检索结果-内蒙古大学图书馆

Template-based Question Answering analysis on the LC-QuAD2.0 Dataset

学校读者我要写书评

暂无评论

Template-based Question Answering analysis on the LC-QuAD2.0...

International Conference on Semantic computing

作者： Akshay Kumar Dileep Anurag Mishra Ria Mehta Siddharth Uppal Jaydeep Chakraborty Srividya K. Bansal School of Computing Informatics Decision Systems Engineering (CIDSE) Arizona State University Mesa Arizona USA

ISBN: (数字)9781728188997

ISBN: (纸本)9781728189000

In recent years, template-based question answer has picked up steam as a solution for evaluating RDF triples. Once we delve into the domain of template-based question answering, two important questions arise which are, the size of the dataset used as the knowledge base and the process of training used on that knowledge base. Previous studies attempted this problem with the LC-QuAD dataset and recursive neural network for training. This paper studies the same problem with a larger and newer benchmark dataset called LC-QuAD 2.0 and training using different machine learning models. The objective of this paper is to provide a comparative study using the newer LC-QuAD 2.0 dataset that has an updated schema and 30,000 question-answer pairs. Our study will focus on using and comparing two Machine Learning models and 3 different pre-processing techniques to generate results and identify the best model for this problem.

关键词： Training Computational modeling Knowledge based systems Semantics Machine learning Knowledge discovery Resource description framework

Distributed asynchronous policy iteration for sequential zero-sum games and minimax control

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bertsekas, Dimitri School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States

We introduce a contractive abstract dynamic programming framework and related policy iteration algorithms, specifically designed for sequential zero-sum games and minimax problems with a general structure. Aside from greater generality, the advantage of our algorithms over alternatives is that they resolve some long-standing convergence difficulties of the "natural" policy iteration algorithm, which have been known since the Pollatschek and Avi-Itzhak method [PoA69] for finite-state Markov games. Mathematically, this "natural" algorithm is a form of Newton's method for solving Bellman's equation, but Newton's method, contrary to the case of single-player DP problems, is not globally convergent in the case of a minimax problem, because the Bellman operator may have components that are neither convex nor concave. Our algorithms address this difficulty by introducing alternating player choices, and by using a policy-dependent mapping with a uniform sup-norm contraction property, similar to earlier works by Bertsekas and Yu [BeY10], [BeY12], [YuB13]. Moreover, our algorithms allow a convergent and highly parallelizable implementation, which is based on state space partitioning, and distributed asynchronous policy evaluation and policy improvement operations within each set of the partition. Our framework is also suitable for the use of reinforcement learning methods based on aggregation, which may be useful for large-scale problem instances. © 2021, CC BY-NC-ND.

关键词： Dynamic programming

Generating active explicable plans in human-robot teaming

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hanni, Akkamahadevi Zhang, Yu School of Computing Informatics Decision Systems Engineering Arizona State University TempeAZ United States

Intelligent robots are redefining a multitude of critical domains but are still far from being fully capable of assisting human peers in day-to-day tasks. An important requirement of collaboration is for each teammate to maintain and respect an understanding of the others’ expectations of itself. Lack of which may lead to serious issues such as loose coordination between teammates, reduced situation awareness, and ultimately teaming failures. Hence, it is important for robots to behave explicably by meeting the human’s expectations. One of the challenges here is that the expectations of the human are often hidden and can change dynamically as the human interacts with the robot. However, existing approaches to generating explicable plans often assume that the human’s expectations are known and static. In this paper, we propose the idea of active explicable planning to relax this assumption. We apply a Bayesian approach to model and predict dynamic human belief and expectations to make explicable planning more anticipatory. We hypothesize that active explicable plans can be more efficient and explicable at the same time, when compared to explicable plans generated by the existing methods. In our experimental evaluation, we verify that our approach generates more efficient explicable plans while successfully capturing the dynamic belief change of the human teammate. Copyright © 2021, The Authors. All rights reserved.

关键词： Intelligent robots

Treed-Gaussian Processes with Support Vector Machines as Nodes for Nonstationary Bayesian Optimization

学校读者我要写书评

暂无评论

Treed-Gaussian Processes with Support Vector Machines as Nod...

