Paper Group ANR 995
Superresolution method for data deconvolution by superposition of point sources. Personalization of Health Interventions using Cluster-Based Reinforcement Learning. Multi-objective Evolutionary Federated Learning. Virtual Wave Optics for Non-Line-of-Sight Imaging. A Machine Learning Approach to Quantitative Prosopography. Learn to See by Events: Co …
Superresolution method for data deconvolution by superposition of point sources
| Title | Superresolution method for data deconvolution by superposition of point sources |
| Authors | Sandra Martínez, Oscar E. Martínez |
| Abstract | In this work we present a new algorithm for data deconvolution that allows the retrieval of the target function with super-resolution with a simple approach that after a precis e measurement of the instrument response function (IRF), the measured data are fit by a superposition of point sources (SUPPOSe) of equal intensity. In this manner only the positions of the sources need to be determined by an algorithm that minimizes the norm of the difference between the measured data and the convolution of the superposed point sources with the IRF. An upper bound for the uncertainty in the position of the sources was derived and two very different experimental situations were used for the test (an optical spectrum and fluorescent microscopy images) showing excellent reconstructions and agreement with the predicted uncertainties, achieving {\lambda}/10 resolution for the microscope and a fivefold improvement in the spectral resolution for the spectrometer. The method also provides a way to determine the optimum number of sources to be used for the fit. |
| Tasks | Super-Resolution |
| Published | 2018-05-08 |
| URL | http://arxiv.org/abs/1805.03170v2 |
| http://arxiv.org/pdf/1805.03170v2.pdf | |
| PWC | https://paperswithcode.com/paper/superresolution-method-for-data-deconvolution |
| Repo | |
| Framework | |
Personalization of Health Interventions using Cluster-Based Reinforcement Learning
| Title | Personalization of Health Interventions using Cluster-Based Reinforcement Learning |
| Authors | Ali el Hassouni, Mark Hoogendoorn, Martijn van Otterlo, Eduardo Barbaro |
| Abstract | Research has shown that personalization of health interventions can contribute to an improved effectiveness. Reinforcement learning algorithms can be used to perform such tailoring using data that is collected about users. Learning is however very fragile for health interventions as only limited time is available to learn from the user before disengagement takes place, or before the opportunity to intervene passes. In this paper, we present a cluster-based reinforcement learning approach which learns across groups of users. Such an approach can speed up the learning process while still giving a level of personalization. The clustering algorithm uses a distance metric over traces of states and rewards. We apply both online and batch learning to learn policies over the clusters and introduce a publicly available simulator which we have developed to evaluate the approach. The results show batch learning clearly outperforms online learning. Furthermore, clustering can be beneficial provided that a proper clustering is found. |
| Tasks | |
| Published | 2018-04-10 |
| URL | http://arxiv.org/abs/1804.03592v1 |
| http://arxiv.org/pdf/1804.03592v1.pdf | |
| PWC | https://paperswithcode.com/paper/personalization-of-health-interventions-using |
| Repo | |
| Framework | |
Multi-objective Evolutionary Federated Learning
| Title | Multi-objective Evolutionary Federated Learning |
| Authors | Hangyu Zhu, Yaochu Jin |
| Abstract | Federated learning is an emerging technique used to prevent the leakage of private information. Unlike centralized learning that needs to collect data from users and store them collectively on a cloud server, federated learning makes it possible to learn a global model while the data are distributed on the users’ devices. However, compared with the traditional centralized approach, the federated setting consumes considerable communication resources of the clients, which is indispensable for updating global models and prevents this technique from being widely used. In this paper, we aim to optimize the structure of the neural network models in federated learning using a multi-objective evolutionary algorithm to simultaneously minimize the communication costs and the global model test errors. A scalable method for encoding network connectivity is adapted to federated learning to enhance the efficiency in evolving deep neural networks. Experimental results on both multilayer perceptrons and convolutional neural networks indicate that the proposed optimization method is able to find optimized neural network models that can not only significantly reduce communication costs but also improve the learning performance of federated learning compared with the standard fully connected neural networks. |
| Tasks | |
| Published | 2018-12-18 |
| URL | https://arxiv.org/abs/1812.07478v2 |
| https://arxiv.org/pdf/1812.07478v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-objective-evolutionary-federated |
| Repo | |
| Framework | |
Virtual Wave Optics for Non-Line-of-Sight Imaging
| Title | Virtual Wave Optics for Non-Line-of-Sight Imaging |
| Authors | Xiaochun Liu, Ibón Guillén, Marco La Manna, Ji Hyun Nam, Syed Azer Reza, Toan Huu Le, Diego Gutierrez, Adrian Jarabo, Andreas Velten |
| Abstract | Non-Line-of-Sight (NLOS) imaging allows to observe objects partially or fully occluded from direct view, by analyzing indirect diffuse reflections off a secondary, relay surface. Despite its many potential applications, existing methods lack practical usability due to several shared limitations, including the assumption of single scattering only, lack of occlusions, and Lambertian reflectance. We lift these limitations by transforming the NLOS problem into a virtual Line-Of-Sight (LOS) one. Since imaging information cannot be recovered from the irradiance arriving at the relay surface, we introduce the concept of the phasor field, a mathematical construct representing a fast variation in irradiance. We show that NLOS light transport can be modeled as the propagation of a phasor field wave, which can be solved accurately by the Rayleigh-Sommerfeld diffraction integral. We demonstrate for the first time NLOS reconstruction of complex scenes with strong multiply scattered and ambient light, arbitrary materials, large depth range, and occlusions. Our method handles these challenging cases without explicitly developing a light transport model. By leveraging existing fast algorithms, we outperform existing methods in terms of execution speed, computational complexity, and memory use. We believe that our approach will help unlock the potential of NLOS imaging, and the development of novel applications not restricted to lab conditions. For example, we demonstrate both refocusing and transient NLOS videos of real-world, complex scenes with large depth. |
| Tasks | |
| Published | 2018-10-17 |
| URL | https://arxiv.org/abs/1810.07535v2 |
| https://arxiv.org/pdf/1810.07535v2.pdf | |
| PWC | https://paperswithcode.com/paper/virtual-wave-optics-for-non-line-of-sight |
| Repo | |
| Framework | |
A Machine Learning Approach to Quantitative Prosopography
| Title | A Machine Learning Approach to Quantitative Prosopography |
| Authors | Aayushee Gupta, Haimonti Dutta, Srikanta Bedathur, Lipika Dey |
| Abstract | Prosopography is an investigation of the common characteristics of a group of people in history, by a collective study of their lives. It involves a study of biographies to solve historical problems. If such biographies are unavailable, surviving documents and secondary biographical data are used. Quantitative prosopography involves analysis of information from a wide variety of sources about “ordinary people”. In this paper, we present a machine learning framework for automatically designing a people gazetteer which forms the basis of quantitative prosopographical research. The gazetteer is learnt from the noisy text of newspapers using a Named Entity Recognizer (NER). It is capable of identifying influential people from it by making use of a custom designed Influential Person Index (IPI). Our corpus comprises of 14020 articles from a local newspaper, “The Sun”, published from New York in 1896. Some influential people identified by our algorithm include Captain Donald Hankey (an English soldier), Dame Nellie Melba (an Australian operatic soprano), Hugh Allan (a Canadian shipping magnate) and Sir Hugh John McDonald (the first Prime Minister of Canada). |
| Tasks | |
| Published | 2018-01-30 |
| URL | http://arxiv.org/abs/1801.10080v1 |
| http://arxiv.org/pdf/1801.10080v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-approach-to-quantitative |
| Repo | |
| Framework | |
Learn to See by Events: Color Frame Synthesis from Event and RGB Cameras
| Title | Learn to See by Events: Color Frame Synthesis from Event and RGB Cameras |
| Authors | Stefano Pini, Guido Borghi, Roberto Vezzani |
