Paper Group ANR 337
Customer Segmentation of Wireless Trajectory Data. Error Analysis on Graph Laplacian Regularized Estimator. Sparse estimation via $\ell_q$ optimization method in high-dimensional linear regression. MuPNet: Multi-modal Predictive Coding Network for Place Recognition by Unsupervised Learning of Joint Visuo-Tactile Latent Representations. Leaky Tiling …
Customer Segmentation of Wireless Trajectory Data
| Title | Customer Segmentation of Wireless Trajectory Data |
| Authors | Matthew R Karlsen, Sotiris K. Moschoyiannis |
| Abstract | Wireless trajectory data consists of a number of (time, point) entries where each point is associated with a particular wireless device (WAP or BLE beacon) tied to a location identifier, such as a place name. A trajectory relates to a particular mobile device. Such data can be clustered semantically' to identify similar trajectories, where similarity relates to non-geographic characteristics such as the type of location visited. Here we present a new approach to semantic trajectory clustering for such data. The approach is applicable to interpreting data that does not contain geographical coordinates, and thus contributes to the current literature on semantic trajectory clustering. The literature does not appear to provide such an approach, instead focusing on trajectory data where latitude and longitude data is available. We apply the techniques developed above in the context of the Onward Journey Planner Application, with the motivation of providing on-line recommendations for onward journey options in a context-specific manner. The trajectories analysed indicate commute patterns on the London Underground. Points are only recorded for communication with WAP and BLE beacons within the rail network. This context presents additional challenge since the trajectories are truncated’, with no true origin and destination details. In the above context we find that there are a range of travel patterns in the data, without the existence of distinct clusters. Suggestions are made concerning how to approach the problem of provision of on-line recommendations with such a data set. Thoughts concerning the related problem of prediction of journey route and destination are also provided. |
| Tasks | |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.08874v1 |
| https://arxiv.org/pdf/1906.08874v1.pdf | |
| PWC | https://paperswithcode.com/paper/customer-segmentation-of-wireless-trajectory |
| Repo | |
| Framework | |
Error Analysis on Graph Laplacian Regularized Estimator
| Title | Error Analysis on Graph Laplacian Regularized Estimator |
| Authors | Kaige Yang, Xiaowen Dong, Laura Toni |
| Abstract | We provide a theoretical analysis of the representation learning problem aimed at learning the latent variables (design matrix) $\Theta$ of observations $Y$ with the knowledge of the coefficient matrix $X$. The design matrix is learned under the assumption that the latent variables $\Theta$ are smooth with respect to a (known) topological structure $\mathcal{G}$. To learn such latent variables, we study a graph Laplacian regularized estimator, which is the penalized least squares estimator with penalty term proportional to a Laplacian quadratic form. This type of estimators has recently received considerable attention due to its capability in incorporating underlying topological graph structure of variables into the learning process. While the estimation problem can be solved efficiently by state-of-the-art optimization techniques, its statistical consistency properties have been largely overlooked. In this work, we develop a non-asymptotic bound of estimation error under the classical statistical setting, where sample size is larger than the ambient dimension of the latent variables. This bound illustrates theoretically the impact of the alignment between the data and the graph structure as well as the graph spectrum on the estimation accuracy. It also provides theoretical evidence of the advantage, in terms of convergence rate, of the graph Laplacian regularized estimator over classical ones (that ignore the graph structure) in case of a smoothness prior. Finally, we provide empirical results of the estimation error to corroborate the theoretical analysis. |
| Tasks | Representation Learning |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.03720v1 |
| http://arxiv.org/pdf/1902.03720v1.pdf | |
| PWC | https://paperswithcode.com/paper/error-analysis-on-graph-laplacian-regularized |
| Repo | |
| Framework | |
Sparse estimation via $\ell_q$ optimization method in high-dimensional linear regression
| Title | Sparse estimation via $\ell_q$ optimization method in high-dimensional linear regression |
| Authors | Xin Li, Yaohua Hu, Chong Li, Xiaoqi Yang, Tianzi Jiang |
