October 18, 2019

3034 words 15 mins read

Paper Group ANR 424

A Deep Learning and Gamification Approach to Energy Conservation at Nanyang Technological University. From Superpixel to Human Shape Modelling for Carried Object Detection. An Empirical Analysis of the Correlation of Syntax and Prosody. Weighted Sigmoid Gate Unit for an Activation Function of Deep Neural Network. Divide and Recombine for Large and …

A Deep Learning and Gamification Approach to Energy Conservation at Nanyang Technological University


Title	A Deep Learning and Gamification Approach to Energy Conservation at Nanyang Technological University
Authors	Ioannis C. Konstantakopoulos, Andrew R. Barkan, Shiying He, Tanya Veeravalli, Huihan Liu, Costas Spanos
Abstract	The implementation of smart building technology in the form of smart infrastructure applications has great potential to improve sustainability and energy efficiency by leveraging humans-in-the-loop strategy. However, human preference in regard to living conditions is usually unknown and heterogeneous in its manifestation as control inputs to a building. Furthermore, the occupants of a building typically lack the independent motivation necessary to contribute to and play a key role in the control of smart building infrastructure. Moreover, true human actions and their integration with sensing/actuation platforms remains unknown to the decision maker tasked with improving operational efficiency. By modeling user interaction as a sequential discrete game between non-cooperative players, we introduce a gamification approach for supporting user engagement and integration in a human-centric cyber-physical system. We propose the design and implementation of a large-scale network game with the goal of improving the energy efficiency of a building through the utilization of cutting-edge Internet of Things (IoT) sensors and cyber-physical systems sensing/actuation platforms. A benchmark utility learning framework that employs robust estimations for classical discrete choice models provided for the derived high dimensional imbalanced data. To improve forecasting performance, we extend the benchmark utility learning scheme by leveraging Deep Learning end-to-end training with Deep bi-directional Recurrent Neural Networks. We apply the proposed methods to high dimensional data from a social game experiment designed to encourage energy efficient behavior among smart building occupants in Nanyang Technological University (NTU) residential housing. Using occupant-retrieved actions for resources such as lighting and A/C, we simulate the game defined by the estimated utility functions.
Tasks
Published	2018-09-13
URL	http://arxiv.org/abs/1809.05142v2
PDF	http://arxiv.org/pdf/1809.05142v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-and-gamification-approach-to
Repo
Framework

From Superpixel to Human Shape Modelling for Carried Object Detection


Title	From Superpixel to Human Shape Modelling for Carried Object Detection
Authors	Farnoosh Ghadiri, Robert Bergevin, Guillaume-Alexandre Bilodeau
Abstract	Detecting carried objects is one of the requirements for developing systems to reason about activities involving people and objects. We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales. Initially, a foreground mask in a video frame is segmented into multi-scale superpixels. Then the human-like regions in the segmented area are identified by matching a set of extracted features from superpixels against learned features in a codebook. A carried object probability map is generated using the complement of the matching probabilities of superpixels to human-like regions and background information. A group of superpixels with high carried object probability and strong edge support is then merged to obtain the shape of the carried object. We applied our method to two challenging datasets, and results show that our method is competitive with or better than the state-of-the-art.
Tasks	Object Detection
Published	2018-01-10
URL	http://arxiv.org/abs/1801.03551v1
PDF	http://arxiv.org/pdf/1801.03551v1.pdf
PWC	https://paperswithcode.com/paper/from-superpixel-to-human-shape-modelling-for
Repo
Framework