| Abstract | Event cameras are biologically-inspired sensors that gather the temporal evolution of the scene. They capture pixel-wise brightness variations and output a corresponding stream of asynchronous events. Despite having multiple advantages with respect to traditional cameras, their use is partially prevented by the limited applicability of traditional data processing and vision algorithms. To this aim, we present a framework which exploits the output stream of event cameras to synthesize RGB frames, relying on an initial or a periodic set of color key-frames and the sequence of intermediate events. Differently from existing work, we propose a deep learning-based frame synthesis method, consisting of an adversarial architecture combined with a recurrent module. Qualitative results and quantitative per-pixel, perceptual, and semantic evaluation on four public datasets confirm the quality of the synthesized images. |
| Tasks | |
| Published | 2018-12-05 |
| URL | https://arxiv.org/abs/1812.02041v2 |
| https://arxiv.org/pdf/1812.02041v2.pdf | |
| PWC | https://paperswithcode.com/paper/learn-to-see-by-events-rgb-frame-synthesis |
| Repo | |
| Framework | |
On Learning Graphs with Edge-Detecting Queries
| Title | On Learning Graphs with Edge-Detecting Queries |
| Authors | Hasan Abasi, Nader H. Bshouty |
| Abstract | We consider the problem of learning a general graph $G=(V,E)$ using edge-detecting queries, where the number of vertices $V=n$ is given to the learner. The information theoretic lower bound gives $m\log n$ for the number of queries, where $m=E$ is the number of edges. In case the number of edges $m$ is also given to the learner, Angluin-Chen’s Las Vegas algorithm \cite{AC08} runs in $4$ rounds and detects the edges in $O(m\log n)$ queries. In the other harder case where the number of edges $m$ is unknown, their algorithm runs in $5$ rounds and asks $O(m\log n+\sqrt{m}\log^2 n)$ queries. There have been two open problems: \emph{(i)} can the number of queries be reduced to $O(m\log n)$ in the second case, and, \emph{(ii)} can the number of rounds be reduced without substantially increasing the number of queries (in both cases). For the first open problem (when $m$ is unknown) we give two algorithms. The first is an $O(1)$-round Las Vegas algorithm that asks $m\log n+\sqrt{m}(\log^{[k]}n)\log n$ queries for any constant $k$ where $\log^{[k]}n=\log \stackrel{k}{\cdots} \log n$. The second is an $O(\log^*n)$-round Las Vegas algorithm that asks $O(m\log n)$ queries. This solves the first open problem for any practical $n$, for example, $n<2^{65536}$. We also show that no deterministic algorithm can solve this problem in a constant number of rounds. To solve the second problem we study the case when $m$ is known. We first show that any non-adaptive Monte Carlo algorithm (one-round) must ask at least $\Omega(m^2\log n)$ queries, and any two-round Las Vegas algorithm must ask at least $m^{4/3-o(1)}\log n$ queries on average. We then give two two-round Monte Carlo algorithms, the first asks $O(m^{4/3}\log n)$ queries for any $n$ and $m$, and the second asks $O(m\log n)$ queries when $n>2^m$. Finally, we give a $3$-round Monte Carlo algorithm that asks $O(m\log n)$ queries for any $n$ and $m$. |
| Tasks | |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10639v1 |
| http://arxiv.org/pdf/1803.10639v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-learning-graphs-with-edge-detecting |
| Repo | |
| Framework | |
A new ultrasound despeckling method through adaptive threshold
| Title | A new ultrasound despeckling method through adaptive threshold |
| Authors | Hamid Reza Shahdoosti |
| Abstract | An efficient despeckling method using a quantum-inspired adaptive threshold function is presented for reducing noise of ultrasound images. In the first step, the ultrasound image is decorrelated by an spectrum equalization procedure due to the fact that speckle noise is neither Gaussian nor white. In fact, a linear filter is exploited to flatten the power spectral density (PSD) of the ultrasound image. Then, the proposed method shrinks complex wavelet coefficients based on the quantum-inspired adaptive threshold function. The proposed approach has been used to denoise both real and simulated data sets and compare with other widely adopted techniques. Experimental results demonstrate that the proposed method has a competitive performance to remove speckle noise and can preserve details and textures of medical ultrasound images. |
| Tasks | |
| Published | 2018-07-05 |
| URL | http://arxiv.org/abs/1807.03160v1 |
| http://arxiv.org/pdf/1807.03160v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-ultrasound-despeckling-method-through |
