Paper Group ANR 959
Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks. Dense neural networks as sparse graphs and the lightning initialization. Listening for Sirens: Locating and Classifying Acoustic Alarms in City Scenes. Deep Inferential Spatial-Temporal Network for Forecasting Air Pollution Concentrations. Component …
Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks
| Title | Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks |
| Authors | Michele Polese, Rittwik Jana, Velin Kounev, Ke Zhang, Supratim Deb, Michele Zorzi |
| Abstract | The fifth generation of cellular networks (5G) will rely on edge cloud deployments to satisfy the ultra-low latency demand of future applications. In this paper, we argue that such deployments can also be used to enable advanced data-driven and Machine Learning (ML) applications in mobile networks. We propose an edge-controller-based architecture for cellular networks and evaluate its performance with real data from hundreds of base stations of a major U.S. operator. In this regard, we will provide insights on how to dynamically cluster and associate base stations and controllers, according to the global mobility patterns of the users. Then, we will describe how the controllers can be used to run ML algorithms to predict the number of users in each base station, and a use case in which these predictions are exploited by a higher-layer application to route vehicular traffic according to network Key Performance Indicators (KPIs). We show that the prediction accuracy improves when based on machine learning algorithms that rely on the controllers’ view and, consequently, on the spatial correlation introduced by the user mobility, with respect to when the prediction is based only on the local data of each single base station. |
| Tasks | |
| Published | 2018-08-23 |
| URL | http://arxiv.org/abs/1808.07647v3 |
| http://arxiv.org/pdf/1808.07647v3.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-at-the-edge-a-data-driven |
| Repo | |
| Framework | |
Dense neural networks as sparse graphs and the lightning initialization
| Title | Dense neural networks as sparse graphs and the lightning initialization |
| Authors | Thomas Pircher, Dominik Haspel, Eberhard Schlücker |
| Abstract | Even though dense networks have lost importance today, they are still used as final logic elements. It could be shown that these dense networks can be simplified by the sparse graph interpretation. This in turn shows that the information flow between input and output is not optimal with an initialization common today. The lightning initialization sets the weights so that complete information paths exist between input and output from the start. It turned out that pure dense networks and also more complex networks with additional layers benefit from this initialization. The networks accuracy increases faster. The lightning initialization has two parameters which behaved robustly in the tests carried out. However, especially with more complex networks, an improvement effect only occurs at lower learning rates, which shows that the initialization retains its positive effect over the epochs with learning rate reduction. |
| Tasks | |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.08836v1 |
| http://arxiv.org/pdf/1809.08836v1.pdf | |
| PWC | https://paperswithcode.com/paper/dense-neural-networks-as-sparse-graphs-and |
| Repo | |
| Framework | |
Listening for Sirens: Locating and Classifying Acoustic Alarms in City Scenes
| Title | Listening for Sirens: Locating and Classifying Acoustic Alarms in City Scenes |
| Authors | Letizia Marchegiani, Paul Newman |
| Abstract | This paper is about alerting acoustic event detection and sound source localisation in an urban scenario. Specifically, we are interested in spotting the presence of horns, and sirens of emergency vehicles. In order to obtain a reliable system able to operate robustly despite the presence of traffic noise, which can be copious, unstructured and unpredictable, we propose to treat the spectrograms of incoming stereo signals as images, and apply semantic segmentation, based on a Unet architecture, to extract the target sound from the background noise. In a multi-task learning scheme, together with signal denoising, we perform acoustic event classification to identify the nature of the alerting sound. Lastly, we use the denoised signals to localise the acoustic source on the horizon plane, by regressing the direction of arrival of the sound through a CNN architecture. Our experimental evaluation shows an average classification rate of 94%, and a median absolute error on the localisation of 7.5{\deg} when operating on audio frames of 0.5s, and of 2.5{\deg} when operating on frames of 2.5s. The system offers excellent performance in particularly challenging scenarios, where the noise level is remarkably high. |
