检索结果-内蒙古大学图书馆

SUBJECTIVE EQUILIBRIA UNDER BELIEFS OF EXOGENOUS UNCERTAINTY: LINEAR QUADRATIC CASE

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Arslan, Gürdal Yüksel, Serdar Department of Electrical and Computer Engineering University of Hawaii at Manoa 2540 Dole Street HonoluluHI96822 United States Department of Mathematics and Statistics Queen’s University KingstonONK7L 3N6 Canada

We consider a stochastic dynamic game where players have their own linear state dynamics and quadratic cost functions. Players are coupled through some environment variables, generated by another linear system driven by the states and decisions of all players. Each player observes his own states realized up to the current time as well as the past realizations of his own decisions and the environment variables. Each player (incorrectly) believes that the environment variables are generated by an independent exogenous stochastic process. In this setup, we study the notion of "subjective equilibrium under beliefs of exogenous uncertainty (SEBEU)" introduced in our recent work [3]. At an SEBEU, each player’s strategy is optimal with respect to his subjective belief;moreover, the objective probability distribution of the environment variables is consistent with players’ subjective beliefs. We construct an SEBEU in pure strategies, where each player strategy is an affine function of his own state and his estimate of the system state. © 2024, CC BY-NC-ND.

关键词： Game theory

Structure Preserving PINN for Solving Time Dependent PDEs with Periodic Boundary

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hao, Baoli Braga-Neto, Ulisses Liu, Chun Wang, Lifan Zhong, Ming Department of Applied Mathematics Illinois Institute of Technology ChicagoIL United States Department of Electrical and Computing Engineering Texas A&M University College StationTX United States Department of Physics and Astrophysics Texas A&M University College StationTX United States

We present a structure preserving PINN for solving a series of time dependent PDEs with periodic boundary. Our method can incorporate the periodic boundary condition as the natural output of any deep neural net, hence significantly improving the training accuracy of baseline PINN. Together with mini-batching and other PINN variants (SA-PINN, RBA-PINN, etc.), our structure preserving PINN can even handle stiff PDEs for modeling a wide range of convection-diffusion and reaction-diffusion processes. We demonstrate the effectiveness of our PINNs on various PDEs from Allen Cahn, Gray Scott to nonlinear Schrödinger. © 2024, CC BY.

关键词： Deep neural networks

Clinically adaptable machine learning model to identify early appreciable features of diabetes

学校读者我要写书评

暂无评论

Intelligent Medicine 2024年第1期4卷 22-32页

作者： Nurjahan Nipa Mahmudul Hasan Riyad Shahriare Satu Walliullah Koushik Chandra Howlader Mohammad Ali Moni Department of Information and Communication Technology Bangabandhu Sheikh Mujibur Rahman Digital UniversityBangladeshKaliakairGazipur1750 Bangladesh Department of Applied Mathematics Noakhali Science and Technology UniversityNoakhali3814Bangladesh Department of Management Information Systems Noakhali Science and Technology UniversityNoakhali3814Bangladesh Department of Computer Science and Telecommunication Engineering Noakhali Science and Technology UniversityNoakhali3814Bangladesh Department of Computer Science North Dakota State UniversityFargo58105NDUnited States School of Health and Rehabilitation Sciences Faculty of Health and Behavioural SciencesThe University of QueenslandSt LuciaQLD 4072Australia

Objective Diabetes mellitus is a serious disease where the body of affected patients are failed to produce enough insulin that causes an abnormality of blood *** disease happens for a number of reasons including modern lifestyle,lethargic attitude,unhealthy food consumption,family history,age,overweight,*** aim of this study was to propose a machine learning based prediction model that detected diabetes at the *** In this work,we collected 520 patients records from the University of California,Irvine(UCI)machine learning repository of Sylhet Diabetes Hospital,***,a similar questionnaire of that hospital was followed and assembled 558 patients records from all over Bangladesh through this ***,we accumulated patient records of these two *** the next step,these datasets were cleaned and applied thirty five state-of-arts classifiers such as logistic regression(LR),K nearest neighbors(KNN),support vector classifier(SVC),Nave Byes(NB),decision tree(DT),random forest(RF),stochastic gradient descent(SGD),Perceptron,AdaBoost,XGBoost,passive aggressive classifier(PAC),ridge classifier(RC),Nu-support vector classifier(NuSVC),linear support vector classifier(LSVC),calibrated classifier CV(CCCV),nearest centroid(NC),Gaussian process classifier(GPC),multinomial NB(MNB),complement NB,Bernoulli NB(BNB),categorical NB,Bagging,extra tree(ET),gradiant boosting classifier(GBC),Hist gradiant boosting classifier(HGBC),one vs rest classifier(OVsRC),multi-layer perceptron(MLP),label propagation(LP),label spreading(LS),stacking,ridge classifier CV(RCCV),logistic regression CV(LRCV),linear discriminant analysis(LDA),quadratic discriminant analysis(QDA),and light gradient boosting machine(LGBM)to explore best stable predictive *** performance of the classifiers has been measured using five metrics such as accuracy,precision,recall,F1-score,and area under the receiver operating ***,these outcomes were interpret

