July 27, 2019

2960 words 14 mins read

Paper Group ANR 649

Calibrating chemical multisensory devices for real world applications: An in-depth comparison of quantitative Machine Learning approaches. Expert-Driven Genetic Algorithms for Simulating Evaluation Functions. Batched High-dimensional Bayesian Optimization via Structural Kernel Learning. Context-aware stacked convolutional neural networks for classi …

Calibrating chemical multisensory devices for real world applications: An in-depth comparison of quantitative Machine Learning approaches


Title	Calibrating chemical multisensory devices for real world applications: An in-depth comparison of quantitative Machine Learning approaches
Authors	S. De Vito, E. Esposito, M. Salvato, O. Popoola, F. Formisano, R. Jones, G. Di Francia
Abstract	Chemical multisensor devices need calibration algorithms to estimate gas concentrations. Their possible adoption as indicative air quality measurements devices poses new challenges due to the need to operate in continuous monitoring modes in uncontrolled environments. Several issues, including slow dynamics, continue to affect their real world performances. At the same time, the need for estimating pollutant concentrations on board the devices, espe- cially for wearables and IoT deployments, is becoming highly desirable. In this framework, several calibration approaches have been proposed and tested on a variety of proprietary devices and datasets; still, no thorough comparison is available to researchers. This work attempts a benchmarking of the most promising calibration algorithms according to recent literature with a focus on machine learning approaches. We test the techniques against absolute and dynamic performances, generalization capabilities and computational/storage needs using three different datasets sharing continuous monitoring operation methodology. Our results can guide researchers and engineers in the choice of optimal strategy. They show that non-linear multivariate techniques yield reproducible results, outperforming lin- ear approaches. Specifically, the Support Vector Regression method consistently shows good performances in all the considered scenarios. We highlight the enhanced suitability of shallow neural networks in a trade-off between performance and computational/storage needs. We confirm, on a much wider basis, the advantages of dynamic approaches with respect to static ones that only rely on instantaneous sensor array response. The latter have been shown to be best choice whenever prompt and precise response is needed.
Tasks	Calibration
Published	2017-08-30
URL	http://arxiv.org/abs/1708.09175v1
PDF	http://arxiv.org/pdf/1708.09175v1.pdf
PWC	https://paperswithcode.com/paper/calibrating-chemical-multisensory-devices-for
Repo
Framework

Expert-Driven Genetic Algorithms for Simulating Evaluation Functions


Title	Expert-Driven Genetic Algorithms for Simulating Evaluation Functions
Authors	Eli David, Moshe Koppel, Nathan S. Netanyahu
Abstract	In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function’s parameters for computer chess. Our results show that using an appropriate expert (or mentor), we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Computer Chess Champion. This performance gain is achieved by evolving a program that mimics the behavior of a superior expert. The resulting evaluation function of the evolved program consists of a much smaller number of parameters than the expert’s. The extended experimental results provided in this paper include a report of our successful participation in the 2008 World Computer Chess Championship. In principle, our expert-driven approach could be used in a wide range of problems for which appropriate experts are available.
Tasks
Published	2017-11-18
URL	http://arxiv.org/abs/1711.06841v1
PDF	http://arxiv.org/pdf/1711.06841v1.pdf
PWC	https://paperswithcode.com/paper/expert-driven-genetic-algorithms-for
Repo
Framework

Batched High-dimensional Bayesian Optimization via Structural Kernel Learning


Title	Batched High-dimensional Bayesian Optimization via Structural Kernel Learning
Authors	Zi Wang, Chengtao Li, Stefanie Jegelka, Pushmeet Kohli
Abstract	Optimization of high-dimensional black-box functions is an extremely challenging problem. While Bayesian optimization has emerged as a popular approach for optimizing black-box functions, its applicability has been limited to low-dimensional problems due to its computational and statistical challenges arising from high-dimensional settings. In this paper, we propose to tackle these challenges by (1) assuming a latent additive structure in the function and inferring it properly for more efficient and effective BO, and (2) performing multiple evaluations in parallel to reduce the number of iterations required by the method. Our novel approach learns the latent structure with Gibbs sampling and constructs batched queries using determinantal point processes. Experimental validations on both synthetic and real-world functions demonstrate that the proposed method outperforms the existing state-of-the-art approaches.
Tasks	Point Processes
Published	2017-03-06
URL	http://arxiv.org/abs/1703.01973v2
PDF	http://arxiv.org/pdf/1703.01973v2.pdf
PWC	https://paperswithcode.com/paper/batched-high-dimensional-bayesian
Repo
Framework