2021 Winter Simulation Conference, WSC 2021

作者： Candelieri, Antonio Pedrielli, Giulia University of Milano-Bicocca Management and Statistics Department of Economics Piazza Ateneo Nuovo 1 Milan Italy School of Computing Informatics and Decision Systems Engineering Arizona State University 699 S Mill Ave Tempe United States

ISBN: (纸本)9781665433112

A large family of black box methods rely on surrogates of the unknown, possibly non linear non convex reward function. While it is common to assume stationarity of the reward, many real-world problems satisfy this assumption only locally, hindering the spread application of such methods. This paper proposes a novel nonstationary regression model combining decision Trees and Support Vector Machine (SVM) classification for a hierarchical non-axis-aligned partition of the input space. Gaussian Process (GP) regression is performed within each identified subregion. The resulting nonstationary regression model is the Treed Gaussian process with Support Vector Machine (SVMTGP), and we investigate the sampling efficiency from using our a model within a Bayesian optimization (BO) context. Empirically, we show how the resulting algorithm, SVMTGP-BO never underperforms BO when this is applied to an homogeneous Gaussian process, while it shows always better performance compared to the homogeneous model with nonlinear functions with complex landscapes. © 2021 IEEE.

关键词： Support vector machines

How Work From Home Has Affected the Occupant’s Well-Being in the Residential Built Environment: An International Survey Amid the Covid-19 Pandemic

学校读者我要写书评

暂无评论

Journal of Engineering for Sustainable Buildings and Cities 2021年第4期2卷 041003页

作者： Pang, Zhihong Becerik-Gerber, Burcin Hoque, Simi O’Neill, Zheng Pedrielli, Giulia Wen, Jin Wu, Teresa J. Mike Walker ‘66 Department of Mechanical Engineering Texas A&M University College Station 77840-1660 TX United States Sonny Astani Department of Civil and Environmental Engineering University of Southern California Los Angeles 90089 CA United States Department of Civil Architectural and Environmental Engineering Drexel University Philadelphia 19104 PA United States School of Computing Informatics and Decision Systems Engineering Arizona State University Tempe 85281 AZ United States School of Computing Informatics and Decision Systems Engineering Arizona State University Tempe 85287-5906 AZ United States

This paper presents the results from an international survey that investigated the impacts of the built environment on occupant well-being during the corona virus disease 2019 (COVID-19) pandemic when most professionals were forced to work from home (WFH). The survey was comprised of 81 questions focusing on the respondent’s profiles, residences, home indoor environmental quality, health, and home working experiences. A total of 1460 responses were collected from 35 countries, and 1137 of them were considered complete for the analysis. The results suggest that home spatial layout has a significant impact on occupant well-being during WFH since home-life distractions and noises due to the lack of a personal workspace are likely to prevent productive work. Lack of scenic views, inadequate daylighting, and poor acoustics were also reported to be detrimental to occupant productivity and the general WFH experience. It is also revealed from this survey that temperature, relative humidity, and indoor air quality generally have higher satisfaction ratios compared with the indoor lighting and acoustic conditions, and the home layout. Hence, home design for lighting, acoustics, and layout should also receive greater attention in the future. Copyright © 2021 by ASME.

关键词： building built environment COVID-19 indoor environmental quality international survey occupant behavior occupant productivity occupant well-being occupant-centric design and operation

Learning Whole-Body Human-Robot Haptic Interaction in Social Contexts

学校读者我要写书评

暂无评论

Learning Whole-Body Human-Robot Haptic Interaction in Social...

2020 IEEE International Conference on Robotics and Automation, ICRA 2020

作者： Campbell, Joseph Yamane, Katsu School of Computing Informatics and Decision Systems Engineering Arizona State University United States Honda Research Institute United States

ISBN: (纸本)9781728173955

This paper presents a learning-from-demonstration (LfD) framework for teaching human-robot social interactions that involve whole-body haptic interaction, i.e. direct human-robot contact over the full robot body. The performance of existing LfD frameworks suffers in such interactions due to the high dimensionality and spatiotemporal sparsity of the demonstration data. We show that by leveraging this sparsity, we can reduce the data dimensionality without incurring a significant accuracy penalty, and introduce three strategies for doing so. By combining these techniques with an LfD framework for learning multimodal human-robot interactions, we can model the spatiotemporal relationship between the tactile and kinesthetic information during whole-body haptic interactions. Using a teleoperated bimanual robot equipped with 61 force sensors, we experimentally demonstrate that a model trained with 121 sample hugs from 4 participants generalizes well to unseen inputs and human partners. © 2020 IEEE.