| Repo | |
| Framework | |
Manuscripts in Time and Space: Experiments in Scriptometrics on an Old French Corpus
| Title | Manuscripts in Time and Space: Experiments in Scriptometrics on an Old French Corpus |
| Authors | Jean-Baptiste Camps |
| Abstract | Witnesses of medieval literary texts, preserved in manuscript, are layered objects , being almost exclusively copies of copies. This results in multiple and hard to distinguish linguistic strata – the author’s scripta interacting with the scriptae of the various scribes – in a context where literary written language is already a dialectal hybrid. Moreover, no single linguistic phenomenon allows to distinguish between different scriptae, and only the combination of multiple characteristics is likely to be significant [9] – but which ones? The most common approach is to search for these features in a set of previously selected texts, that are supposed to be representative of a given scripta. This can induce a circularity, in which texts are used to select features that in turn characterise them as belonging to a linguistic area. To counter this issue, this paper offers an unsupervised and corpus-based approach, in which clustering methods are applied to an Old French corpus to identify main divisions and groups. Ultimately, scriptometric profiles are built for each of them. |
| Tasks | |
| Published | 2018-01-30 |
| URL | http://arxiv.org/abs/1802.01429v1 |
| http://arxiv.org/pdf/1802.01429v1.pdf | |
| PWC | https://paperswithcode.com/paper/manuscripts-in-time-and-space-experiments-in |
| Repo | |
| Framework | |
JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
| Title | JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics |
| Authors | Anders Andreassen, Ilya Feige, Christopher Frye, Matthew D. Schwartz |
| Abstract | In applications of machine learning to particle physics, a persistent challenge is how to go beyond discrimination to learn about the underlying physics. To this end, a powerful tool would be a framework for unsupervised learning, where the machine learns the intricate high-dimensional contours of the data upon which it is trained, without reference to pre-established labels. In order to approach such a complex task, an unsupervised network must be structured intelligently, based on a qualitative understanding of the data. In this paper, we scaffold the neural network’s architecture around a leading-order model of the physics underlying the data. In addition to making unsupervised learning tractable, this design actually alleviates existing tensions between performance and interpretability. We call the framework JUNIPR: “Jets from UNsupervised Interpretable PRobabilistic models”. In this approach, the set of particle momenta composing a jet are clustered into a binary tree that the neural network examines sequentially. Training is unsupervised and unrestricted: the network could decide that the data bears little correspondence to the chosen tree structure. However, when there is a correspondence, the network’s output along the tree has a direct physical interpretation. JUNIPR models can perform discrimination tasks, through the statistically optimal likelihood-ratio test, and they permit visualizations of discrimination power at each branching in a jet’s tree. Additionally, JUNIPR models provide a probability distribution from which events can be drawn, providing a data-driven Monte Carlo generator. As a third application, JUNIPR models can reweight events from one (e.g. simulated) data set to agree with distributions from another (e.g. experimental) data set. |
| Tasks | |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09720v1 |
| http://arxiv.org/pdf/1804.09720v1.pdf | |
| PWC | https://paperswithcode.com/paper/junipr-a-framework-for-unsupervised-machine |
| Repo | |
| Framework | |
Prognostics Estimations with Dynamic States
| Title | Prognostics Estimations with Dynamic States |
| Authors | Rong-Jing Bao, Hai-Jun Rong, Zhi-Xin Yang, Badong Chen |