| Tasks | Denoising, Multi-Task Learning, Semantic Segmentation |
| Published | 2018-10-11 |
| URL | http://arxiv.org/abs/1810.04989v1 |
| http://arxiv.org/pdf/1810.04989v1.pdf | |
| PWC | https://paperswithcode.com/paper/listening-for-sirens-locating-and-classifying |
| Repo | |
| Framework | |
Deep Inferential Spatial-Temporal Network for Forecasting Air Pollution Concentrations
| Title | Deep Inferential Spatial-Temporal Network for Forecasting Air Pollution Concentrations |
| Authors | Hao Wang, Bojin Zhuang, Yang Chen, Ni Li, Dongxia Wei |
| Abstract | Air pollution poses a serious threat to human health as well as economic development around the world. To meet the increasing demand for accurate predictions for air pollutions, we proposed a Deep Inferential Spatial-Temporal Network to deal with the complicated non-linear spatial and temporal correlations. We forecast three air pollutants (i.e., PM2.5, PM10 and O3) of monitoring stations over the next 48 hours, using a hybrid deep learning model consists of inferential predictor (inference for regions without air pollution readings), spatial predictor (capturing spatial correlations using CNN) and temporal predictor (capturing temporal relationship using sequence-to-sequence model with simplified attention mechanism). Our proposed model considers historical air pollution records and historical meteorological data. We evaluate our model on a large-scale dataset containing air pollution records of 35 monitoring stations and grid meteorological data in Beijing, China. Our model outperforms other state-of-art methods in terms of SMAPE and RMSE. |
| Tasks | |
| Published | 2018-09-11 |
| URL | http://arxiv.org/abs/1809.03964v1 |
| http://arxiv.org/pdf/1809.03964v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-inferential-spatial-temporal-network-for |
| Repo | |
| Framework | |
Component SPD Matrices: A lower-dimensional discriminative data descriptor for image set classification
| Title | Component SPD Matrices: A lower-dimensional discriminative data descriptor for image set classification |
| Authors | Kai-Xuan Chen, Xiao-Jun Wu |
| Abstract | In the domain of pattern recognition, using the SPD (Symmetric Positive Definite) matrices to represent data and taking the metrics of resulting Riemannian manifold into account have been widely used for the task of image set classification. In this paper, we propose a new data representation framework for image sets named CSPD (Component Symmetric Positive Definite). Firstly, we obtain sub-image sets by dividing the image set into square blocks with the same size, and use traditional SPD model to describe them. Then, we use the results of the Riemannian kernel on SPD matrices as similarities of corresponding sub-image sets. Finally, the CSPD matrix appears in the form of the kernel matrix for all the sub-image sets, and CSPDi,j denotes the similarity between i-th sub-image set and j-th sub-image set. Here, the Riemannian kernel is shown to satisfy the Mercer’s theorem, so our proposed CSPD matrix is symmetric and positive definite and also lies on a Riemannian manifold. On three benchmark datasets, experimental results show that CSPD is a lower-dimensional and more discriminative data descriptor for the task of image set classification. |
| Tasks | |
| Published | 2018-06-16 |
| URL | http://arxiv.org/abs/1806.06178v1 |
| http://arxiv.org/pdf/1806.06178v1.pdf | |
| PWC | https://paperswithcode.com/paper/component-spd-matrices-a-lower-dimensional |
| Repo | |
| Framework | |
Tell Me Something New: A New Framework for Asynchronous Parallel Learning
| Title | Tell Me Something New: A New Framework for Asynchronous Parallel Learning |
| Authors | Julaiti Alafate, Yoav Freund |
| Abstract | We present a novel approach for parallel computation in the context of machine learning that we call “Tell Me Something New” (TMSN). This approach involves a set of independent workers that use broadcast to update each other when they observe “something new”. TMSN does not require synchronization or a head node and is highly resilient against failing machines or laggards. We demonstrate the utility of TMSN by applying it to learning boosted trees. We show that our implementation is 10 times faster than XGBoost and LightGBM on the splice-site prediction problem. |