Context-aware stacked convolutional neural networks for classification of breast carcinomas in whole-slide histopathology images


Title	Context-aware stacked convolutional neural networks for classification of breast carcinomas in whole-slide histopathology images
Authors	Babak Ehteshami Bejnordi, Guido Zuidhof, Maschenka Balkenhol, Meyke Hermsen, Peter Bult, Bram van Ginneken, Nico Karssemeijer, Geert Litjens, Jeroen van der Laak
Abstract	Automated classification of histopathological whole-slide images (WSI) of breast tissue requires analysis at very high resolutions with a large contextual area. In this paper, we present context-aware stacked convolutional neural networks (CNN) for classification of breast WSIs into normal/benign, ductal carcinoma in situ (DCIS), and invasive ductal carcinoma (IDC). We first train a CNN using high pixel resolution patches to capture cellular level information. The feature responses generated by this model are then fed as input to a second CNN, stacked on top of the first. Training of this stacked architecture with large input patches enables learning of fine-grained (cellular) details and global interdependence of tissue structures. Our system is trained and evaluated on a dataset containing 221 WSIs of H&E stained breast tissue specimens. The system achieves an AUC of 0.962 for the binary classification of non-malignant and malignant slides and obtains a three class accuracy of 81.3% for classification of WSIs into normal/benign, DCIS, and IDC, demonstrating its potentials for routine diagnostics.
Tasks
Published	2017-05-10
URL	http://arxiv.org/abs/1705.03678v1
PDF	http://arxiv.org/pdf/1705.03678v1.pdf
PWC	https://paperswithcode.com/paper/context-aware-stacked-convolutional-neural
Repo
Framework

Saliency Preservation in Low-Resolution Grayscale Images


Title	Saliency Preservation in Low-Resolution Grayscale Images
Authors	Shivanthan A. C. Yohanandan, Adrian G. Dyer, Dacheng Tao, Andy Song
Abstract	Visual salience detection originated over 500 million years ago and is one of nature’s most efficient mechanisms. In contrast, many state-of-the-art computational saliency models are complex and inefficient. Most saliency models process high-resolution color (HC) images; however, insights into the evolutionary origins of visual salience detection suggest that achromatic low-resolution vision is essential to its speed and efficiency. Previous studies showed that low-resolution color and high-resolution grayscale images preserve saliency information. However, to our knowledge, no one has investigated whether saliency is preserved in low-resolution grayscale (LG) images. In this study, we explain the biological and computational motivation for LG, and show, through a range of human eye-tracking and computational modeling experiments, that saliency information is preserved in LG images. Moreover, we show that using LG images leads to significant speedups in model training and detection times and conclude by proposing LG images for fast and efficient salience detection.
Tasks	Eye Tracking
Published	2017-12-06
URL	http://arxiv.org/abs/1712.02048v3
PDF	http://arxiv.org/pdf/1712.02048v3.pdf
PWC	https://paperswithcode.com/paper/saliency-preservation-in-low-resolution
Repo
Framework

