Paper Group ANR 770
Generating High-Quality Query Suggestion Candidates for Task-Based Search. Valuing knowledge, information and agency in Multi-agent Reinforcement Learning: a case study in smart buildings. Sine Cosine Crow Search Algorithm: A powerful hybrid meta heuristic for global optimization. Perceptrons from Memristors. Learning Multimodal Word Representation …
Generating High-Quality Query Suggestion Candidates for Task-Based Search
Title | Generating High-Quality Query Suggestion Candidates for Task-Based Search |
Authors | Heng Ding, Shuo Zhang, Darío Garigliotti, Krisztian Balog |
Abstract | We address the task of generating query suggestions for task-based search. The current state of the art relies heavily on suggestions provided by a major search engine. In this paper, we solve the task without reliance on search engines. Specifically, we focus on the first step of a two-stage pipeline approach, which is dedicated to the generation of query suggestion candidates. We present three methods for generating candidate suggestions and apply them on multiple information sources. Using a purpose-built test collection, we find that these methods are able to generate high-quality suggestion candidates. |
Tasks | |
Published | 2018-02-22 |
URL | http://arxiv.org/abs/1802.07997v1 |
http://arxiv.org/pdf/1802.07997v1.pdf | |
PWC | https://paperswithcode.com/paper/generating-high-quality-query-suggestion |
Repo | |
Framework | |
Valuing knowledge, information and agency in Multi-agent Reinforcement Learning: a case study in smart buildings
Title | Valuing knowledge, information and agency in Multi-agent Reinforcement Learning: a case study in smart buildings |
Authors | Hussain Kazmi, Johan Suykens, Johan Driesen |
Abstract | Increasing energy efficiency in buildings can reduce costs and emissions substantially. Historically, this has been treated as a local, or single-agent, optimization problem. However, many buildings utilize the same types of thermal equipment e.g. electric heaters and hot water vessels. During operation, occupants in these buildings interact with the equipment differently thereby driving them to diverse regions in the state-space. Reinforcement learning agents can learn from these interactions, recorded as sensor data, to optimize the overall energy efficiency. However, if these agents operate individually at a household level, they can not exploit the replicated structure in the problem. In this paper, we demonstrate that this problem can indeed benefit from multi-agent collaboration by making use of targeted exploration of the state-space allowing for better generalization. We also investigate trade-offs between integrating human knowledge and additional sensors. Results show that savings of over 40% are possible with collaborative multi-agent systems making use of either expert knowledge or additional sensors with no loss of occupant comfort. We find that such multi-agent systems comfortably outperform comparable single agent systems. |
Tasks | Multi-agent Reinforcement Learning |
Published | 2018-03-09 |
URL | http://arxiv.org/abs/1803.03491v1 |
http://arxiv.org/pdf/1803.03491v1.pdf | |
PWC | https://paperswithcode.com/paper/valuing-knowledge-information-and-agency-in |
Repo | |
Framework | |
Sine Cosine Crow Search Algorithm: A powerful hybrid meta heuristic for global optimization
Title | Sine Cosine Crow Search Algorithm: A powerful hybrid meta heuristic for global optimization |
Authors | Seyed Hamid Reza Pasandideh, Soheyl Khalilpourazari |
Abstract | This paper presents a novel hybrid algorithm named Since Cosine Crow Search Algorithm. To propose the SCCSA, two novel algorithms are considered including Crow Search Algorithm (CSA) and Since Cosine Algorithm (SCA). The advantages of the two algorithms are considered and utilize to design an efficient hybrid algorithm which can perform significantly better in various benchmark functions. The combination of concept and operators of the two algorithms enable the SCCSA to make an appropriate trade-off between exploration and exploitation abilities of the algorithm. To evaluate the performance of the proposed SCCSA, seven well-known benchmark functions are utilized. The results indicated that the proposed hybrid algorithm is able to provide very competitive solution comparing to other state-of-the-art meta heuristics. |
Tasks | |
Published | 2018-01-25 |
URL | http://arxiv.org/abs/1801.08485v1 |