An Empirical Analysis of the Correlation of Syntax and Prosody


Title	An Empirical Analysis of the Correlation of Syntax and Prosody
Authors	Arne Köhn, Timo Baumann, Oskar Dörfler
Abstract	The relation of syntax and prosody (the syntax–prosody interface) has been an active area of research, mostly in linguistics and typically studied under controlled conditions. More recently, prosody has also been successfully used in the data-based training of syntax parsers. However, there is a gap between the controlled and detailed study of the individual effects between syntax and prosody and the large-scale application of prosody in syntactic parsing with only a shallow analysis of the respective influences. In this paper, we close the gap by investigating the significance of correlations of prosodic realization with specific syntactic functions using linear mixed effects models in a very large corpus of read-out German encyclopedic texts. Using this corpus, we are able to analyze prosodic structuring performed by a diverse set of speakers while they try to optimize factual content delivery. After normalization by speaker, we obtain significant effects, e.g. confirming that the subject function, as compared to the object function, has a positive effect on pitch and duration of a word, but a negative effect on loudness.
Tasks
Published	2018-06-15
URL	http://arxiv.org/abs/1806.05900v1
PDF	http://arxiv.org/pdf/1806.05900v1.pdf
PWC	https://paperswithcode.com/paper/an-empirical-analysis-of-the-correlation-of
Repo
Framework

Weighted Sigmoid Gate Unit for an Activation Function of Deep Neural Network


Title	Weighted Sigmoid Gate Unit for an Activation Function of Deep Neural Network
Authors	Masayuki Tanaka
Abstract	An activation function has crucial role in a deep neural network. A simple rectified linear unit (ReLU) are widely used for the activation function. In this paper, a weighted sigmoid gate unit (WiG) is proposed as the activation function. The proposed WiG consists of a multiplication of inputs and the weighted sigmoid gate. It is shown that the WiG includes the ReLU and same activation functions as a special case. Many activation functions have been proposed to overcome the performance of the ReLU. In the literature, the performance is mainly evaluated with an object recognition task. The proposed WiG is evaluated with the object recognition task and the image restoration task. Then, the expeirmental comparisons demonstrate the proposed WiG overcomes the existing activation functions including the ReLU.
Tasks	Image Restoration, Object Recognition
Published	2018-10-03
URL	http://arxiv.org/abs/1810.01829v1
PDF	http://arxiv.org/pdf/1810.01829v1.pdf
PWC	https://paperswithcode.com/paper/weighted-sigmoid-gate-unit-for-an-activation
Repo
Framework

Divide and Recombine for Large and Complex Data: Model Likelihood Functions using MCMC


Title	Divide and Recombine for Large and Complex Data: Model Likelihood Functions using MCMC
Authors	Qi Liu, Anindya Bhadra, William S. Cleveland
Abstract	In Divide & Recombine (D&R), big data are divided into subsets, each analytic method is applied to subsets, and the outputs are recombined. This enables deep analysis and practical computational performance. An innovate D&R procedure is proposed to compute likelihood functions of data-model (DM) parameters for big data. The likelihood-model (LM) is a parametric probability density function of the DM parameters. The density parameters are estimated by fitting the density to MCMC draws from each subset DM likelihood function, and then the fitted densities are recombined. The procedure is illustrated using normal and skew-normal LMs for the logistic regression DM.
Tasks
Published	2018-01-15
URL	http://arxiv.org/abs/1801.05007v1
PDF	http://arxiv.org/pdf/1801.05007v1.pdf
PWC	https://paperswithcode.com/paper/divide-and-recombine-for-large-and-complex
Repo
Framework

HyperST-Net: Hypernetworks for Spatio-Temporal Forecasting


Title	HyperST-Net: Hypernetworks for Spatio-Temporal Forecasting
Authors	Zheyi Pan, Yuxuan Liang, Junbo Zhang, Xiuwen Yi, Yong Yu, Yu Zheng
Abstract	Spatio-temporal (ST) data, which represent multiple time series data corresponding to different spatial locations, are ubiquitous in real-world dynamic systems, such as air quality readings. Forecasting over ST data is of great importance but challenging as it is affected by many complex factors, including spatial characteristics, temporal characteristics and the intrinsic causality between them. In this paper, we propose a general framework (HyperST-Net) based on hypernetworks for deep ST models. More specifically, it consists of three major modules: a spatial module, a temporal module and a deduction module. Among them, the deduction module derives the parameter weights of the temporal module from the spatial characteristics, which are extracted by the spatial module. Then, we design a general form of HyperST layer as well as different forms for several basic layers in neural networks, including the dense layer (HyperST-Dense) and the convolutional layer (HyperST-Conv). Experiments on three types of real-world tasks demonstrate that the predictive models integrated with our framework achieve significant improvements, and outperform the state-of-the-art baselines as well.
Tasks	Spatio-Temporal Forecasting, Time Series
Published	2018-09-28
URL	http://arxiv.org/abs/1809.10889v1
PDF	http://arxiv.org/pdf/1809.10889v1.pdf
PWC	https://paperswithcode.com/paper/hyperst-net-hypernetworks-for-spatio-temporal
Repo
Framework