关键词： Diabetes Early features Machine learning Classification

Exponential Quantum Advantage for Pathfinding in Regular Sunflower Graphs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Jianqiang Tong, Yu Department of Computer Science Pennsylvania State University State CollegePA United States Institute for Quantum Information and Matter California Institute of Technology PasadenaCA United States Department of Mathematics Duke University DurhamNC United States Department of Electrical and Computer Engineering Duke University DurhamNC United States

Finding problems that allow for superpolynomial quantum speedup is one of the most important tasks in quantum computation. A key challenge is identifying problem structures that can only be exploited by quantum mechanics. In this paper, we find a class of graphs that allows for exponential quantum-classical separation for the pathfinding problem with the adjacency list oracle, and this class of graphs is named regular sunflower graphs. We prove that, with high probability, a regular sunflower graph of degree at least 7 is a mild expander graph, that is, the spectral gap of the graph Laplacian is at least inverse polylogarithmic in the graph size. We provide an efficient quantum algorithm to find an s-t path in the regular sunflower graph while any classical algorithm takes exponential time. This quantum advantage is achieved by efficiently preparing a 0-eigenstate of the adjacency matrix of the regular sunflower graph as a quantum superposition state over the vertices, and this quantum state contains enough information to help us efficiently find an s-t path in the regular sunflower graph. Because the security of an isogeny-based cryptosystem depends on the hardness of finding an s-t path in an expander graph [CLG09], a quantum speedup of the pathfinding problem on an expander graph is of significance. Our result represents a step towards this goal as the first provable exponential speedup for pathfinding in a mild expander graph. © 2024, CC BY.

关键词： Quantum theory

Best Arm Identification with Minimal Regret

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Junwen Tan, Vincent Y.F. Jin, Tianyuan Institute of Operations Research and Analytics National University of Singapore 117602 Singapore Department of Mathematics Department of Electrical and Computer Engineering Institute of Operations Research and Analytics National University of Singapore 119076 Singapore School of Computing National University of Singapore 117417 Singapore

Motivated by real-world applications that necessitate responsible experimentation, we introduce the problem of best arm identification (BAI) with minimal regret. This innovative variant of the multi-armed bandit problem elegantly amalgamates two of its most ubiquitous objectives: regret minimization and BAI. More precisely, the agent’s goal is to identify the best arm with a prescribed confidence level δ, while minimizing the cumulative regret up to the stopping time. Focusing on single-parameter exponential families of distributions, we leverage information-theoretic techniques to establish an instance-dependent lower bound on the expected cumulative regret. Moreover, we present an intriguing impossibility result that underscores the tension between cumulative regret and sample complexity in fixed-confidence BAI. Complementarily, we design and analyze the Double KL-UCB algorithm, which achieves asymptotic optimality as the confidence level tends to zero. Notably, this algorithm employs two distinct confidence bounds to guide arm selection in a randomized manner. Our findings elucidate a fresh perspective on the inherent connections between regret minimization and BAI. © 2024, CC BY.

关键词： Clutter (information theory)

Utilization of Encoding, Early Stopping, Hyper Parameter Tuning, and Machine Learning Models for Bank Fraud Detection

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2023年

作者： Islam, Md Aminul Chowdhury, Saumik Nag, Anindya Mumtaj, Nahi Ghosh, Arjan Fahim, S.M. Firoz Ahmed School of Engineering Computing and Mathematics Oxford Brookes University Oxford United Kingdom Computer Science & Engineering Dscipline Khulna University Khulna9208 Bangladesh Department of Computer Science & Engineering Jashore University of Science & Technology Jashore7408 Bangladesh Department of Computer Science & Engineering American International University Dhaka Bangladesh Bangladesh BSRM School of Engineering Electrical and Electronics BRAC University Dhaka Bangladesh

An effective fraud detection system must protect millions of clients for a secure banking system, which can be achieved using machine learning and AI. In this article, we have applied four supervised machine learning models: k-nearest neighbors (KNN), random forest (RF), decision tree, and logistic regression (LR) algorithm to detect bank fraud for a synthetic dataset having 1,00,000 rows and 32 columns. Adequate preprocessing, decoding, rigorous feature engineering, validation, performance evaluation, and explanation have allowed the readers to understand the whole study. Though the algorithms' accuracy is similar, logistic regression shows a higher accuracy of 0.98921 for label encoding, which is not prescribed. Still, a significant AUC of 95% has been achieved in XGBoost and LGBM. Further application of this study can be done in real-life cases of banks, insurance, and finance institutions. © 2023, CC BY.

