检索结果-内蒙古大学图书馆

Annotative Software Product Line Analysis Using Variability-Aware Datalog

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2023年第3期49卷 1323-1341页

作者： Shahin, Ramy Akhundov, Murad Chechik, Marsha Univ Toronto Toronto ON M5S 1A1 Canada

Applying program analyses to Software Product Lines (SPLs) has been a fundamental research problem at the intersection of Product Line Engineering and software analysis. Different attempts have been made to "lift " particular product-level analyses to run on the entire product line. In this paper, we tackle the class of Datalog-based analyses (e.g., pointer and taint analyses), study the theoretical aspects of lifting Datalog inference, and implement a lifted inference algorithm inside the Souffle Datalog engine. We evaluate our implementation on a set of Java and C-language benchmark annotative software product lines. We show significant savings in processing time and fact database size (billions of times faster on one of the benchmarks) compared to brute-force analysis of each product individually.

关键词： inference algorithms Engines Codes Software product lines Software Databases Color datalog program analysis pointer analysis lifting variability doop Souffle

来源：评论

学校读者我要写书评

暂无评论

Exploration With Task Information for Meta Reinforcement Learning

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第8期34卷 4033-4046页

作者： Jiang, Peng Song, Shiji Huang, Gao Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Beijing Acad Artificial Intelligence Beijing 100084 Peoples R China

Meta reinforcement learning (meta-RL) is a promising technique for fast task adaptation by leveraging prior knowledge from previous tasks. Recently, context-based meta-RL has been proposed to improve data efficiency by applying a principled framework, dividing the learning procedure into task inference and task execution. However, the task information is not adequately leveraged in this approach, thus leading to inefficient exploration. To address this problem, we propose a novel context-based meta-RL framework with an improved exploration mechanism. For the existing exploration and execution problem in context-based meta-RL, we propose a novel objective that employs two exploration terms to encourage better exploration in action and task embedding space, respectively. The first term pushes for improving the diversity of task inference, while the second term, named action information, works as sharing or hiding task information in different exploration stages. We divide the meta-training procedure into task-independent exploration and task-relevant exploration stages according to the utilization of action information. By decoupling task inference and task execution and proposing the respective optimization objectives in the two exploration stages, we can efficiently learn policy and task inference networks. We compare our algorithm with several popular meta-RL methods on MuJoco benchmarks with both dense and sparse reward settings. The empirical results show that our method significantly outperforms baselines on the benchmarks in terms of sample efficiency and task performance.

关键词： Task analysis Optimization Reinforcement learning Mutual information Entropy Context modeling inference algorithms Exploration meta reinforcement learning (meta-RL) mutual information task information

来源：评论

学校读者我要写书评

暂无评论

Diffusion Bayesian Decorrelation algorithms Over Networks

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2023年 71卷 571-586页

作者： Huang, Fuyi Zhang, Sheng Zhang, Jiashu Chen, Hongyang Sayed, Ali H. Guangxi Univ Sch Comp Elect & Informat Guangxi Key Lab Multimedia Commun & Network Techno Nanning 530004 Peoples R China Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 611756 Peoples R China Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 611756 Peoples R China Res Ctr Graph Comp Zhejiang Lab Hangzhou 311121 Peoples R China Ecole Polytech Federalede Lausanne Sch Engn CH-1015 Lausanne Switzerland

The convergence rate of the diffusion normalized least mean squares (NLMS) algorithm can be speeded up by decorrelation of signals. However, the diffusion decorrelation NLMS algorithm confronts the conflicting requirements of fast convergence rate and small steady-state error. To address the issue, this paper proposes a family of diffusion Bayesian decorrelation least mean squares (DBDLMS) algorithms based on decorrelated observation models. Firstly, the weight update equations of the proposed DBDLMS algorithms are obtained by performing Bayesian inference over the decorrelated observation models, with variable step-sizes emerging naturally to help address the conflicting requirement. Secondly, the update equations of the decorrelation coefficient vectors are inferred from the Bayesian perspective, with the variable step-sizes emerging again. Subsequently, the performance analysis of the proposed DBDLMS algorithms is carried out. Moreover, a simple and effective approach is derived to estimate the free parameters for the proposed DBDLMS algorithms. Finally, the learning performance of the proposed algorithms are verified by Monte Carlo simulations.