关键词： Human robot interaction

Reliability analysis for dependent competing failure processes with two-stage degradation and external shocks 30th

学校读者我要写书评

暂无评论

Reliability analysis for dependent competing failure process...

30th European Safety and Reliability Conference, ESREL 2020 and 15th Probabilistic Safety Assessment and Management Conference, PSAM 2020

作者： Wang, Yukun Fang, Guanqi Pan, Rong School of Economics and Management Tianjin Chengjian University China School of Computing Informatics and Decision Systems Engineering Arizona State University United States

ISBN: (纸本)9789811485930

This article proposes a reliability model for systems subject to dependent degradation and external shocks. The dependence between degradation and external shocks is considered as follows. When the system is working but the degradation level reaches a critical threshold, the degradation rate increases in a stochastic sense. Meanwhile, the system becomes more vulnerable to external shocks due to accumulated degradation. An extended degradation-threshold-shock (DTS) model is developed to describe these two competing but dependent failure processes. The continuous degradation path is monotone and modeled by a two-stage inverse Gaussian (IG) process with random effects to account for the unit-specific heterogeneity across systems. External shocks arrive at the system following a doubly stochastic Poisson process (DSPP) with stochastic increasing intensity which depends on the degradation level. Integrating the degradation-based and shock-based failure processes, the system reliability function is derived. Afterwards, a numerical example is presented to illustrate the applicability of the developed reliability model, along with sensitivity analysis to examine the effect of several parameters on the reliability performance. The proposed reliability model is supposed to be applied directly or customized for other complex systems that experience dependent competing failure processes. © ESREL2020-PSAM15 Organizers.

关键词： Degradation

Not all users are the same: Providing personalized explanations for sequential decision making problems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Soni, Utkarsh Sreedharan, Sarath Kambhampati, Subbarao School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States

There is a growing interest in designing autonomous agents that can work alongside humans. Such agents will undoubtedly be expected to explain their behavior and decisions. While generating explanations is an actively researched topic, most works tend to focus on methods that generate explanations that are one size fits all. As in the specifics of the usermodel are completely ignored. The handful of works that look at tailoring their explanation to the user's background rely on having specific models of the users (either analytic models or learned labeling models). The goal of this work is thus to propose an end-to-end adaptive explanation generation system that begins by learning the different types of users that the agent could interact with. Then during the interaction with the target user, it is tasked with identifying the type on the fly and adjust its explanations accordingly. The former is achieved by a data-driven clustering approach while for the latter, we compile our explanation generation problem into a POMDP. We demonstrate the usefulness of our system on two domains using state-of-the-art POMDP solvers. We also report the results of a user study that investigates the benefits of providing personalized explanations in a human-robot interaction setting. Copyright © 2021, The Authors. All rights reserved.

关键词： Human robot interaction

How robust are model rankings: A leaderboard customization approach for equitable evaluation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mishra, Swaroop Arunkumar, Anjana School of Computing Informatics Decision Systems Engineering Arizona State University TempeAZ85281 United States

Models that top leaderboards often perform unsatisfactorily when deployed in real world applications;this has necessitated rigorous and expensive pre-deployment model testing. A hitherto unexplored facet of model performance is: Are our leaderboards doing equitable evaluation? In this paper, we introduce a task-agnostic method to probe leaderboards by weighting samples based on their ‘difficulty’ level. We find that leaderboards can be adversarially attacked and top performing models may not always be the best models. We subsequently propose alternate evaluation metrics. Our experiments on 10 models show changes in model ranking and an overall reduction in previously reported performance– thus rectifying the overestimation of AI systems’ capabilities. Inspired by behavioral testing principles, we further develop a prototype of a visual analytics tool that enables leaderboard revamping through customization, based on an end user’s focus area. This helps users analyze models’ strengths and weaknesses, and guides them in the selection of a model best suited for their application scenario. In a user study, members of various commercial product development teams, covering 5 focus areas, find that our prototype reduces pre-deployment development and testing effort by 41 % on average. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning