Framework

Off-the-grid model based deep learning (O-MODL)


Title	Off-the-grid model based deep learning (O-MODL)
Authors	Aniket Pramanik, Hemant Kumar Aggarwal, Mathews Jacob
Abstract	We introduce a model based off-the-grid image reconstruction algorithm using deep learned priors. The main difference of the proposed scheme with current deep learning strategies is the learning of non-linear annihilation relations in Fourier space. We rely on a model based framework, which allows us to use a significantly smaller deep network, compared to direct approaches that also learn how to invert the forward model. Preliminary comparisons against image domain MoDL approach demonstrates the potential of the off-the-grid formulation. The main benefit of the proposed scheme compared to structured low-rank methods is the quite significant reduction in computational complexity.
Tasks	Image Reconstruction
Published	2018-12-27
URL	http://arxiv.org/abs/1812.10747v1
PDF	http://arxiv.org/pdf/1812.10747v1.pdf
PWC	https://paperswithcode.com/paper/off-the-grid-model-based-deep-learning-o-modl
Repo
Framework

Learning beamforming in ultrasound imaging


Title	Learning beamforming in ultrasound imaging
Authors	Sanketh Vedula, Ortal Senouf, Grigoriy Zurakhov, Alex Bronstein, Oleg Michailovich, Michael Zibulevsky
Abstract	Medical ultrasound (US) is a widespread imaging modality owing its popularity to cost efficiency, portability, speed, and lack of harmful ionizing radiation. In this paper, we demonstrate that replacing the traditional ultrasound processing pipeline with a data-driven, learnable counterpart leads to significant improvement in image quality. Moreover, we demonstrate that greater improvement can be achieved through a learning-based design of the transmitted beam patterns simultaneously with learning an image reconstruction pipeline. We evaluate our method on an in-vivo first-harmonic cardiac ultrasound dataset acquired from volunteers and demonstrate the significance of the learned pipeline and transmit beam patterns on the image quality when compared to standard transmit and receive beamformers used in high frame-rate US imaging. We believe that the presented methodology provides a fundamentally different perspective on the classical problem of ultrasound beam pattern design.
Tasks	Image Reconstruction
Published	2018-12-19
URL	http://arxiv.org/abs/1812.08043v1
PDF	http://arxiv.org/pdf/1812.08043v1.pdf
PWC	https://paperswithcode.com/paper/learning-beamforming-in-ultrasound-imaging
Repo
Framework

A New Variational Model for Joint Image Reconstruction and Motion Estimation in Spatiotemporal Imaging


Title	A New Variational Model for Joint Image Reconstruction and Motion Estimation in Spatiotemporal Imaging
Authors	Chong Chen, Barbara Gris, Ozan Öktem
Abstract	We propose a new variational model for joint image reconstruction and motion estimation in spatiotemporal imaging, which is investigated along a general framework that we present with shape theory. This model consists of two components, one for conducting modified static image reconstruction, and the other performs sequentially indirect image registration. For the latter, we generalize the large deformation diffeomorphic metric mapping framework into the sequentially indirect registration setting. The proposed model is compared theoretically against alternative approaches (optical flow based model and diffeomorphic motion models), and we demonstrate that the proposed model has desirable properties in terms of the optimal solution. The theoretical derivations and efficient algorithms are also presented for a time-discretized scenario of the proposed model, which show that the optimal solution of the time-discretized version is consistent with that of the time-continuous one, and most of the computational components is the easy-implemented linearized deformation. The complexity of the algorithm is analyzed as well. This work is concluded by some numerical examples in 2D space + time tomography with very sparse and/or highly noisy data.
Tasks	Image Reconstruction, Image Registration, Motion Estimation, Optical Flow Estimation
Published	2018-12-09
URL	http://arxiv.org/abs/1812.03446v2
PDF	http://arxiv.org/pdf/1812.03446v2.pdf
PWC	https://paperswithcode.com/paper/a-new-variational-model-for-joint-image
Repo
Framework

A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees


Title	A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees
Authors	Klaus Broelemann, Gjergji Kasneci
Abstract	Machine learning algorithms aim at minimizing the number of false decisions and increasing the accuracy of predictions. However, the high predictive power of advanced algorithms comes at the costs of transparency. State-of-the-art methods, such as neural networks and ensemble methods, often result in highly complex models that offer little transparency. We propose shallow model trees as a way to combine simple and highly transparent predictive models for higher predictive power without losing the transparency of the original models. We present a novel split criterion for model trees that allows for significantly higher predictive power than state-of-the-art model trees while maintaining the same level of simplicity. This novel approach finds split points which allow the underlying simple models to make better predictions on the corresponding data. In addition, we introduce multiple mechanisms to increase the transparency of the resulting trees.
Tasks
Published	2018-09-25
URL	https://arxiv.org/abs/1809.09703v2
PDF	https://arxiv.org/pdf/1809.09703v2.pdf
PWC	https://paperswithcode.com/paper/a-gradient-based-split-criterion-for-highly
Repo
Framework