| Tasks | |
| Published | 2018-05-19 |
| URL | http://arxiv.org/abs/1805.07483v2 |
| http://arxiv.org/pdf/1805.07483v2.pdf | |
| PWC | https://paperswithcode.com/paper/tell-me-something-new-a-new-framework-for |
| Repo | |
| Framework | |
Stereo 3D Object Trajectory Reconstruction
| Title | Stereo 3D Object Trajectory Reconstruction |
| Authors | Sebastian Bullinger, Christoph Bodensteiner, Michael Arens, Rainer Stiefelhagen |
| Abstract | We present a method to reconstruct the three-dimensional trajectory of a moving instance of a known object category using stereo video data. We track the two-dimensional shape of objects on pixel level exploiting instance-aware semantic segmentation techniques and optical flow cues. We apply Structure from Motion (SfM) techniques to object and background images to determine for each frame initial camera poses relative to object instances and background structures. We refine the initial SfM results by integrating stereo camera constraints exploiting factor graphs. We compute the object trajectory by combining object and background camera pose information. In contrast to stereo matching methods, our approach leverages temporal adjacent views for object point triangulation. As opposed to monocular trajectory reconstruction approaches, our method shows no degenerated cases. We evaluate our approach using publicly available video data of vehicles in urban scenes. |
| Tasks | Optical Flow Estimation, Semantic Segmentation, Stereo Matching, Stereo Matching Hand |
| Published | 2018-08-27 |
| URL | http://arxiv.org/abs/1808.09297v1 |
| http://arxiv.org/pdf/1808.09297v1.pdf | |
| PWC | https://paperswithcode.com/paper/stereo-3d-object-trajectory-reconstruction |
| Repo | |
| Framework | |
Deep Model-Based 6D Pose Refinement in RGB
| Title | Deep Model-Based 6D Pose Refinement in RGB |
| Authors | Fabian Manhardt, Wadim Kehl, Nassir Navab, Federico Tombari |
| Abstract | We present a novel approach for model-based 6D pose refinement in color data. Building on the established idea of contour-based pose tracking, we teach a deep neural network to predict a translational and rotational update. At the core, we propose a new visual loss that drives the pose update by aligning object contours, thus avoiding the definition of any explicit appearance model. In contrast to previous work our method is correspondence-free, segmentation-free, can handle occlusion and is agnostic to geometrical symmetry as well as visual ambiguities. Additionally, we observe a strong robustness towards rough initialization. The approach can run in real-time and produces pose accuracies that come close to 3D ICP without the need for depth data. Furthermore, our networks are trained from purely synthetic data and will be published together with the refinement code to ensure reproducibility. |
| Tasks | Pose Tracking |
| Published | 2018-10-07 |
| URL | http://arxiv.org/abs/1810.03065v1 |
| http://arxiv.org/pdf/1810.03065v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-model-based-6d-pose-refinement-in-rgb |
| Repo | |
| Framework | |
Memristor-based Synaptic Sampling Machines
| Title | Memristor-based Synaptic Sampling Machines |
| Authors | Irina Dolzhikova, Khaled Salama, Vipin Kizheppatt, Alex Pappachen James |
| Abstract | Synaptic Sampling Machine (SSM) is a type of neural network model that considers biological unreliability of the synapses. We propose the circuit design of the SSM neural network which is realized through the memristive-CMOS crossbar structure with the synaptic sampling cell (SSC) being used as a basic stochastic unit. The increase in the edge computing devices in the Internet of things era, drives the need for hardware acceleration for data processing and computing. The computational considerations of the processing speed and possibility for the real-time realization pushes the synaptic sampling algorithm that demonstrated promising results on software for hardware implementation. |
| Tasks | |
| Published | 2018-08-02 |
| URL | http://arxiv.org/abs/1808.00679v1 |
| http://arxiv.org/pdf/1808.00679v1.pdf | |
| PWC | https://paperswithcode.com/paper/memristor-based-synaptic-sampling-machines |
| Repo | |
| Framework | |
SL$^2$MF: Predicting Synthetic Lethality in Human Cancers via Logistic Matrix Factorization