| Abstract | The health state assessment and remaining useful life (RUL) estimation play very important roles in prognostics and health management (PHM), owing to their abilities to reduce the maintenance and improve the safety of machines or equipment. However, they generally suffer from this problem of lacking prior knowledge to pre-define the exact failure thresholds for a machinery operating in a dynamic environment with a high level of uncertainty. In this case, dynamic thresholds depicted by the discrete states is a very attractive way to estimate the RUL of a dynamic machinery. Currently, there are only very few works considering the dynamic thresholds, and these studies adopted different algorithms to determine the discrete states and predict the continuous states separately, which largely increases the complexity of the learning process. In this paper, we propose a novel prognostics approach for RUL estimation of aero-engines with self-joint prediction of continuous and discrete states, wherein the prediction of continuous and discrete states are conducted simultaneously and dynamically within one learning framework. |
| Tasks | |
| Published | 2018-07-16 |
| URL | http://arxiv.org/abs/1807.06093v3 |
| http://arxiv.org/pdf/1807.06093v3.pdf | |
| PWC | https://paperswithcode.com/paper/prognostics-estimations-with-dynamic-states |
| Repo | |
| Framework | |
Exploiting Inherent Error-Resiliency of Neuromorphic Computing to achieve Extreme Energy-Efficiency through Mixed-Signal Neurons
| Title | Exploiting Inherent Error-Resiliency of Neuromorphic Computing to achieve Extreme Energy-Efficiency through Mixed-Signal Neurons |
| Authors | Baibhab Chatterjee, Priyadarshini Panda, Shovan Maity, Ayan Biswas, Kaushik Roy, Shreyas Sen |
| Abstract | Neuromorphic computing, inspired by the brain, promises extreme efficiency for certain classes of learning tasks, such as classification and pattern recognition. The performance and power consumption of neuromorphic computing depends heavily on the choice of the neuron architecture. Digital neurons (Dig-N) are conventionally known to be accurate and efficient at high speed, while suffering from high leakage currents from a large number of transistors in a large design. On the other hand, analog/mixed-signal neurons are prone to noise, variability and mismatch, but can lead to extremely low-power designs. In this work, we will analyze, compare and contrast existing neuron architectures with a proposed mixed-signal neuron (MS-N) in terms of performance, power and noise, thereby demonstrating the applicability of the proposed mixed-signal neuron for achieving extreme energy-efficiency in neuromorphic computing. The proposed MS-N is implemented in 65 nm CMOS technology and exhibits > 100X better energy-efficiency across all frequencies over two traditional digital neurons synthesized in the same technology node. We also demonstrate that the inherent error-resiliency of a fully connected or even convolutional neural network (CNN) can handle the noise as well as the manufacturing non-idealities of the MS-N up to certain degrees. Notably, a system-level implementation on MNIST datasets exhibits a worst-case increase in classification error by 2.1% when the integrated noise power in the bandwidth is ~ 0.1 uV2, along with +-3{\sigma} amount of variation and mismatch introduced in the transistor parameters for the proposed neuron with 8-bit precision. |
| Tasks | |
| Published | 2018-06-13 |
| URL | http://arxiv.org/abs/1806.05141v1 |
| http://arxiv.org/pdf/1806.05141v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-inherent-error-resiliency-of |
| Repo | |
| Framework | |
Conducting Credit Assignment by Aligning Local Representations
| Title | Conducting Credit Assignment by Aligning Local Representations |
| Authors | Alexander G. Ororbia, Ankur Mali, Daniel Kifer, C. Lee Giles |
| Abstract | Using back-propagation and its variants to train deep networks is often problematic for new users. Issues such as exploding gradients, vanishing gradients, and high sensitivity to weight initialization strategies often make networks difficult to train, especially when users are experimenting with new architectures. Here, we present Local Representation Alignment (LRA), a training procedure that is much less sensitive to bad initializations, does not require modifications to the network architecture, and can be adapted to networks with highly nonlinear and discrete-valued activation functions. Furthermore, we show that one variation of LRA can start with a null initialization of network weights and still successfully train networks with a wide variety of nonlinearities, including tanh, ReLU-6, softplus, signum and others that may draw their inspiration from biology. A comprehensive set of experiments on MNIST and the much harder Fashion MNIST data sets show that LRA can be used to train networks robustly and effectively, succeeding even when back-propagation fails and outperforming other alternative learning algorithms, such as target propagation and feedback alignment. |
| Tasks | |
| Published | 2018-03-05 |