Real Time Elbow Angle Estimation Using Single RGB Camera


Title	Real Time Elbow Angle Estimation Using Single RGB Camera
Authors	Muhammad Yahya, Jawad Ali Shah, Arif Warsi, Kushsairy Kadir, Sheroz Khan, M Izani
Abstract	The use of motion capture has increased from last decade in a varied spectrum of applications like film special effects, controlling games and robots, rehabilitation system, animations etc. The current human motion capture techniques use markers, structured environment, and high resolution cameras in a dedicated environment. Because of rapid movement, elbow angle estimation is observed as the most difficult problem in human motion capture system. In this paper, we take elbow angle estimation as our research subject and propose a novel, markerless and cost-effective solution that uses RGB camera for estimating elbow angle in real time using part affinity field. We have recruited five (5) participants to perform cup to mouth movement and at the same time measured the angle by both RGB camera and Microsoft Kinect. The experimental results illustrate that markerless and cost-effective RGB camera has a median RMS errors of 3.06{\deg} and 0.95{\deg} in sagittal and coronal plane respectively as compared to Microsoft Kinect.
Tasks	Motion Capture
Published	2018-08-21
URL	http://arxiv.org/abs/1808.07017v1
PDF	http://arxiv.org/pdf/1808.07017v1.pdf
PWC	https://paperswithcode.com/paper/real-time-elbow-angle-estimation-using-single
Repo
Framework

Rotting bandits are no harder than stochastic ones


Title	Rotting bandits are no harder than stochastic ones
Authors	Julien Seznec, Andrea Locatelli, Alexandra Carpentier, Alessandro Lazaric, Michal Valko
Abstract	In bandits, arms’ distributions are stationary. This is often violated in practice, where rewards change over time. In applications as recommendation systems, online advertising, and crowdsourcing, the changes may be triggered by the pulls, so that the arms’ rewards change as a function of the number of pulls. In this paper, we consider the specific case of non-parametric rotting bandits, where the expected reward of an arm may decrease every time it is pulled. We introduce the filtering on expanding window average (FEWA) algorithm that at each round constructs moving averages of increasing windows to identify arms that are more likely to return high rewards when pulled once more. We prove that, without any knowledge on the decreasing behavior of the arms, FEWA achieves similar anytime problem-dependent, $\widetilde{\mathcal{O}}(\log{(KT)}),$ and problem-independent, $\widetilde{\mathcal{O}}(\sqrt{KT})$, regret bounds of near-optimal stochastic algorithms as UCB1 of Auer et al. (2002a). This result substantially improves the prior result of Levine et al. (2017) which needed knowledge of the horizon and decaying parameters to achieve problem-independent bound of only $\widetilde{\mathcal{O}}(K^{1/3}T^{2/3})$. Finally, we report simulations confirming the theoretical improvements of FEWA.
Tasks	Recommendation Systems
Published	2018-11-27
URL	http://arxiv.org/abs/1811.11043v1
PDF	http://arxiv.org/pdf/1811.11043v1.pdf
PWC	https://paperswithcode.com/paper/rotting-bandits-are-no-harder-than-stochastic
Repo
Framework

Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues


Title	Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues
Authors	Yaohua Sun, Mugen Peng, Yangcheng Zhou, Yuzhe Huang, Shiwen Mao
Abstract	As a key technique for enabling artificial intelligence, machine learning (ML) is capable of solving complex problems without explicit programming. Motivated by its successful applications to many practical tasks like image recognition, both industry and the research community have advocated the applications of ML in wireless communication. This paper comprehensively surveys the recent advances of the applications of ML in wireless communication, which are classified as: resource management in the MAC layer, networking and mobility management in the network layer, and localization in the application layer. The applications in resource management further include power control, spectrum management, backhaul management, cache management, beamformer design and computation resource management, while ML based networking focuses on the applications in clustering, base station switching control, user association and routing. Moreover, literatures in each aspect is organized according to the adopted ML techniques. In addition, several conditions for applying ML to wireless communication are identified to help readers decide whether to use ML and which kind of ML techniques to use, and traditional approaches are also summarized together with their performance comparison with ML based approaches, based on which the motivations of surveyed literatures to adopt ML are clarified. Given the extensiveness of the research area, challenges and unresolved issues are presented to facilitate future studies, where ML based network slicing, infrastructure update to support ML based paradigms, open data sets and platforms for researchers, theoretical guidance for ML implementation and so on are discussed.
Tasks	Recommendation Systems
Published	2018-09-24
URL	http://arxiv.org/abs/1809.08707v2
PDF	http://arxiv.org/pdf/1809.08707v2.pdf
PWC	https://paperswithcode.com/paper/application-of-machine-learning-in-wireless
Repo
Framework