| Abstract | In this paper, we discuss the statistical properties of the $\ell_q$ optimization methods $(0<q\leq 1)$, including the $\ell_q$ minimization method and the $\ell_q$ regularization method, for estimating a sparse parameter from noisy observations in high-dimensional linear regression with either a deterministic or random design. For this purpose, we introduce a general $q$-restricted eigenvalue condition (REC) and provide its sufficient conditions in terms of several widely-used regularity conditions such as sparse eigenvalue condition, restricted isometry property, and mutual incoherence property. By virtue of the $q$-REC, we exhibit the stable recovery property of the $\ell_q$ optimization methods for either deterministic or random designs by showing that the $\ell_2$ recovery bound $O(\epsilon^2)$ for the $\ell_q$ minimization method and the oracle inequality and $\ell_2$ recovery bound $O(\lambda^{\frac{2}{2-q}}s)$ for the $\ell_q$ regularization method hold respectively with high probability. The results in this paper are nonasymptotic and only assume the weak $q$-REC. The preliminary numerical results verify the established statistical property and demonstrate the advantages of the $\ell_q$ regularization method over some existing sparse optimization methods. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.05073v1 |
| https://arxiv.org/pdf/1911.05073v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-estimation-via-ell_q-optimization |
| Repo | |
| Framework | |
MuPNet: Multi-modal Predictive Coding Network for Place Recognition by Unsupervised Learning of Joint Visuo-Tactile Latent Representations
| Title | MuPNet: Multi-modal Predictive Coding Network for Place Recognition by Unsupervised Learning of Joint Visuo-Tactile Latent Representations |
| Authors | Oliver Struckmeier, Kshitij Tiwari, Shirin Dora, Martin J. Pearson, Sander M. Bohte, Cyriel MA Pennartz, Ville Kyrki |
| Abstract | Extracting and binding salient information from different sensory modalities to determine common features in the environment is a significant challenge in robotics. Here we present MuPNet (Multi-modal Predictive Coding Network), a biologically plausible network architecture for extracting joint latent features from visuo-tactile sensory data gathered from a biomimetic mobile robot. In this study we evaluate MuPNet applied to place recognition as a simulated biomimetic robot platform explores visually aliased environments. The F1 scores demonstrate that its performance over prior hand-crafted sensory feature extraction techniques is equivalent under controlled conditions, with significant improvement when operating in novel environments. |
| Tasks | |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07201v1 |
| https://arxiv.org/pdf/1909.07201v1.pdf | |
| PWC | https://paperswithcode.com/paper/mupnet-multi-modal-predictive-coding-network |
| Repo | |
| Framework | |
Leaky Tiling Activations: A Simple Approach to Learning Sparse Representations Online
| Title | Leaky Tiling Activations: A Simple Approach to Learning Sparse Representations Online |
| Authors | Yangchen Pan, Kirby Banman, Martha White |
| Abstract | Interference is a known problem when learning in online settings, such as continual learning or reinforcement learning. Interference occurs when updates, to improve performance for some inputs, degrades performance for others. Recent work has shown that sparse representations—where only a small percentage of units are active—can significantly reduce interference. Those works, however, relied on relatively complex regularization or meta-learning approaches, that have only been used offline in a pre-training phase. In our approach, we design an activation function that naturally produces sparse representations, and so is much more amenable to online training. The idea relies on the simple approach of binning, but overcomes the two key limitations of binning: zero gradients for the flat regions almost everywhere, and lost precision—reduced discrimination—due to coarse aggregation. We introduce a Leaky Tiling Activation (LTA) that provides non-negligible gradients and produces overlap between bins that improves discrimination. We empirically investigate both value-based and policy gradient reinforcement learning algorithms that use neural networks with LTAs, in classic discrete-action control environments and Mujoco continuous-action environments. We show that, with LTAs, learning is faster, with more stable policies, without needing target networks. |
| Tasks | Continual Learning, Meta-Learning, Representation Learning |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08068v2 |
| https://arxiv.org/pdf/1911.08068v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-tile-coder-an-efficient-sparse |