Invariant Synthesis for Incomplete Verification Engines


Title	Invariant Synthesis for Incomplete Verification Engines
Authors	Daniel Neider, Pranav Garg, P. Madhusudan, Shambwaditya Saha, Daejun Park
Abstract	We propose a framework for synthesizing inductive invariants for incomplete verification engines, which soundly reduce logical problems in undecidable theories to decidable theories. Our framework is based on the counter-example guided inductive synthesis principle (CEGIS) and allows verification engines to communicate non-provability information to guide invariant synthesis. We show precisely how the verification engine can compute such non-provability information and how to build effective learning algorithms when invariants are expressed as Boolean combinations of a fixed set of predicates. Moreover, we evaluate our framework in two verification settings, one in which verification engines need to handle quantified formulas and one in which verification engines have to reason about heap properties expressed in an expressive but undecidable separation logic. Our experiments show that our invariant synthesis framework based on non-provability information can both effectively synthesize inductive invariants and adequately strengthen contracts across a large suite of programs.
Tasks
Published	2017-12-15
URL	http://arxiv.org/abs/1712.05581v2
PDF	http://arxiv.org/pdf/1712.05581v2.pdf
PWC	https://paperswithcode.com/paper/invariant-synthesis-for-incomplete
Repo
Framework

On the Model Shrinkage Effect of Gamma Process Edge Partition Models


Title	On the Model Shrinkage Effect of Gamma Process Edge Partition Models
Authors	Iku Ohama, Issei Sato, Takuya Kida, Hiroki Arimura
Abstract	The edge partition model (EPM) is a fundamental Bayesian nonparametric model for extracting an overlapping structure from binary matrix. The EPM adopts a gamma process ($\Gamma$P) prior to automatically shrink the number of active atoms. However, we empirically found that the model shrinkage of the EPM does not typically work appropriately and leads to an overfitted solution. An analysis of the expectation of the EPM’s intensity function suggested that the gamma priors for the EPM hyperparameters disturb the model shrinkage effect of the internal $\Gamma$P. In order to ensure that the model shrinkage effect of the EPM works in an appropriate manner, we proposed two novel generative constructions of the EPM: CEPM incorporating constrained gamma priors, and DEPM incorporating Dirichlet priors instead of the gamma priors. Furthermore, all DEPM’s model parameters including the infinite atoms of the $\Gamma$P prior could be marginalized out, and thus it was possible to derive a truly infinite DEPM (IDEPM) that can be efficiently inferred using a collapsed Gibbs sampler. We experimentally confirmed that the model shrinkage of the proposed models works well and that the IDEPM indicated state-of-the-art performance in generalization ability, link prediction accuracy, mixing efficiency, and convergence speed.
Tasks	Link Prediction
Published	2017-09-26
URL	http://arxiv.org/abs/1709.08770v1
PDF	http://arxiv.org/pdf/1709.08770v1.pdf
PWC	https://paperswithcode.com/paper/on-the-model-shrinkage-effect-of-gamma
Repo
Framework

Modeling Target-Side Inflection in Neural Machine Translation


Title	Modeling Target-Side Inflection in Neural Machine Translation
Authors	Aleš Tamchyna, Marion Weller-Di Marco, Alexander Fraser
Abstract	NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, it does not enable effective generalization over the rich vocabulary in morphologically rich languages with strong inflectional phenomena. We introduce a simple approach to overcome this problem by training a system to produce the lemma of a word and its morphologically rich POS tag, which is then followed by a deterministic generation step. We apply this strategy for English-Czech and English-German translation scenarios, obtaining improvements in both settings. We furthermore show that the improvement is not due to only adding explicit morphological information.
Tasks	Machine Translation
Published	2017-07-19
URL	http://arxiv.org/abs/1707.06012v2
PDF	http://arxiv.org/pdf/1707.06012v2.pdf
PWC	https://paperswithcode.com/paper/modeling-target-side-inflection-in-neural
Repo
Framework

Predictive networking and optimization for flow-based networks


Title	Predictive networking and optimization for flow-based networks
Authors	Michael Arnold
Abstract	Artificial Neural Networks (ANNs) were used to classify neural network flows by flow size. After training the neural network was able to predict the size of a flows with 87% accuracy with a Feed Forward Neural Network. This demonstrates that flow based routers can prioritize candidate flows with a predicted large number of packets for priority insertion into hardware content-addressable memory.
Tasks
Published	2017-07-21
URL	http://arxiv.org/abs/1707.06729v1
PDF	http://arxiv.org/pdf/1707.06729v1.pdf
PWC	https://paperswithcode.com/paper/predictive-networking-and-optimization-for
Repo
Framework