关键词： Decorrelation Signal processing algorithms Bayes methods Estimation Convergence inference algorithms Steady-state Adaptive networks decorrelation diffusion strategy distributed processing least mean squares

来源：评论

学校读者我要写书评

暂无评论

Ensemble Classification With Noisy Real-Valued Base Functions

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2023年第4期41卷 1067-1080页

作者： Ben-Hur, Yuval Goren, Asaf Klang, Da-El Kim, Yongjune Cassuto, Yuval Technion Israel Inst Technol Dept Elect & Comp Engn IL-3200003 Haifa Israel Pohang Univ Sci & Technol POSTECH Dept Elect Engn Pohang 37673 South Korea Yonsei Univ Inst Convergence Res & Educ Adv Technol Seoul 03722 South Korea

In data-intensive applications, it is advantageous to perform partial processing close to the data, and communicate intermediate results to a central processor, instead of the data itself. When the communication or computation medium is noisy, the resulting degradation in computation quality at the central processor must be mitigated. We study this problem for the setup of binary classification performed by an ensemble of base functions communicating real-valued confidence levels. We propose a noise-mitigation solution that optimizes the transmission gains and aggregation coefficients of the base functions. Toward that, we formulate a post-training gradient-based optimization algorithm that minimizes the error probability given the training dataset and the noise parameters. We further derive lower and upper bounds on the optimized error probability, and show empirical results that demonstrate the enhanced performance achieved by our approach on real data.

关键词： Noise measurement Training Classification algorithms Optimization Reliability Performance evaluation Hardware Machine learning classification algorithms Index Terms boosting inference algorithms distributed computing Gaussian noise

来源：评论

学校读者我要写书评

暂无评论

Extending Group Role Assignment With Cooperation and Conflict Factors via KD45 Logic

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2023年第1期10卷 178-191页

作者： Jiang, Qian Zhu, Haibin Qiao, Yan Liu, Dongning Huang, Baoying Macau Univ Sci & Technol Inst Syst Engn Macau 999078 Peoples R China Macau Univ Sci & Technol Collaborat Lab Intelligent Sci & Syst Macau 999078 Peoples R China Nipissing Univ Collaborat Syst Lab CoSys Lab North Bay ON P1B 8L7 Canada Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou 510006 Guangdong Peoples R China

Group role assignment with cooperation and conflict factors (GRACCFs) is a creative social computing method for team establishment. It can maximize the new team's performance through role assignment considering potential cooperation or conflict factors among agents. However, this method has two bottlenecks in practical applications. First, in the scenario of establishing a new team from several existing teams, collecting the pertinent cooperation or conflict information encounters challenges. Second, GRACCF merely takes the CCFs as a part of the objective function for team performance, but this will underestimate the CCFs' impacts on the sustainable development of the team. This article tackles these issues by extending GRACCF from a new viewpoint. It first designs a KD45 logic algorithm based on the KD45 logic system, which can discover the implicit cognitive CCFs through logical inferences with closure calculations. Then, it proposes an original team evaluation method that can help decision-makers determine the weights of team performance and CCFs' impacts based on their demands. Large-scale simulation experiments indicate that the proposed solution is practicable and robust. The proposed method provides a solid decision-making reference for administrators when establishing a sustainable team.

关键词： Teamwork Task analysis Measurement inference algorithms Sustainable development Linear programming Companies Group role assignment with cooperation and conflict factors (GRACCFs) KD45 logic algorithm role-based collaboration (RBC) social computational strategy team evaluation method

来源：评论

学校读者我要写书评

暂无评论

A Fast and Generalized Broad-Phase Collision Detection Method Based on KD-Tree Spatial Subdivision and Sweep-and-Prune

引用

IEEE ACCESS 2023年 11卷 44696-44710页

作者： Cao, Jiaqi Wang, Monan Harbin Univ Sci & Technol Sch Mech & Power Engn Harbin 230103 Peoples R China

Various graphics applications use multibody collision detection, a critical technology in computer graphics, system simulations, and virtual reality. In these simulation environments, broad-phase collision detection, as part of collision detection, plays a critical role in ensuring that rejecting disjoint objects and collision detection is accelerated. Few existing methods implement collision detection of millions of objects in a general-purpose environment on the CPU. This paper proposes a broad-phase collision detection algorithm based on KD-Tree spatial subdivision and sweep-and-prune, which optimizes and accelerates broad-phase collision detection using a pre-sorting and temporal inference solution. Our method enables broad-phase collision detection for coherent and non-coherent settings for uniformly and non-uniformly sized objects respectively. Based on our proposed solution is tested in the context of complex scenarios and compared with other solutions available in the literature and in the industry. The experimental results show that our approach has a 1X to 2X performance improvement in virtual environments with up to 1024 x 103 objects, reaching the fastest collision detection speed of 119.45 milliseconds per frame in the test environment.