http://arxiv.org/pdf/1801.08485v1.pdf | |
PWC | https://paperswithcode.com/paper/sine-cosine-crow-search-algorithm-a-powerful |
Repo | |
Framework | |
Perceptrons from Memristors
Title | Perceptrons from Memristors |
Authors | Francisco Silva, Mikel Sanz, João Seixas, Enrique Solano, Yasser Omar |
Abstract | Memristors, resistors with memory whose outputs depend on the history of their inputs, have been used with success in neuromorphic architectures, particularly as synapses and non-volatile memories. However, to the best of our knowledge, no model for a network in which both the synapses and the neurons are implemented using memristors has been proposed so far. In the present work we introduce models for single and multilayer perceptrons based exclusively on memristors. We adapt the delta rule to the memristor-based single-layer perceptron and the backpropagation algorithm to the memristor-based multilayer perceptron. Our results show that both perform as expected for perceptrons, including satisfying Minsky-Papert’s theorem. As a consequence of the Universal Approximation Theorem, they also show that memristors are universal function approximators. By using memristors for both the neurons and the synapses, our models pave the way for novel memristor-based neural network architectures and algorithms. A neural network based on memristors could show advantages in terms of energy conservation and open up possibilities for other learning systems to be adapted to a memristor-based paradigm, both in the classical and quantum learning realms. |
Tasks | |
Published | 2018-07-13 |
URL | http://arxiv.org/abs/1807.04912v2 |
http://arxiv.org/pdf/1807.04912v2.pdf | |
PWC | https://paperswithcode.com/paper/perceptrons-from-memristors |
Repo | |
Framework | |
Learning Multimodal Word Representation via Dynamic Fusion Methods
Title | Learning Multimodal Word Representation via Dynamic Fusion Methods |
Authors | Shaonan Wang, Jiajun Zhang, Chengqing Zong |
Abstract | Multimodal models have been proven to outperform text-based models on learning semantic word representations. Almost all previous multimodal models typically treat the representations from different modalities equally. However, it is obvious that information from different modalities contributes differently to the meaning of words. This motivates us to build a multimodal model that can dynamically fuse the semantic representations from different modalities according to different types of words. To that end, we propose three novel dynamic fusion methods to assign importance weights to each modality, in which weights are learned under the weak supervision of word association pairs. The extensive experiments have demonstrated that the proposed methods outperform strong unimodal baselines and state-of-the-art multimodal models. |
Tasks | |
Published | 2018-01-02 |
URL | http://arxiv.org/abs/1801.00532v1 |
http://arxiv.org/pdf/1801.00532v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-multimodal-word-representation-via |
Repo | |
Framework | |
DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction
Title | DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction |
Authors | Brandon Ballinger, Johnson Hsieh, Avesh Singh, Nimit Sohoni, Jack Wang, Geoffrey H. Tison, Gregory M. Marcus, Jose M. Sanchez, Carol Maguire, Jeffrey E. Olgin, Mark J. Pletcher |
Abstract | We train and validate a semi-supervised, multi-task LSTM on 57,675 person-weeks of data from off-the-shelf wearable heart rate sensors, showing high accuracy at detecting multiple medical conditions, including diabetes (0.8451), high cholesterol (0.7441), high blood pressure (0.8086), and sleep apnea (0.8298). We compare two semi-supervised train- ing methods, semi-supervised sequence learning and heuristic pretraining, and show they outperform hand-engineered biomarkers from the medical literature. We believe our work suggests a new approach to patient risk stratification based on cardiovascular risk scores derived from popular wearables such as Fitbit, Apple Watch, or Android Wear. |
Tasks | |
Published | 2018-02-07 |
URL | http://arxiv.org/abs/1802.02511v1 |
http://arxiv.org/pdf/1802.02511v1.pdf | |
PWC | https://paperswithcode.com/paper/deepheart-semi-supervised-sequence-learning |
Repo | |
Framework | |
Intent-aware Multi-agent Reinforcement Learning
Title | Intent-aware Multi-agent Reinforcement Learning |
Authors | Siyuan Qi, Song-Chun Zhu |
Abstract | This paper proposes an intent-aware multi-agent planning framework as well as a learning algorithm. Under this framework, an agent plans in the goal space to maximize the expected utility. The planning process takes the belief of other agents’ intents into consideration. Instead of formulating the learning problem as a partially observable Markov decision process (POMDP), we propose a simple but effective linear function approximation of the utility function. It is based on the observation that for humans, other people’s intents will pose an influence on our utility for a goal. The proposed framework has several major advantages: i) it is computationally feasible and guaranteed to converge. ii) It can easily integrate existing intent prediction and low-level planning algorithms. iii) It does not suffer from sparse feedbacks in the action space. We experiment our algorithm in a real-world problem that is non-episodic, and the number of agents and goals can vary over time. Our algorithm is trained in a scene in which aerial robots and humans interact, and tested in a novel scene with a different environment. Experimental results show that our algorithm achieves the best performance and human-like behaviors emerge during the dynamic process. |
Tasks | Multi-agent Reinforcement Learning |
Published | 2018-03-06 |
URL | http://arxiv.org/abs/1803.02018v1 |
http://arxiv.org/pdf/1803.02018v1.pdf | |
PWC | https://paperswithcode.com/paper/intent-aware-multi-agent-reinforcement |
Repo | |
Framework | |
Support Vector Machine Application for Multiphase Flow Pattern Prediction
Title | Support Vector Machine Application for Multiphase Flow Pattern Prediction |
Authors | Pablo Guillen-Rondon, Melvin D. Robinson, Carlos Torres, Eduardo Pereya |
Abstract | In this paper a data analytical approach featuring support vector machines (SVM) is employed to train a predictive model over an experimentaldataset, which consists of the most relevant studies for two-phase flow pattern prediction. The database for this study consists of flow patterns or flow regimes in gas-liquid two-phase flow. The term flow pattern refers to the geometrical configuration of the gas and liquid phases in the pipe. When gas and liquid flow simultaneously in a pipe, the two phases can distribute themselves in a variety of flow configurations. Gas-liquid two-phase flow occurs ubiquitously in various major industrial fields: petroleum, chemical, nuclear, and geothermal industries. The flow configurations differ from each other in the spatial distribution of the interface, resulting in different flow characteristics. Experimental results obtained by applying the presented methodology to different combinations of flow patterns demonstrate that the proposed approach is state-of-the-art alternatives by achieving 97% correct classification. The results suggest machine learning could be used as an effective tool for automatic detection and classification of gas-liquid flow patterns. |
Tasks | |
Published | 2018-06-12 |
URL | http://arxiv.org/abs/1806.05054v1 |
http://arxiv.org/pdf/1806.05054v1.pdf | |
PWC | https://paperswithcode.com/paper/support-vector-machine-application-for |
Repo | |
Framework | |
Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising
Title | Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising |
Authors | Junqi Jin, Chengru Song, Han Li, Kun Gai, Jun Wang, Weinan Zhang |
Abstract | Real-time advertising allows advertisers to bid for each impression for a visiting user. To optimize specific goals such as maximizing revenue and return on investment (ROI) led by ad placements, advertisers not only need to estimate the relevance between the ads and user’s interests, but most importantly require a strategic response with respect to other advertisers bidding in the market. In this paper, we formulate bidding optimization with multi-agent reinforcement learning. To deal with a large number of advertisers, we propose a clustering method and assign each cluster with a strategic bidding agent. A practical Distributed Coordinated Multi-Agent Bidding (DCMAB) has been proposed and implemented to balance the tradeoff between the competition and cooperation among advertisers. The empirical study on our industry-scaled real-world data has demonstrated the effectiveness of our methods. Our results show cluster-based bidding would largely outperform single-agent and bandit approaches, and the coordinated bidding achieves better overall objectives than purely self-interested bidding agents. |
Tasks | Multi-agent Reinforcement Learning |
Published | 2018-02-27 |
URL | http://arxiv.org/abs/1802.09756v2 |
http://arxiv.org/pdf/1802.09756v2.pdf | |
PWC | https://paperswithcode.com/paper/real-time-bidding-with-multi-agent |
Repo | |
Framework | |
Processing of missing data by neural networks
Title | Processing of missing data by neural networks |
Authors | Marek Smieja, Łukasz Struski, Jacek Tabor, Bartosz Zieliński, Przemysław Spurek |
Abstract | We propose a general, theoretically justified mechanism for processing missing data by neural networks. Our idea is to replace typical neuron’s response in the first hidden layer by its expected value. This approach can be applied for various types of networks at minimal cost in their modification. Moreover, in contrast to recent approaches, it does not require complete data for training. Experimental results performed on different types of architectures show that our method gives better results than typical imputation strategies and other methods dedicated for incomplete data. |
Tasks | Imputation |
Published | 2018-05-18 |
URL | http://arxiv.org/abs/1805.07405v3 |
http://arxiv.org/pdf/1805.07405v3.pdf | |
PWC | https://paperswithcode.com/paper/processing-of-missing-data-by-neural-networks |
Repo | |
Framework | |
Combinatorial Preconditioners for Proximal Algorithms on Graphs
Title | Combinatorial Preconditioners for Proximal Algorithms on Graphs |
Authors | Thomas Möllenhoff, Zhenzhang Ye, Tao Wu, Daniel Cremers |
Abstract | We present a novel preconditioning technique for proximal optimization methods that relies on graph algorithms to construct effective preconditioners. Such combinatorial preconditioners arise from partitioning the graph into forests. We prove that certain decompositions lead to a theoretically optimal condition number. We also show how ideal decompositions can be realized using matroid partitioning and propose efficient greedy variants thereof for large-scale problems. Coupled with specialized solvers for the resulting scaled proximal subproblems, the preconditioned algorithm achieves competitive performance in machine learning and vision applications. |
Tasks | |
Published | 2018-01-16 |
URL | http://arxiv.org/abs/1801.05413v2 |
http://arxiv.org/pdf/1801.05413v2.pdf | |
PWC | https://paperswithcode.com/paper/combinatorial-preconditioners-for-proximal |
Repo | |
Framework | |
CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis
Title | CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis |
Authors | Ankit Shah, Jean Baptiste Lamare, Tuan Nguyen Anh, Alexander Hauptmann |
Abstract | This paper presents a novel dataset for traffic accidents analysis. Our goal is to resolve the lack of public data for research about automatic spatio-temporal annotations for traffic safety in the roads. Through the analysis of the proposed dataset, we observed a significant degradation of object detection in pedestrian category in our dataset, due to the object sizes and complexity of the scenes. To this end, we propose to integrate contextual information into conventional Faster R-CNN using Context Mining (CM) and Augmented Context Mining (ACM) to complement the accuracy for small pedestrian detection. Our experiments indicate a considerable improvement in object detection accuracy: +8.51% for CM and +6.20% for ACM. Finally, we demonstrate the performance of accident forecasting in our dataset using Faster R-CNN and an Accident LSTM architecture. We achieved an average of 1.684 seconds in terms of Time-To-Accident measure with an Average Precision of 47.25%. Our Webpage for the paper is https://goo.gl/cqK2wE |
Tasks | Object Detection, Pedestrian Detection |
Published | 2018-09-16 |
URL | http://arxiv.org/abs/1809.05782v2 |
http://arxiv.org/pdf/1809.05782v2.pdf | |
PWC | https://paperswithcode.com/paper/cadp-a-novel-dataset-for-cctv-traffic-camera |
Repo | |
Framework | |
Unsupervised Hard Example Mining from Videos for Improved Object Detection
Title | Unsupervised Hard Example Mining from Videos for Improved Object Detection |
Authors | SouYoung Jin, Aruni RoyChowdhury, Huaizu Jiang, Ashish Singh, Aditya Prasad, Deep Chakraborty, Erik Learned-Miller |