Towards Context-aware Interaction Recognition


Title	Towards Context-aware Interaction Recognition
Authors	Bohan Zhuang, Lingqiao Liu, Chunhua Shen, Ian Reid
Abstract	Recognizing how objects interact with each other is a crucial task in visual recognition. If we define the context of the interaction to be the objects involved, then most current methods can be categorized as either: (i) training a single classifier on the combination of the interaction and its context; or (ii) aiming to recognize the interaction independently of its explicit context. Both methods suffer limitations: the former scales poorly with the number of combinations and fails to generalize to unseen combinations, while the latter often leads to poor interaction recognition performance due to the difficulty of designing a context-independent interaction classifier. To mitigate those drawbacks, this paper proposes an alternative, context-aware interaction recognition framework. The key to our method is to explicitly construct an interaction classifier which combines the context, and the interaction. The context is encoded via word2vec into a semantic space, and is used to derive a classification result for the interaction. The proposed method still builds one classifier for one interaction (as per type (ii) above), but the classifier built is adaptive to context via weights which are context dependent. The benefit of using the semantic space is that it naturally leads to zero-shot generalizations in which semantically similar contexts (subjectobject pairs) can be recognized as suitable contexts for an interaction, even if they were not observed in the training set.
Tasks
Published	2017-03-18
URL	http://arxiv.org/abs/1703.06246v3
PDF	http://arxiv.org/pdf/1703.06246v3.pdf
PWC	https://paperswithcode.com/paper/towards-context-aware-interaction-recognition
Repo
Framework

Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB


Title	Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB
Authors	Aitor Alvarez-Gila, Joost van de Weijer, Estibaliz Garrote
Abstract	Hyperspectral signal reconstruction aims at recovering the original spectral input that produced a certain trichromatic (RGB) response from a capturing device or observer. Given the heavily underconstrained, non-linear nature of the problem, traditional techniques leverage different statistical properties of the spectral signal in order to build informative priors from real world object reflectances for constructing such RGB to spectral signal mapping. However, most of them treat each sample independently, and thus do not benefit from the contextual information that the spatial dimensions can provide. We pose hyperspectral natural image reconstruction as an image to image mapping learning problem, and apply a conditional generative adversarial framework to help capture spatial semantics. This is the first time Convolutional Neural Networks -and, particularly, Generative Adversarial Networks- are used to solve this task. Quantitative evaluation shows a Root Mean Squared Error (RMSE) drop of 33.2% and a Relative RMSE drop of 54.0% on the ICVL natural hyperspectral image dataset.
Tasks	Image Reconstruction
Published	2017-09-01
URL	http://arxiv.org/abs/1709.00265v2
PDF	http://arxiv.org/pdf/1709.00265v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-networks-for-spatial-context
Repo
Framework

Online Learning with Local Permutations and Delayed Feedback


Title	Online Learning with Local Permutations and Delayed Feedback
Authors	Ohad Shamir, Liran Szlak
Abstract	We propose an Online Learning with Local Permutations (OLLP) setting, in which the learner is allowed to slightly permute the \emph{order} of the loss functions generated by an adversary. On one hand, this models natural situations where the exact order of the learner’s responses is not crucial, and on the other hand, might allow better learning and regret performance, by mitigating highly adversarial loss sequences. Also, with random permutations, this can be seen as a setting interpolating between adversarial and stochastic losses. In this paper, we consider the applicability of this setting to convex online learning with delayed feedback, in which the feedback on the prediction made in round $t$ arrives with some delay $\tau$. With such delayed feedback, the best possible regret bound is well-known to be $O(\sqrt{\tau T})$. We prove that by being able to permute losses by a distance of at most $M$ (for $M\geq \tau$), the regret can be improved to $O(\sqrt{T}(1+\sqrt{\tau^2/M}))$, using a Mirror-Descent based algorithm which can be applied for both Euclidean and non-Euclidean geometries. We also prove a lower bound, showing that for $M<\tau/3$, it is impossible to improve the standard $O(\sqrt{\tau T})$ regret bound by more than constant factors. Finally, we provide some experiments validating the performance of our algorithm.
Tasks
Published	2017-03-13
URL	http://arxiv.org/abs/1703.04274v1
PDF	http://arxiv.org/pdf/1703.04274v1.pdf
PWC	https://paperswithcode.com/paper/online-learning-with-local-permutations-and
Repo
Framework