Adaptive Scan Gibbs Sampler for Large Scale Inference Problems


Title	Adaptive Scan Gibbs Sampler for Large Scale Inference Problems
Authors	Vadim Smolyakov, Qiang Liu, John W. Fisher III
Abstract	For large scale on-line inference problems the update strategy is critical for performance. We derive an adaptive scan Gibbs sampler that optimizes the update frequency by selecting an optimum mini-batch size. We demonstrate performance of our adaptive batch-size Gibbs sampler by comparing it against the collapsed Gibbs sampler for Bayesian Lasso, Dirichlet Process Mixture Models (DPMM) and Latent Dirichlet Allocation (LDA) graphical models.
Tasks
Published	2018-01-27
URL	http://arxiv.org/abs/1801.09144v1
PDF	http://arxiv.org/pdf/1801.09144v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-scan-gibbs-sampler-for-large-scale
Repo
Framework

A Distributed Quasi-Newton Algorithm for Empirical Risk Minimization with Nonsmooth Regularization


Title	A Distributed Quasi-Newton Algorithm for Empirical Risk Minimization with Nonsmooth Regularization
Authors	Ching-pei Lee, Cong Han Lim, Stephen J. Wright
Abstract	We propose a communication- and computation-efficient distributed optimization algorithm using second-order information for solving ERM problems with a nonsmooth regularization term. Current second-order and quasi-Newton methods for this problem either do not work well in the distributed setting or work only for specific regularizers. Our algorithm uses successive quadratic approximations, and we describe how to maintain an approximation of the Hessian and solve subproblems efficiently in a distributed manner. The proposed method enjoys global linear convergence for a broad range of non-strongly convex problems that includes the most commonly used ERMs, thus requiring lower communication complexity. It also converges on non-convex problems, so has the potential to be used on applications such as deep learning. Initial computational results on convex problems demonstrate that our method significantly improves on communication cost and running time over the current state-of-the-art methods.
Tasks	Distributed Optimization
Published	2018-03-04
URL	http://arxiv.org/abs/1803.01370v2
PDF	http://arxiv.org/pdf/1803.01370v2.pdf
PWC	https://paperswithcode.com/paper/a-distributed-quasi-newton-algorithm-for
Repo
Framework

Innateness, AlphaZero, and Artificial Intelligence


Title	Innateness, AlphaZero, and Artificial Intelligence
Authors	Gary Marcus
Abstract	The concept of innateness is rarely discussed in the context of artificial intelligence. When it is discussed, or hinted at, it is often the context of trying to reduce the amount of innate machinery in a given system. In this paper, I consider as a test case a recent series of papers by Silver et al (Silver et al., 2017a) on AlphaGo and its successors that have been presented as an argument that a “even in the most challenging of domains: it is possible to train to superhuman level, without human examples or guidance”, “starting tabula rasa.” I argue that these claims are overstated, for multiple reasons. I close by arguing that artificial intelligence needs greater attention to innateness, and I point to some proposals about what that innateness might look like.
Tasks
Published	2018-01-17
URL	http://arxiv.org/abs/1801.05667v1
PDF	http://arxiv.org/pdf/1801.05667v1.pdf
PWC	https://paperswithcode.com/paper/innateness-alphazero-and-artificial
Repo
Framework