| Repo | |
| Framework | |
A Model Counter’s Guide to Probabilistic Systems
| Title | A Model Counter’s Guide to Probabilistic Systems |
| Authors | Marcell Vazquez-Chanlatte, Markus N. Rabe, Sanjit A. Seshia |
| Abstract | In this paper, we systematize the modeling of probabilistic systems for the purpose of analyzing them with model counting techniques. Starting from unbiased coin flips, we show how to model biased coins, correlated coins, and distributions over finite sets. From there, we continue with modeling sequential systems, such as Markov chains, and revisit the relationship between weighted and unweighted model counting. Thereby, this work provides a conceptual framework for deriving #SAT encodings for probabilistic inference. |
| Tasks | |
| Published | 2019-03-22 |
| URL | http://arxiv.org/abs/1903.09354v1 |
| http://arxiv.org/pdf/1903.09354v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-model-counters-guide-to-probabilistic |
| Repo | |
| Framework | |
Privacy of Existence of Secrets: Introducing Steganographic DCOPs and Revisiting DCOP Frameworks
| Title | Privacy of Existence of Secrets: Introducing Steganographic DCOPs and Revisiting DCOP Frameworks |
| Authors | Viorel D. Silaghi, Marius C. Silaghi, René Mandiau |
| Abstract | Here we identify a type of privacy concern in Distributed Constraint Optimization (DCOPs) not previously addressed in literature, despite its importance and impact on the application field: the privacy of existence of secrets. Science only starts where metrics and assumptions are clearly defined. The area of Distributed Constraint Optimization has emerged at the intersection of the multi-agent system community and constraint programming. For the multi-agent community, the constraint optimization problems are an elegant way to express many of the problems occurring in trading and distributed robotics. For the theoretical constraint programming community the DCOPs are a natural extension of their main object of study, the constraint satisfaction problem. As such, the understanding of the DCOP framework has been refined with the needs of the two communities, but sometimes without spelling the new assumptions formally and therefore making it difficult to compare techniques. Here we give a direction to the efforts for structuring concepts in this area. |
| Tasks | |
| Published | 2019-02-15 |
| URL | http://arxiv.org/abs/1902.05943v1 |
| http://arxiv.org/pdf/1902.05943v1.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-of-existence-of-secrets-introducing |
| Repo | |
| Framework | |
Six Degree-of-Freedom Body-Fixed Hovering over Unmapped Asteroids via LIDAR Altimetry and Reinforcement Meta-Learning
| Title | Six Degree-of-Freedom Body-Fixed Hovering over Unmapped Asteroids via LIDAR Altimetry and Reinforcement Meta-Learning |
| Authors | Brian Gaudet, Richard Linares, Roberto Furfaro |
| Abstract | We optimize a six degrees of freedom hovering policy using reinforcement meta-learning. The policy maps flash LIDAR measurements directly to on/off spacecraft body-frame thrust commands, allowing hovering at a fixed position and attitude in the asteroid body-fixed reference frame. Importantly, the policy does not require position and velocity estimates, and can operate in environments with unknown dynamics, and without an asteroid shape model or navigation aids. Indeed, during optimization the agent is confronted with a new randomly generated asteroid for each episode, insuring that it does not learn an asteroid’s shape, texture, or environmental dynamics. This allows the deployed policy to generalize well to novel asteroid characteristics, which we demonstrate in our experiments. Moreover, our experiments show that the optimized policy adapts to actuator failure and sensor noise. Although the policy is optimized using randomly generated synthetic asteroids, it is tested on two shape models from actual asteroids: Bennu and Itokawa. We find that the policy generalizes well to these shape models. The hovering controller has the potential to simplify mission planning by allowing asteroid body-fixed hovering immediately upon the spacecraft’s arrival to an asteroid. This in turn simplifies shape model generation and allows resource mapping via remote sensing immediately upon arrival at the target asteroid. |
| Tasks | Meta-Learning |
| Published | 2019-11-16 |
| URL | https://arxiv.org/abs/1911.08553v2 |
| https://arxiv.org/pdf/1911.08553v2.pdf | |
| PWC | https://paperswithcode.com/paper/six-degree-of-freedom-hovering-using-lidar |
| Repo | |
| Framework | |
Resource-Efficient Computing in Wearable Systems
| Title | Resource-Efficient Computing in Wearable Systems |