Spectral clustering in the dynamic stochastic block model


Title	Spectral clustering in the dynamic stochastic block model
Authors	Marianna Pensky, Teng Zhang
Abstract	In the present paper, we studied a Dynamic Stochastic Block Model (DSBM) under the assumptions that the connection probabilities, as functions of time, are smooth and that at most $s$ nodes can switch their class memberships between two consecutive time points. We estimate the edge probability tensor by a kernel-type procedure and extract the group memberships of the nodes by spectral clustering. The procedure is computationally viable, adaptive to the unknown smoothness of the functional connection probabilities, to the rate $s$ of membership switching and to the unknown number of clusters. In addition, it is accompanied by non-asymptotic guarantees for the precision of estimation and clustering.
Tasks
Published	2017-05-02
URL	http://arxiv.org/abs/1705.01204v1
PDF	http://arxiv.org/pdf/1705.01204v1.pdf
PWC	https://paperswithcode.com/paper/spectral-clustering-in-the-dynamic-stochastic
Repo
Framework

PIRVS: An Advanced Visual-Inertial SLAM System with Flexible Sensor Fusion and Hardware Co-Design


Title	PIRVS: An Advanced Visual-Inertial SLAM System with Flexible Sensor Fusion and Hardware Co-Design
Authors	Zhe Zhang, Shaoshan Liu, Grace Tsai, Hongbing Hu, Chen-Chi Chu, Feng Zheng
Abstract	In this paper, we present the PerceptIn Robotics Vision System (PIRVS) system, a visual-inertial computing hardware with embedded simultaneous localization and mapping (SLAM) algorithm. The PIRVS hardware is equipped with a multi-core processor, a global-shutter stereo camera, and an IMU with precise hardware synchronization. The PIRVS software features a novel and flexible sensor fusion approach to not only tightly integrate visual measurements with inertial measurements and also to loosely couple with additional sensor modalities. It runs in real-time on both PC and the PIRVS hardware. We perform a thorough evaluation of the proposed system using multiple public visual-inertial datasets. Experimental results demonstrate that our system reaches comparable accuracy of state-of-the-art visual-inertial algorithms on PC, while being more efficient on the PIRVS hardware.
Tasks	Sensor Fusion, Simultaneous Localization and Mapping
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00893v1
PDF	http://arxiv.org/pdf/1710.00893v1.pdf
PWC	https://paperswithcode.com/paper/pirvs-an-advanced-visual-inertial-slam-system
Repo
Framework

Learning Approximate Neural Estimators for Wireless Channel State Information


Title	Learning Approximate Neural Estimators for Wireless Channel State Information
Authors	Timothy J. O’Shea, Kiran Karra, T. Charles Clancy
Abstract	Estimation is a critical component of synchronization in wireless and signal processing systems. There is a rich body of work on estimator derivation, optimization, and statistical characterization from analytic system models which are used pervasively today. We explore an alternative approach to building estimators which relies principally on approximate regression using large datasets and large computationally efficient artificial neural network models capable of learning non-linear function mappings which provide compact and accurate estimates. For single carrier PSK modulation, we explore the accuracy and computational complexity of such estimators compared with the current gold-standard analytically derived alternatives. We compare performance in various wireless operating conditions and consider the trade offs between the two different classes of systems. Our results show the learned estimators can provide improvements in areas such as short-time estimation and estimation under non-trivial real world channel conditions such as fading or other non-linear hardware or propagation effects.
Tasks
Published	2017-07-19
URL	http://arxiv.org/abs/1707.06260v1
PDF	http://arxiv.org/pdf/1707.06260v1.pdf
PWC	https://paperswithcode.com/paper/learning-approximate-neural-estimators-for
Repo
Framework