关键词： Decision trees

Deep Inverse Design for High-Level Synthesis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chang, Ping Adegbija, Tosiron Liao, Yuchao Talarico, Claudio Li, Ao Roveda, Janet Department of Electrical & Computer Engineering The University of Arizona TucsonAZ United States Bio5 Institute The University of Arizona TucsonAZ United States Department of Biomedical Engineering The University of Arizona TucsonAZ United States School of Engineering & Applied Science Gonzaga University SpokaneWA United States

High-level synthesis (HLS) has significantly advanced the automation of digital circuits design, yet the need for expertise and time in pragma tuning remains challenging. Existing solutions for the design space exploration (DSE) adopt either heuristic methods, lacking essential information for further optimization potential, or predictive models, missing sufficient generalization due to the time-consuming nature of HLS and the exponential growth of the design space. To address these challenges, we propose Deep Inverse Design for HLS (DID4HLS), a novel approach that integrates graph neural networks and generative models. DID4HLS iteratively optimizes hardware designs aimed at compute-intensive algorithms by learning conditional distributions of design features from post-HLS data. Compared to four state-of-the-art DSE baselines, our method achieved an average improvement of 42.8% on average distance to reference set (ADRS) compared to the best-performing baselines across six benchmarks, while demonstrating high robustness and efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

An alternative construction for the district institutional development index (IDID) of Bogota using DEA-CCR 7

学校读者我要写书评

暂无评论

An alternative construction for the district institutional d...

7th Congreso Internacional de Innovacion y Tendencias en Ingenieria, CONIITI 2021

作者： Rodriguez, Norvey Barrero, Juan Rincon-Yanez, Diego Universidad Catolica de Colombia Basic Sciences Department Bogotá Colombia Universidad Catolica de Colombia Faculty of Engineering Bogotá Colombia University of Salerno Department of Information and Electrical Engineering and Applied Mathematics SA Fisciano84084 Italy

ISBN: (纸本)9781665402217

The Institutional District Development Index (IDID) created in 2011 is an instrument for the annual evaluation of the development plans of public entities in the city of Bogotá. In this research, the construction of the indices was carried out using data envelopment analysis (DEA) with a CCR frontier oriented to the inputs as an alternative model to the methodology proposed by the District Office of Institutional Development in 2016. Taking the District data from 2015, the indicators were calculated for the 42 district entities, and their results were organized and classified from highest to lowest. Global sensitivity analysis and uncertainty analysis were performed using the Monte Carlo simulation technique to validate the reliability and stability of the set of indicators. The results of this work were compared with the 2016 calculated indicators, using the District methodology for the same data from 2015. One of these work results is a discrepancy between the set of IDID-DEA indicators and the set of district IDID indicators for each entity. The difference lies in the District's methodology;it uses categorical scales and simple averages to consider each entity individually, where low values are observed, and the entities are being very strict without considering other variables or dynamics of the city. On the other hand, with the DEA methodology, the advantage is that the set of indicators arises from considering all the entities simultaneously, and the classification is generated by comparing the efficiency between them. © 2021 IEEE.

关键词： Uncertainty analysis

Comprehensive Training and Evaluation on Deep Reinforcement Learning for Automated Driving in Various Simulated Driving Maneuvers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dong, Yongqi Datema, Tobias Wassenaar, Vincent van de Weg, Joris Kopar, Cahit Tolga Suleman, Harim The Department of Transport and Planning Delft University of Technology Delft2628 CN Netherlands The Faculty of Electrical Engineering Mathematics & Computer Science Delft University of Technology Delft2628 CN Netherlands

Developing and testing automated driving models in the real world might be challenging and even dangerous, while simulation can help with this, especially for challenging maneuvers. Deep reinforcement learning (DRL) has the potential to tackle complex decision-making and controlling tasks through learning and interacting with the environment, thus it is suitable for developing automated driving while not being explored in detail yet. This study carried out a comprehensive study by implementing, evaluating, and comparing the two DRL algorithms, Deep Q-networks (DQN) and Trust Region Policy Optimization (TRPO), for training automated driving on the highway-env simulation platform. Effective and customized reward functions were developed and the implemented algorithms were evaluated in terms of onlane accuracy (how well the car drives on the road within the lane), efficiency (how fast the car drives), safety (how likely the car is to crash into obstacles), and comfort (how much the car makes jerks, e.g., suddenly accelerates or brakes). Results show that the TRPO-based models with modified reward functions delivered the best performance in most cases. Furthermore, to train a uniform driving model that can tackle various driving maneuvers besides the specific ones, this study expanded the highway-env and developed an extra customized training environment, namely, ComplexRoads, integrating various driving maneuvers and multiple road scenarios together. Models trained on the designed ComplexRoads environment can adapt well to other driving maneuvers with promising overall performance. Lastly, several functionalities were added to the highway-env to implement this work. The codes are open on GitHub at https://***/alaineman/drlcarsim-paper. © 2023, CC BY.

关键词： Simulation platform