检索结果-内蒙古大学图书馆

Domain concretization from examples: addressing missing domain knowledge via robust planning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Sharma, Akshay Medikeri, Piyush Rajesh Zhang, Yu School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States

The assumption of complete domain knowledge is not warranted for robot planning and decision-making in the real world. It could be due to design flaws or arise from domain ramifications or qualifications. In such cases, existing planning and learning algorithms could produce highly undesirable behaviors. This problem is more challenging than partial observability in the sense that the agent is unaware of certain knowledge, in contrast to it being partially observable: the difference between known unknowns and unknown unknowns. In this work, we formulate it as the problem of domain concretization, an inverse problem to domain abstraction. Based on an incomplete domain model provided by the designer and teacher traces from human users, our algorithm searches for a candidate model set under a minimalistic model assumption. It then generates a robust plan with the maximum probability of success under the set of candidate models. In addition to a standard search formulation in the model-space, we propose a sample-based search method and also an online version of it to improve search time. We tested our approach on IPC domains and a simulated robotics domain where incompleteness was introduced by removing domain features from the complete model. Results show that our planning algorithm increases the plan success rate without impacting the cost much. Copyright © 2020, The Authors. All rights reserved.

关键词： Domain Knowledge

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...

Simulation Winter Conference

作者： Antonio Candelieri Giulia Pedrielli Management and Statistics University of Milano-Bicocca Piazza Ateneo Nuovo 1 Milan ITALY School of Computing Informatics & Decision Systems Engineering Arizona State University 699 S Mill Ave Tempe USA

ISBN: (纸本)9781665433129

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.

关键词： Support vector machines Shape Gaussian processes Switches Prediction algorithms Bayes methods Partitioning algorithms

Are we on the same page? Hierarchical explanation generation for planning tasks in human-robot teaming using reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zakershahrak, Mehrdad Ghodratnama, Samira The School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States

Providing explanations is considered an imperative ability for an AI agent in a human-robot teaming framework. The right explanation provides the rationale behind an AI agent's decision-making. However, to maintain the human teammate's cognitive demand to comprehend the provided explanations, prior works have focused on providing explanations in a specific order or intertwining the explanation generation with plan execution. Moreover, these approaches do not consider the degree of details required to share throughout the provided explanations. In this work, we argue that the agent-generated explanations, especially the complex ones, should be abstracted to be aligned with the level of details the human teammate desires to maintain the recipient's cognitive load. Therefore, learning a hierarchical explanations model is a challenging task. Moreover, the agent needs to follow a consistent high-level policy to transfer the learned teammate preferences to a new scenario while lower-level detailed plans are different. Our evaluation confirmed the process of understanding an explanation, especially a complex and detailed explanation, is hierarchical. The human preference that reflected this aspect corresponded exactly to creating and employing abstraction for knowledge assimilation hidden deeper in our cognitive process. We showed that hierarchical explanations achieved better task performance and behavior interpretability while reduced cognitive load. These results shed light on designing explainable agents utilizing reinforcement learning and planning across various domains. © 2020, CC BY.

关键词： Reinforcement learning

Distributing hash families with few rows

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Colbourn, Charles J. Dougherty, Ryan E. Horsley, Daniel Computing Informatics and Decision Systems Engineering Arizona State University P.O. Box 878809 TempeAZ85287 United States School of Mathematical Sciences Monash University Vic3800 Australia

Column replacement techniques for creating covering arrays rely on the construction of perfect and distributing hash families with few rows, having as many columns as possible for a specified number of symbols. To construct distributing hash families in which the number of rows is less than the strength, we examine a method due to Blackburn and extend it in three ways. First, the method is generalized from homogeneous hash families (in which every row has the same number of symbols) to heterogeneous ones. Second, the extension treats distributing hash families, in which only separation into a prescribed number of parts is required, rather than perfect hash families, in which columns must be completely separated. Third, the requirements on one of the main ingredients are relaxed to permit the use of a large class of distributing hash families, which we call fractal. Constructions for fractal perfect and distributing hash families are given, and applications to the construction of perfect hash families of large strength are *** Codes 05B15 Copyright © 2021, The Authors. All rights reserved.

关键词： Fractals

A configurable BNN ASIC using a network of programmable threshold logic standard cells

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wagle, Ankit Khatri, Sunil Vrudhula, Sarma School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States Dept. of Electrical and Computer Engineering Texas A&M University College StationTX United States

This paper presents TULIP, a new architecture for a binary neural network (BNN) that uses an optimal schedule for executing the operations of an arbitrary BNN. It was constructed with the goal of maximizing energy efficiency per classification. At the top-level, TULIP consists of a collection of unique processing elements (TULIP-PEs) that are organized in a SIMD fashion. Each TULIP-PE consists of a small network of binary neurons, and a small amount of local memory per neuron. The unique aspect of the binary neuron is that it is implemented as a mixed-signal circuit that natively performs the inner-product and thresholding operation of an artificial binary neuron. Moreover, the binary neuron, which is implemented as a single CMOS standard cell, is reconfigurable, and with a change in a single parameter, can implement all standard operations involved in a BNN. We present novel algorithms for mapping arbitrary nodes of a BNN onto the TULIP-PEs. TULIP was implemented as an ASIC in TSMC 40nm-LP technology. To provide a fair comparison, a recently reported BNN that employs a conventional MAC-based arithmetic processor was also implemented in the same technology. The results show that TULIP is consistently 3X more energy-efficient than the conventional design, without any penalty in performance, area, or accuracy. © 2021, CC BY.

关键词： Energy efficiency

Adaptive change point monitoring for high-dimensional data

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Teng Wang, Runmin Yan, Hao Shao, Xiaofeng Department of Statistics University of Illinois at Urbana-Champaign United States Department of Statistical Science Southern Methodist University United States School of Computing Informatics & Decision Systems Engineering Arizona State University United States

In this paper, we propose a class of monitoring statistics for a mean shift in a sequence of high-dimensional observations. Inspired by the recent U-statistic based retrospective tests developed by Wang et al. (2019) and Zhang et al. (2020), we advance the U-statistic based approach to the sequential monitoring problem by developing a new adaptive monitoring procedure that can detect both dense and sparse changes in real time. Unlike Wang et al. (2019) and Zhang et al. (2020), where self-normalization was used in their tests, we instead introduce a class of estimators for q-norm of the covariance matrix and prove their ratio consistency. To facilitate fast computation, we further develop recursive algorithms to improve the computational efficiency of the monitoring procedure. The advantage of the proposed methodology is demonstrated via simulation studies and real data illustrations. © 2021, CC BY.

关键词： Monitoring

A survey of system architectures and techniques for FPGA virtualization

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Quraishi, Masudul Hassan Tavakoli, Erfan Bank Ren, Fengbo School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States

FPGA accelerators are gaining increasing attention in both cloud and edge computing because of their hardware flexibility, high computational throughput, and low power consumption. However, the design flow of FPGAs often requires specific knowledge of the underlying hardware, which hinders the wide adoption of FPGAs by application developers. Therefore, the virtualization of FPGAs becomes extremely important to create a useful abstraction of the hardware suitable for application developers. Such abstraction also enables the sharing of FPGA resources among multiple users and accelerator applications, which is important because, traditionally, FPGAs have been mostly used in single-user, single-embedded-application scenarios. There are many works in the field of FPGA virtualization covering different aspects and targeting different application areas. In this survey, we review the system architectures used in the literature for FPGA virtualization. In addition, we identify the primary objectives of FPGA virtualization, based on which we summarize the techniques for realizing FPGA virtualization. This survey helps researchers to efficiently learn about FPGA virtualization research by providing a comprehensive review of the existing literature. © 2020, CC BY-NC-ND.

关键词： Field programmable gate arrays (FPGA)

Randomly Weighted, Untrained Neural Tensor Networks Achieve Greater Relational Expressiveness

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hong, Jinyung Pavlic, Theodore P. School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States

Neural Tensor Networks (NTNs), which are structured to encode the degree of relationship among pairs of entities, are used in Logic Tensor Networks (LTNs) to facilitate Statistical Relational Learning (SRL) in first-order logic. In this paper, we propose Randomly Weighted Tensor Networks (RWTNs), which incorporate randomly drawn, untrained tensors into an NTN encoder network with a trained decoder network. We show that RWTNs meet or surpass the performance of traditionally trained LTNs for Semantic Image Interpretation (SII) tasks that have been used as a representative example of how LTNs utilize reasoning over first-order logic to exceed the performance of solely data-driven methods. We demonstrate that RWTNs outperform LTNs for the detection of the relevant part-of relations between objects, and we show that RWTNs can achieve similar performance as LTNs for object classification while using fewer parameters for learning. Copyright © 2020, The Authors. All rights reserved.

关键词： Tensors

Data-driven probabilistic scenarios simulation model and visualization for hurricane impact

学校读者我要写书评

暂无评论

Data-driven probabilistic scenarios simulation model and vis...

2019 Institute of Industrial and systems Engineers Annual Conference and Expo, IISE 2019

作者： Mirchandani, Pitu Ayu, Ketut Gita Maciejewski, Ross School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States

ISBN: (纸本)9781713814092

The 2017 Atlantic hurricane season was horrendous and became one of the costliest hurricanes in the United States. Understanding its highly erratic movement with changing speed direction and precipitation, access to storm forecast models is essential for local and state officials and emergency responders as these models provide critical storm information (e.g., possible storm trajectories and potential impacts) that acts as basis in decision making under uncertainty for preparedness and response operations. Unfortunately, access to these sophisticated models is limited or come at substantial costs. We developed a data-driven simulation model that takes possible hurricane trajectories, referred here as scenarios, as inputs, coupled with publicly available rolling horizon forecasts of overall weather while incorporating hurricane characteristics (wind speeds, precipitation and storm surges) to generate spatial-temporal storm predicted impacts at scenario level. The model also estimates the scenario probabilities, not directly provided in the public forecasts. The computational results on hurricane Irma case study illustrates the scenario-level storm impacts are generated with fairly accurately within reasonably short runtimes. In the next phase of research not reported here, these predictions impacts can drive models for disruptions in transportation, supply chains and power grids © 2019 IISE Annual Conference and Expo 2019. All rights reserved.

关键词： Hurricanes