| Authors | Mahdi Pedram, Mahsan Rofouei, Francesco Fraternali, Zhila Esna Ashari, Hassan Ghasemzadeh |
| Abstract | We propose two optimization techniques to minimize memory usage and computation while meeting system timing constraints for real-time classification in wearable systems. Our method derives a hierarchical classifier structure for Support Vector Machine (SVM) in order to reduce the amount of computations, based on the probability distribution of output classes occurrences. Also, we propose a memory optimization technique based on SVM parameters, which results in storing fewer support vectors and as a result requiring less memory. To demonstrate the efficiency of our proposed techniques, we performed an activity recognition experiment and were able to save up to 35% and 56% in memory storage when classifying 14 and 6 different activities, respectively. In addition, we demonstrated that there is a trade-off between accuracy of classification and memory savings, which can be controlled based on application requirements. |
| Tasks | Activity Recognition |
| Published | 2019-07-07 |
| URL | https://arxiv.org/abs/1907.03247v1 |
| https://arxiv.org/pdf/1907.03247v1.pdf | |
| PWC | https://paperswithcode.com/paper/resource-efficient-computing-in-wearable |
| Repo | |
| Framework | |
Automatic Handgun Detection in X-ray Images using Bag of Words Model with Selective Search
| Title | Automatic Handgun Detection in X-ray Images using Bag of Words Model with Selective Search |
| Authors | David Castro Piñol, Enrique Juan Marañón Reyes |
| Abstract | Baggage inspection systems using X-ray screening are crucial for security. Only 90% of threat objects are recognized from the X-ray system based in human inspection. Manual detection requires high concentration due to the images complexity and the challenges objects points of view. An algorithm based on Bag of Visual Word (BoVW) with Selective Search is proposed in this paper for handguns detection in single energy X-ray images from the public GDXray database. This approach is an adaptation of BoVW for X-ray baggage images context. In order to evaluate the proposed method the algorithm effectiveness recognition was tested on all bounding boxes returned by selective search algorithm in 200 images. The most relevant result is the precision and true positive rate (PPV = 80%, TPR= 92%). This approach achieves good performance for handgun recognition. In addition, it is the first time the Selective Search localization algorithm was tested in baggage X-ray images and showed possibilities with Bag of Visual Words. |
| Tasks | |
| Published | 2019-03-04 |
| URL | http://arxiv.org/abs/1903.01322v1 |
| http://arxiv.org/pdf/1903.01322v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-handgun-detection-in-x-ray-images |
| Repo | |
| Framework | |
Variance Reduced Advantage Estimation with $δ$ Hindsight Credit Assignment
| Title | Variance Reduced Advantage Estimation with $δ$ Hindsight Credit Assignment |
| Authors | Kenny Young |
| Abstract | Hindsight Credit Assignment (HCA) refers to a recently proposed family of methods for producing more efficient credit assignment in reinforcement learning. These methods work by explicitly estimating the probability that certain actions were taken in the past given present information. Prior work has studied the properties of such methods and demonstrated their behaviour empirically. We extend this work by introducing a particular HCA algorithm which has provably lower variance than the conventional Monte-Carlo estimator when the necessary functions can be estimated exactly. This result provides a strong theoretical basis for how HCA could be broadly useful. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08362v3 |
| https://arxiv.org/pdf/1911.08362v3.pdf | |
| PWC | https://paperswithcode.com/paper/variance-reduced-advantage-estimation-with |
| Repo | |
| Framework | |
Extending the step-size restriction for gradient descent to avoid strict saddle points
| Title | Extending the step-size restriction for gradient descent to avoid strict saddle points |
| Authors | Hayden Schaeffer, Scott G. McCalla |
| Abstract | We provide larger step-size restrictions for which gradient descent based algorithms (almost surely) avoid strict saddle points. In particular, consider a twice differentiable (non-convex) objective function whose gradient has Lipschitz constant L and whose Hessian is well-behaved. We prove that the probability of initial conditions for gradient descent with step-size up to 2/L converging to a strict saddle point, given one uniformly random initialization, is zero. This extends previous results up to the sharp limit imposed by the convex case. In addition, the arguments hold in the case when a learning rate schedule is given, with either a continuous decaying rate or a piece-wise constant schedule. |
| Tasks | |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1908.01753v1 |
| https://arxiv.org/pdf/1908.01753v1.pdf | |
| PWC | https://paperswithcode.com/paper/extending-the-step-size-restriction-for |
| Repo | |
| Framework | |
A self-organizing fuzzy neural network for sequence learning
| Title | A self-organizing fuzzy neural network for sequence learning |
| Authors | Armin Salimi-Badr, Mohammad Mehdi Ebadzadeh |
| Abstract | In this paper, a new self-organizing fuzzy neural network model is presented which is able to learn and reproduce different sequences accurately. Sequence learning is important in performing skillful tasks, such as writing and playing piano. The structure of the proposed network is composed of two parts: 1-sequence identifier which computes a novel sequence identity value based on initial samples of a sequence, and detects the sequence identity based on proper fuzzy rules, and 2-sequence locator, which locates the input sample in the sequence. Therefore, by integrating outputs of these two parts in fuzzy rules, the network is able to produce the proper output based on current state of the sequence. To learn the proposed structure, a gradual learning procedure is proposed. First, learning is performed by adding new fuzzy rules, based on coverage measure, using available correct data. Next, the initialized parameters are fine-tuned, by gradient descent algorithm, based on fed back approximated network output as the next input. The proposed method has a dynamic structure which is able to learn new sequences online. The proposed method is used to learn and reproduce different sequences simultaneously which is the novelty of this method. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://arxiv.org/abs/1908.00617v1 |
| https://arxiv.org/pdf/1908.00617v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-self-organizing-fuzzy-neural-network-for |
| Repo | |
| Framework | |
Detecting abnormalities in resting-state dynamics: An unsupervised learning approach
| Title | Detecting abnormalities in resting-state dynamics: An unsupervised learning approach |
| Authors | Meenakshi Khosla, Keith Jamison, Amy Kuceyeski, Mert R. Sabuncu |
| Abstract | Resting-state functional MRI (rs-fMRI) is a rich imaging modality that captures spontaneous brain activity patterns, revealing clues about the connectomic organization of the human brain. While many rs-fMRI studies have focused on static measures of functional connectivity, there has been a recent surge in examining the temporal patterns in these data. In this paper, we explore two strategies for capturing the normal variability in resting-state activity across a healthy population: (a) an autoencoder approach on the rs-fMRI sequence, and (b) a next frame prediction strategy. We show that both approaches can learn useful representations of rs-fMRI data and demonstrate their novel application for abnormality detection in the context of discriminating autism patients from healthy controls. |
| Tasks | Anomaly Detection |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06168v1 |
| https://arxiv.org/pdf/1908.06168v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-abnormalities-in-resting-state |
| Repo | |
| Framework | |
Pose-Invariant Object Recognition for Event-Based Vision with Slow-ELM
| Title | Pose-Invariant Object Recognition for Event-Based Vision with Slow-ELM |
| Authors | Rohan Ghosh, Siyi Tang, Mahdi Rasouli, Nitish Thakor, Sunil Kukreja |
| Abstract | Neuromorphic image sensors produce activity-driven spiking output at every pixel. These low-power consuming imagers which encode visual change information in the form of spikes help reduce computational overhead and realize complex real-time systems; object recognition and pose-estimation to name a few. However, there exists a lack of algorithms in event-based vision aimed towards capturing invariance to transformations. In this work, we propose a methodology for recognizing objects invariant to their pose with the Dynamic Vision Sensor (DVS). A novel slow-ELM architecture is proposed which combines the effectiveness of Extreme Learning Machines and Slow Feature Analysis. The system, tested on an Intel Core i5-4590 CPU, can perform 10,000 classifications per second and achieves 1% classification error for 8 objects with views accumulated over 90 degrees of 2D pose. |
| Tasks | Event-based vision, Object Recognition, Pose Estimation |
| Published | 2019-03-19 |
| URL | http://arxiv.org/abs/1903.07873v1 |
| http://arxiv.org/pdf/1903.07873v1.pdf | |
| PWC | https://paperswithcode.com/paper/pose-invariant-object-recognition-for-event |
| Repo | |
| Framework | |