Machine Translation: A Literature Review


Title	Machine Translation: A Literature Review
Authors	Ankush Garg, Mayank Agarwal
Abstract	Machine translation (MT) plays an important role in benefiting linguists, sociologists, computer scientists, etc. by processing natural language to translate it into some other natural language. And this demand has grown exponentially over past couple of years, considering the enormous exchange of information between different regions with different regional languages. Machine Translation poses numerous challenges, some of which are: a) Not all words in one language has equivalent word in another language b) Two given languages may have completely different structures c) Words can have more than one meaning. Owing to these challenges, along with many others, MT has been active area of research for more than five decades. Numerous methods have been proposed in the past which either aim at improving the quality of the translations generated by them, or study the robustness of these systems by measuring their performance on many different languages. In this literature review, we discuss statistical approaches (in particular word-based and phrase-based) and neural approaches which have gained widespread prominence owing to their state-of-the-art results across multiple major languages.
Tasks	Machine Translation
Published	2018-12-28
URL	http://arxiv.org/abs/1901.01122v1
PDF	http://arxiv.org/pdf/1901.01122v1.pdf
PWC	https://paperswithcode.com/paper/machine-translation-a-literature-review
Repo
Framework

Linear Queries Estimation with Local Differential Privacy


Title	Linear Queries Estimation with Local Differential Privacy
Authors	Raef Bassily
Abstract	We study the problem of estimating a set of $d$ linear queries with respect to some unknown distribution $\mathbf{p}$ over a domain $\mathcal{J}=[J]$ based on a sensitive data set of $n$ individuals under the constraint of local differential privacy. This problem subsumes a wide range of estimation tasks, e.g., distribution estimation and $d$-dimensional mean estimation. We provide new algorithms for both the offline (non-adaptive) and adaptive versions of this problem. In the offline setting, the set of queries are fixed before the algorithm starts. In the regime where $n\lesssim d^2/\log(J)$, our algorithms attain $L_2$ estimation error that is independent of $d$, and is tight up to a factor of $\tilde{O}\left(\log^{1/4}(J)\right)$. For the special case of distribution estimation, we show that projecting the output estimate of an algorithm due to [Acharya et al. 2018] on the probability simplex yields an $L_2$ error that depends only sub-logarithmically on $J$ in the regime where $n\lesssim J^2/\log(J)$. These results show the possibility of accurate estimation of linear queries in the high-dimensional settings under the $L_2$ error criterion. In the adaptive setting, the queries are generated over $d$ rounds; one query at a time. In each round, a query can be chosen adaptively based on all the history of previous queries and answers. We give an algorithm for this problem with optimal $L_{\infty}$ estimation error (worst error in the estimated values for the queries w.r.t. the data distribution). Our bound matches a lower bound on the $L_{\infty}$ error for the offline version of this problem [Duchi et al. 2013].
Tasks
Published	2018-10-05
URL	http://arxiv.org/abs/1810.02810v1
PDF	http://arxiv.org/pdf/1810.02810v1.pdf
PWC	https://paperswithcode.com/paper/linear-queries-estimation-with-local
Repo
Framework

A Work Zone Simulation Model for Travel Time Prediction in a Connected Vehicle Environment


Title	A Work Zone Simulation Model for Travel Time Prediction in a Connected Vehicle Environment
Authors	Xuejin Wen
Abstract	A work zone bottleneck in a roadway network can cause traffic delays, emissions and safety issues. Accurate measurement and prediction of work zone travel time can help travelers make better routing decisions and therefore mitigate its impact. Historically, data used for travel time analyses comes from fixed loop detectors, which are expensive to install and maintain. With connected vehicle technology, such as Vehicle-to-Infrastructure, portable roadside unit (RSU) can be located in and around a work zone segment to communicate with the vehicles and collect traffic data. A PARAMICS simulation model for a prototypical freeway work zone in a connected vehicle environment was built to test this idea using traffic demand data from NY State Route 104. For the simulation, twelve RSUs were placed along the work zone segment and sixteen variables were extracted from the simulation results to explore travel time estimation and prediction. For the travel time analysis, four types of models were constructed, including linear regression, multivariate adaptive regression splines (MARS), stepwise regression and elastic net. The results show that the modeling approaches under consideration have similar performance in terms of the Root of Mean Square Error (RMSE), which provides an opportunity for model selection based on additional factors including the number and locations of the RSUs according to the significant variables identified in the various models. Among the four approaches, the stepwise regression model only needs variables from two RSUs: one placed sufficiently upstream of the work zone and one at the end of the work zone.
Tasks	Model Selection
Published	2018-01-20
URL	http://arxiv.org/abs/1801.07579v1
PDF	http://arxiv.org/pdf/1801.07579v1.pdf
PWC	https://paperswithcode.com/paper/a-work-zone-simulation-model-for-travel-time
Repo
Framework