Abstract | Important gains have recently been obtained in object detection by using training objectives that focus on {\em hard negative} examples, i.e., negative examples that are currently rated as positive or ambiguous by the detector. These examples can strongly influence parameters when the network is trained to correct them. Unfortunately, they are often sparse in the training data, and are expensive to obtain. In this work, we show how large numbers of hard negatives can be obtained {\em automatically} by analyzing the output of a trained detector on video sequences. In particular, detections that are {\em isolated in time}, i.e., that have no associated preceding or following detections, are likely to be hard negatives. We describe simple procedures for mining large numbers of such hard negatives (and also hard {\em positives}) from unlabeled video data. Our experiments show that retraining detectors on these automatically obtained examples often significantly improves performance. We present experiments on multiple architectures and multiple data sets, including face detection, pedestrian detection and other object categories. |
Tasks | Face Detection, Object Detection, Pedestrian Detection |
Published | 2018-08-13 |
URL | http://arxiv.org/abs/1808.04285v1 |
http://arxiv.org/pdf/1808.04285v1.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-hard-example-mining-from-videos |
Repo | |
Framework | |
Real-time Pedestrian Detection Approach with an Efficient Data Communication Bandwidth Strategy
Title | Real-time Pedestrian Detection Approach with an Efficient Data Communication Bandwidth Strategy |
Authors | Mizanur Rahman, Mhafuzul Islam, Jon Calhoun, Mashrur Chowdhury |
Abstract | Vehicle-to-Pedestrian (V2P) communication can significantly improve pedestrian safety at a signalized intersection. It is unlikely that pedestrians will carry a low latency communication enabled device and activate a pedestrian safety application in their hand-held device all the time. Because of this limitation, multiple traffic cameras at the signalized intersection can be used to accurately detect and locate pedestrians using deep learning and broadcast safety alerts related to pedestrians to warn connected and automated vehicles around a signalized intersection. However, unavailability of high-performance computing infrastructure at the roadside and limited network bandwidth between traffic cameras and the computing infrastructure limits the ability of real-time data streaming and processing for pedestrian detection. In this paper, we develop an edge computing based real-time pedestrian detection strategy combining pedestrian detection algorithm using deep learning and an efficient data communication approach to reduce bandwidth requirements while maintaining a high object detection accuracy. We utilize a lossy compression technique on traffic camera data to determine the tradeoff between the reduction of the communication bandwidth requirements and a defined object detection accuracy. The performance of the pedestrian-detection strategy is measured in terms of pedestrian classification accuracy with varying peak signal-to-noise ratios. The analyses reveal that we detect pedestrians by maintaining a defined detection accuracy with a peak signal-to-noise ratio (PSNR) 43 dB while reducing the communication bandwidth from 9.82 Mbits/sec to 0.31 Mbits/sec, a 31x reduction. |
Tasks | Object Detection, Pedestrian Detection |
Published | 2018-08-27 |
URL | http://arxiv.org/abs/1808.09023v3 |
http://arxiv.org/pdf/1808.09023v3.pdf | |
PWC | https://paperswithcode.com/paper/real-time-pedestrian-detection-approach-with |
Repo | |
Framework | |
Gen-Oja: A Two-time-scale approach for Streaming CCA
Title | Gen-Oja: A Two-time-scale approach for Streaming CCA |
Authors | Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan |
Abstract | In this paper, we study the problems of principal Generalized Eigenvector computation and Canonical Correlation Analysis in the stochastic setting. We propose a simple and efficient algorithm, Gen-Oja, for these problems. We prove the global convergence of our algorithm, borrowing ideas from the theory of fast-mixing Markov chains and two-time-scale stochastic approximation, showing that it achieves the optimal rate of convergence. In the process, we develop tools for understanding stochastic processes with Markovian noise which might be of independent interest. |
Tasks | |
Published | 2018-11-20 |
URL | https://arxiv.org/abs/1811.08393v2 |
https://arxiv.org/pdf/1811.08393v2.pdf | |
PWC | https://paperswithcode.com/paper/gen-oja-a-simple-and-efficient-algorithm-for |
Repo | |
Framework | |