| URL | http://arxiv.org/abs/1803.01834v2 |
| http://arxiv.org/pdf/1803.01834v2.pdf | |
| PWC | https://paperswithcode.com/paper/conducting-credit-assignment-by-aligning |
| Repo | |
| Framework | |
A universal framework for learning the elliptical mixture model
| Title | A universal framework for learning the elliptical mixture model |
| Authors | Shengxi Li, Zeyang Yu, Danilo Mandic |
| Abstract | Mixture modelling using elliptical distributions promises enhanced robustness, flexibility and stability over the widely employed Gaussian mixture model (GMM). However, existing studies based on the elliptical mixture model (EMM) are restricted to several specific types of elliptical probability density functions, which are not supported by general solutions or systematic analysis frameworks; this significantly limits the rigour and the power of EMMs in applications. To this end, we propose a novel general framework for estimating and analysing the EMMs, achieved through Riemannian manifold optimisation. First, we investigate the relationships between Riemannian manifolds and elliptical distributions, and the so established connection between the original manifold and a reformulated one indicates a mismatch between those manifolds, the major cause of failure of the existing optimisation for solving general EMMs. We next propose a universal solver which is based on the optimisation of a re-designed cost and prove the existence of the same optimum as in the original problem; this is achieved in a simple, fast and stable way. We further calculate the influence functions of the EMM as theoretical bounds to quantify robustness to outliers. Comprehensive numerical results demonstrate the ability of the proposed framework to accommodate EMMs with different properties of individual functions in a stable way and with fast convergence speed. Finally, the enhanced robustness and flexibility of the proposed framework over the standard GMM are demonstrated both analytically and through comprehensive simulations. |
| Tasks | |
| Published | 2018-05-21 |
| URL | https://arxiv.org/abs/1805.08045v4 |
| https://arxiv.org/pdf/1805.08045v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-universal-framework-for-learning-based-on |
| Repo | |
| Framework | |
Deep Learning for Signal Authentication and Security in Massive Internet of Things Systems
| Title | Deep Learning for Signal Authentication and Security in Massive Internet of Things Systems |
| Authors | Aidin Ferdowsi, Walid Saad |
| Abstract | Secure signal authentication is arguably one of the most challenging problems in the Internet of Things (IoT) environment, due to the large-scale nature of the system and its susceptibility to man-in-the-middle and eavesdropping attacks. In this paper, a novel deep learning method is proposed for dynamic authentication of IoT signals to detect cyber attacks. The proposed learning framework, based on a long short-term memory (LSTM) structure, enables the IoT devices (IoTDs) to extract a set of stochastic features from their generated signal and dynamically watermark these features into the signal. This method enables the cloud, which collects signals from the IoT devices, to effectively authenticate the reliability of the signals. Moreover, in massive IoT scenarios, since the cloud cannot authenticate all the IoTDs simultaneously due to computational limitations, a game-theoretic framework is proposed to improve the cloud’s decision making process by predicting vulnerable IoTDs. The mixed-strategy Nash equilibrium (MSNE) for this game is derived and the uniqueness of the expected utility at the equilibrium is proven. In the massive IoT system, due to a large set of available actions for the cloud, it is shown that analytically deriving the MSNE is challenging and, thus, a learning algorithm proposed that converges to the MSNE. Moreover, in order to cope with the incomplete information case in which the cloud cannot access the state of the unauthenticated IoTDs, a deep reinforcement learning algorithm is proposed to dynamically predict the state of unauthenticated IoTDs and allow the cloud to decide on which IoTDs to authenticate. Simulation results show that, with an attack detection delay of under 1 second the messages can be transmitted from IoT devices with an almost 100% reliability. |
| Tasks | Decision Making |
| Published | 2018-03-01 |
| URL | https://arxiv.org/abs/1803.00916v2 |
| https://arxiv.org/pdf/1803.00916v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-signal-authentication-and |
| Repo | |
| Framework | |