Towards a general mathematical theory of experimental science


Title	Towards a general mathematical theory of experimental science
Authors	Gabriele Carcassi, Christine A. Aidala
Abstract	We lay the groundwork for a formal framework that studies scientific theories and can serve as a unified foundation for the different theories within physics. We define a scientific theory as a set of verifiable statements, assertions that can be shown to be true with an experimental test in finite time. By studying the algebra of such objects, we show that verifiability already provides severe constraints. In particular, it requires that a set of physically distinguishable cases is naturally equipped with the mathematical structures (i.e. second-countable Kolmogorov topologies and $\sigma$-algebras) that form the foundation of manifold theory, differential geometry, measure theory, probability theory and all the major branches of mathematics currently used in physics. This gives a clear physical meaning to those mathematical structures and provides a strong justification for their use in science. Most importantly it provides a formal framework to incorporate additional assumptions and constrain the search space for new physical theories.
Tasks
Published	2018-06-22
URL	http://arxiv.org/abs/1807.07896v2
PDF	http://arxiv.org/pdf/1807.07896v2.pdf
PWC	https://paperswithcode.com/paper/towards-a-general-mathematical-theory-of
Repo
Framework

L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks


Title	L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
Authors	Shuang Wu, Guoqi Li, Lei Deng, Liu Liu, Yuan Xie, Luping Shi
Abstract	Batch Normalization (BN) has been proven to be quite effective at accelerating and improving the training of deep neural networks (DNNs). However, BN brings additional computation, consumes more memory and generally slows down the training process by a large margin, which aggravates the training effort. Furthermore, the nonlinear square and root operations in BN also impede the low bit-width quantization techniques, which draws much attention in deep learning hardware community. In this work, we propose an L1-norm BN (L1BN) with only linear operations in both the forward and the backward propagations during training. L1BN is shown to be approximately equivalent to the original L2-norm BN (L2BN) by multiplying a scaling factor. Experiments on various convolutional neural networks (CNNs) and generative adversarial networks (GANs) reveal that L1BN maintains almost the same accuracies and convergence rates compared to L2BN but with higher computational efficiency. On FPGA platform, the proposed signum and absolute operations in L1BN can achieve 1.5$\times$ speedup and save 50% power consumption, compared with the original costly square and root operations, respectively. This hardware-friendly normalization method not only surpasses L2BN in speed, but also simplify the hardware design of ASIC accelerators with higher energy efficiency. Last but not the least, L1BN promises a fully quantized training of DNNs, which is crucial to future adaptive terminal devices.
Tasks	Quantization
Published	2018-02-27
URL	http://arxiv.org/abs/1802.09769v1
PDF	http://arxiv.org/pdf/1802.09769v1.pdf
PWC	https://paperswithcode.com/paper/l1-norm-batch-normalization-for-efficient
Repo
Framework

Learning an Approximate Model Predictive Controller with Guarantees


Title	Learning an Approximate Model Predictive Controller with Guarantees
Authors	Michael Hertneck, Johannes Köhler, Sebastian Trimpe, Frank Allgöwer
Abstract	A supervised learning framework is proposed to approximate a model predictive controller (MPC) with reduced computational complexity and guarantees on stability and constraint satisfaction. The framework can be used for a wide class of nonlinear systems. Any standard supervised learning technique (e.g. neural networks) can be employed to approximate the MPC from samples. In order to obtain closed-loop guarantees for the learned MPC, a robust MPC design is combined with statistical learning bounds. The MPC design ensures robustness to inaccurate inputs within given bounds, and Hoeffding’s Inequality is used to validate that the learned MPC satisfies these bounds with high confidence. The result is a closed-loop statistical guarantee on stability and constraint satisfaction for the learned MPC. The proposed learning-based MPC framework is illustrated on a nonlinear benchmark problem, for which we learn a neural network controller with guarantees.
Tasks
Published	2018-06-11
URL	http://arxiv.org/abs/1806.04167v1
PDF	http://arxiv.org/pdf/1806.04167v1.pdf
PWC	https://paperswithcode.com/paper/learning-an-approximate-model-predictive
Repo
Framework

Multi-level Activation for Segmentation of Hierarchically-nested Classes


Title	Multi-level Activation for Segmentation of Hierarchically-nested Classes
Authors	Marie Piraud, Anjany Sekuboyina, Bjoern H. Menze
Abstract	For many biological image segmentation tasks, including topological knowledge, such as the nesting of classes, can greatly improve results. However, most `out-of-the-box’ CNN models are still blind to such prior information. In this paper, we propose a novel approach to encode this information, through a multi-level activation layer and three compatible losses. We benchmark all of them on nuclei segmentation in bright-field microscopy cell images from the 2018 Data Science Bowl challenge, offering an exemplary segmentation task with cells and nested subcellular structures. Our scheme greatly speeds up learning, and outperforms standard multi-class classification with soft-max activation and a previously proposed method stemming from it, improving the Dice score significantly (p-values<0.007). Our approach is conceptually simple, easy to implement and can be integrated in any CNN architecture. It can be generalized to a higher number of classes, with or without further relations of containment. \|
Tasks	Semantic Segmentation
Published	2018-04-05
URL	http://arxiv.org/abs/1804.01910v2
PDF	http://arxiv.org/pdf/1804.01910v2.pdf
PWC	https://paperswithcode.com/paper/multi-level-activation-for-segmentation-of
Repo
Framework