| Title | SL$^2$MF: Predicting Synthetic Lethality in Human Cancers via Logistic Matrix Factorization |
| Authors | Yong Liu, Min Wu, Chenghao Liu, Xiao-Li Li, Jie Zheng |
| Abstract | Synthetic lethality (SL) is a promising concept for novel discovery of anti-cancer drug targets. However, wet-lab experiments for detecting SLs are faced with various challenges, such as high cost, low consistency across platforms or cell lines. Therefore, computational prediction methods are needed to address these issues. This paper proposes a novel SL prediction method, named SL2MF, which employs logistic matrix factorization to learn latent representations of genes from the observed SL data. The probability that two genes are likely to form SL is modeled by the linear combination of gene latent vectors. As known SL pairs are more trustworthy than unknown pairs, we design importance weighting schemes to assign higher importance weights for known SL pairs and lower importance weights for unknown pairs in SL2MF. Moreover, we also incorporate biological knowledge about genes from protein-protein interaction (PPI) data and Gene Ontology (GO). In particular, we calculate the similarity between genes based on their GO annotations and topological properties in the PPI network. Extensive experiments on the SL interaction data from SynLethDB database have been conducted to demonstrate the effectiveness of SL2MF. |
| Tasks | |
| Published | 2018-10-20 |
| URL | http://arxiv.org/abs/1810.08726v1 |
| http://arxiv.org/pdf/1810.08726v1.pdf | |
| PWC | https://paperswithcode.com/paper/sl2mf-predicting-synthetic-lethality-in-human |
| Repo | |
| Framework | |
Multi-scale CNN stereo and pattern removal technique for underwater active stereo system
| Title | Multi-scale CNN stereo and pattern removal technique for underwater active stereo system |
| Authors | Kazuto Ichimaru, Ryo Furukawa, Hiroshi Kawasaki |
| Abstract | Demands on capturing dynamic scenes of underwater environments are rapidly growing. Passive stereo is applicable to capture dynamic scenes, however the shape with textureless surfaces or irregular reflections cannot be recovered by the technique. In our system, we add a pattern projector to the stereo camera pair so that artificial textures are augmented on the objects. To use the system at underwater environments, several problems should be compensated, i.e., refraction, disturbance by fluctuation and bubbles. Further, since surface of the objects are interfered by the bubbles, projected patterns, etc., those noises and patterns should be removed from captured images to recover original texture. To solve these problems, we propose three approaches; a depth-dependent calibration, Convolutional Neural Network(CNN)-stereo method and CNN-based texture recovery method. A depth-dependent calibration is our analysis to find the acceptable depth range for approximation by center projection to find the certain target depth for calibration. In terms of CNN stereo, unlike common CNNbased stereo methods which do not consider strong disturbances like refraction or bubbles, we designed a novel CNN architecture for stereo matching using multi-scale information, which is intended to be robust against such disturbances. Finally, we propose a multi-scale method for bubble and a projected-pattern removal method using CNNs to recover original textures. Experimental results are shown to prove the effectiveness of our method compared with the state of the art techniques. Furthermore, reconstruction of a live swimming fish is demonstrated to confirm the feasibility of our techniques. |
| Tasks | Calibration, Stereo Matching, Stereo Matching Hand |
| Published | 2018-08-25 |
| URL | http://arxiv.org/abs/1808.08348v1 |
| http://arxiv.org/pdf/1808.08348v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-scale-cnn-stereo-and-pattern-removal |
| Repo | |
| Framework | |
Adaptive Sampling for Convex Regression
| Title | Adaptive Sampling for Convex Regression |
| Authors | Max Simchowitz, Kevin Jamieson, Jordan W. Suchow, Thomas L. Griffiths |
| Abstract | In this paper, we introduce the first principled adaptive-sampling procedure for learning a convex function in the $L_\infty$ norm, a problem that arises often in the behavioral and social sciences. We present a function-specific measure of complexity and use it to prove that, for each convex function $f_{\star}$, our algorithm nearly attains the information-theoretically optimal, function-specific error rate. We also corroborate our theoretical contributions with numerical experiments, finding that our method substantially outperforms passive, uniform sampling for favorable synthetic and data-derived functions in low-noise settings with large sampling budgets. Our results also suggest an idealized “oracle strategy”, which we use to gauge the potential advance of any adaptive-sampling strategy over passive sampling, for any given convex function. |
| Tasks | |
| Published | 2018-08-14 |
| URL | http://arxiv.org/abs/1808.04523v3 |
| http://arxiv.org/pdf/1808.04523v3.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-sampling-for-convex-regression |
| Repo | |
| Framework | |
Grasp2Vec: Learning Object Representations from Self-Supervised Grasping
| Title | Grasp2Vec: Learning Object Representations from Self-Supervised Grasping |
| Authors | Eric Jang, Coline Devin, Vincent Vanhoucke, Sergey Levine |
| Abstract | Well structured visual representations can make robot learning faster and can improve generalization. In this paper, we study how we can acquire effective object-centric representations for robotic manipulation tasks without human labeling by using autonomous robot interaction with the environment. Such representation learning methods can benefit from continuous refinement of the representation as the robot collects more experience, allowing them to scale effectively without human intervention. Our representation learning approach is based on object persistence: when a robot removes an object from a scene, the representation of that scene should change according to the features of the object that was removed. We formulate an arithmetic relationship between feature vectors from this observation, and use it to learn a representation of scenes and objects that can then be used to identify object instances, localize them in the scene, and perform goal-directed grasping tasks where the robot must retrieve commanded objects from a bin. The same grasping procedure can also be used to automatically collect training data for our method, by recording images of scenes, grasping and removing an object, and recording the outcome. Our experiments demonstrate that this self-supervised approach for tasked grasping substantially outperforms direct reinforcement learning from images and prior representation learning methods. |
| Tasks | Representation Learning |
| Published | 2018-11-16 |
| URL | http://arxiv.org/abs/1811.06964v2 |
| http://arxiv.org/pdf/1811.06964v2.pdf | |
| PWC | https://paperswithcode.com/paper/grasp2vec-learning-object-representations |
| Repo | |
| Framework | |
Error estimates for spectral convergence of the graph Laplacian on random geometric graphs towards the Laplace–Beltrami operator
| Title | Error estimates for spectral convergence of the graph Laplacian on random geometric graphs towards the Laplace–Beltrami operator |
| Authors | Nicolas Garcia Trillos, Moritz Gerlach, Matthias Hein, Dejan Slepcev |
| Abstract | We study the convergence of the graph Laplacian of a random geometric graph generated by an i.i.d. sample from a $m$-dimensional submanifold $M$ in $R^d$ as the sample size $n$ increases and the neighborhood size $h$ tends to zero. We show that eigenvalues and eigenvectors of the graph Laplacian converge with a rate of $O\Big(\big(\frac{\log n}{n}\big)^\frac{1}{2m}\Big)$ to the eigenvalues and eigenfunctions of the weighted Laplace-Beltrami operator of $M$. No information on the submanifold $M$ is needed in the construction of the graph or the “out-of-sample extension” of the eigenvectors. Of independent interest is a generalization of the rate of convergence of empirical measures on submanifolds in $R^d$ in infinity transportation distance. |
| Tasks | |
| Published | 2018-01-30 |
| URL | http://arxiv.org/abs/1801.10108v1 |
| http://arxiv.org/pdf/1801.10108v1.pdf | |
| PWC | https://paperswithcode.com/paper/error-estimates-for-spectral-convergence-of |
| Repo | |
| Framework | |
Exponential Convergence of the Deep Neural Network Approximation for Analytic Functions
| Title | Exponential Convergence of the Deep Neural Network Approximation for Analytic Functions |
| Authors | Weinan E, Qingcan Wang |
| Abstract | We prove that for analytic functions in low dimension, the convergence rate of the deep neural network approximation is exponential. |
| Tasks | |
| Published | 2018-07-01 |
| URL | http://arxiv.org/abs/1807.00297v1 |
| http://arxiv.org/pdf/1807.00297v1.pdf | |
| PWC | https://paperswithcode.com/paper/exponential-convergence-of-the-deep-neural |
| Repo | |
| Framework | |