Combining Background Subtraction Algorithms with Convolutional Neural Network


Title	Combining Background Subtraction Algorithms with Convolutional Neural Network
Authors	Dongdong Zeng, Ming Zhu, Arjan Kuijper
Abstract	Accurate and fast extraction of foreground object is a key prerequisite for a wide range of computer vision applications such as object tracking and recognition. Thus, enormous background subtraction methods for foreground object detection have been proposed in recent decades. However, it is still regarded as a tough problem due to a variety of challenges such as illumination variations, camera jitter, dynamic backgrounds, shadows, and so on. Currently, there is no single method that can handle all the challenges in a robust way. In this letter, we try to solve this problem from a new perspective by combining different state-of-the-art background subtraction algorithms to create a more robust and more advanced foreground detection algorithm. More specifically, an encoder-decoder fully convolutional neural network architecture is trained to automatically learn how to leverage the characteristics of different algorithms to fuse the results produced by different background subtraction algorithms and output a more precise result. Comprehensive experiments evaluated on the CDnet 2014 dataset demonstrate that the proposed method outperforms all the considered single background subtraction algorithm. And we show that our solution is more efficient than other combination strategies.
Tasks	Object Detection, Object Tracking
Published	2018-07-05
URL	http://arxiv.org/abs/1807.02080v2
PDF	http://arxiv.org/pdf/1807.02080v2.pdf
PWC	https://paperswithcode.com/paper/combining-background-subtraction-algorithms
Repo
Framework

Local Critic Training of Deep Neural Networks


Title	Local Critic Training of Deep Neural Networks
Authors	Hojung Lee, Jong-seok Lee
Abstract	This paper proposes a novel approach to train deep neural networks by unlocking the layer-wise dependency of backpropagation training. The approach employs additional modules called local critic networks besides the main network model to be trained, which are used to obtain error gradients without complete feedforward and backward propagation processes. We propose a cascaded learning strategy for these local networks. In addition, the approach is also useful from multi-model perspectives, including structural optimization of neural networks, computationally efficient progressive inference, and ensemble classification for performance improvement. Experimental results show the effectiveness of the proposed approach and suggest guidelines for determining appropriate algorithm parameters.
Tasks
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01128v2
PDF	http://arxiv.org/pdf/1805.01128v2.pdf
PWC	https://paperswithcode.com/paper/local-critic-training-of-deep-neural-networks
Repo
Framework

FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation


Title	FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation
Authors	René Schuster, Christian Bailer, Oliver Wasenmüller, Didier Stricker
Abstract	Optical Flow algorithms are of high importance for many applications. Recently, the Flow Field algorithm and its modifications have shown remarkable results, as they have been evaluated with top accuracy on different data sets. In our analysis of the algorithm we have found that it produces accurate sparse matches, but there is room for improvement in the interpolation. Thus, we propose in this paper FlowFields++, where we combine the accurate matches of Flow Fields with a robust interpolation. In addition, we propose improved variational optimization as post-processing. Our new algorithm is evaluated on the challenging KITTI and MPI Sintel data sets with public top results on both benchmarks.
Tasks	Optical Flow Estimation
Published	2018-05-09
URL	http://arxiv.org/abs/1805.03517v1
PDF	http://arxiv.org/pdf/1805.03517v1.pdf
PWC	https://paperswithcode.com/paper/flowfields-accurate-optical-flow
Repo
Framework