关键词： Collision avoidance Computational modeling Solid modeling Object recognition inference algorithms Cognition Three-dimensional displays Collision detection KD-tree spatial subdivision sweep and prune

来源：评论

学校读者我要写书评

暂无评论

PAWN: Programmed Analog Weights for Non-Linearity Optimization in Memristor-Based Neuromorphic Computing System

引用

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS 2023年第1期13卷 436-444页

作者： Khan, Saleh Ahmad Oli-Uz-Zaman, Md. Wang, Jinhui Univ S Alabama Dept Elect & Comp Engn Mobile AL 36688 USA

Memristors offer advantages as a hardware solution for neuromorphic systems. However, their nonlinear device property makes the weight update inaccurately and reduces the inference accuracy of a neural network. A Programmed Analog Weights for Nonlinearity (PAWN) method is proposed in this paper to update the conductance of a memristor by following the nonlinear curve during the training in a neuromorphic system. The experiment results indicates the PAWN method is effective to alleviate the nonlinearity influence to memristors in all different LTP/LTD conditions. Especially in extreme nonlinearity (LTP=6, LTD=-6), the memristor-based neuromorphic system has significantly low accuracy (51.77%), but the PAWN method enables large accuracy improvement (9.87%) without the inference energy and latency overhead. In addition, overall performance of the neuromorphic system is also evaluated for further verification. Finally, comprehensive experiments show that the PAWN method is still greatly valid even considering device-to-device variations, cycle-to-cycle variations, various technology nodes, and different architectures.

关键词： Memristors Mathematical models Neural networks Hardware Optimization inference algorithms Voltage control Memristor neuromorphic system artificial intelligence (AI) inference accuracy nonlinearity

来源：评论

学校读者我要写书评

暂无评论

Estimating Structurally Similar Graphical Models

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2023年第2期69卷 1093-1124页

作者： Sihag, Saurabh Tajer, Ali Univ Penn Dept Neurol Philadelphia PA 19104 USA Rensselaer Polytech Inst Dept Elect Comp & Syst Engn Troy NY 12180 USA

This paper considers the problem of estimating the structure of structurally similar graphical models in high dimensions. This problem is pertinent in multi-modal or multi-domain datasets that consist of multiple information domains, each modeled by one probabilistic graphical model (PGM), e.g., in brain network modeling using different neuroimaging modalities. Induced by an underlying shared causal source, the domains, and subsequently their associated PGMs, can have structural similarities. This paper focuses on Gaussian and Ising models and characterizes the information-theoretic sample complexity of estimating the structures of a pair of PGMs in the degree-bounded and edge-bounded subclasses. The PGMs are assumed to have p nodes with distinct and unknown structures. Their similarity is accounted for by assuming that a pre-specified set of q nodes form identical subgraphs in both PGMs. Necessary and sufficient conditions on the sample complexity for a bounded probability of error are characterized. The necessary conditions are information-theoretic (algorithm-independent), delineating the statistical difficulty of the problem. The sufficient conditions are based on deploying maximum likelihood decoders. While the specifics of the results vary across different subclasses and parameter regimes, one key observation is that in specific subclasses and regimes, the sample complexity varies with p and q according to Theta(log(p - q)). For Ising models, a low complexity, online structure estimation (learning) algorithm based on multiplicative weights is also proposed. Numerical evaluations are also included to illustrate the interplay among different parameters on the sample complexity when the structurally similar graphs are recovered by a maximum likelihood-based graph decoder and the proposed online estimation algorithm.

关键词： Complexity theory Graphical models Random variables inference algorithms Data models Brain modeling Probabilistic logic Structure learning probabilistic graphical models Gaussian Ising high-dimensional estimation

来源：评论

学校读者我要写书评

暂无评论

Tiny Machine Learning: Progress and Futures

引用

IEEE CIRCUITS AND SYSTEMS MAGAZINE 2023年第3期23卷 8-34页

作者： Lin, Ji Zhu, Ligeng Chen, Wei-Ming Wang, Wei-Chen Han, Song MIT Cambridge MA 02139 USA

Tiny machine learning (TinyML) is a new frontier of machine learning. By squeezing deep learning models into billions of IoT devices and microcontrollers (MCUs), we expand the scope of applications and enable ubiquitous intelligence. However, TinyML is challenging due to the hardware constraints: the tiny memory resource is difficult hold deep learning models designed for cloud and mobile platforms. There is also limited compiler and inference engine support for bare-metal devices. Therefore, we need to co-design the algorithm and system stack to enable TinyML. In this review, we will first discuss the definition, challenges, and applications of TinyML. We then survey the recent progress in TinyML and deep learning on MCUs. Next, we will introduce MCUNet, showing how we can achieve ImageNet-scale AI applications on IoT devices with system-algorithm co-design. We will further extend the solution from inference to training and introduce tiny on-device training techniques. Finally, we present future directions in this area. Today's "large" model might be tomorrow's "tiny" model. The scope of TinyML should evolve and adapt over time.

关键词： Deep learning Training Adaptation models Microcontrollers Memory management inference algorithms Tiny machine learning Machine learning TinyML efficient deep learning on-device training learning on the edge

来源：评论

学校读者我要写书评

暂无评论

Outlier-Concerned Data Completion Exploiting Intra-and Inter-Data Correlations in Sparse CrowdSensing

引用

IEEE-ACM TRANSACTIONS ON NETWORKING 2023年第2期31卷 648-663页

作者： Wang, En Zhang, Mijia Liu, Wenbin Xiong, Haoyi Yang, Bo Yang, Yongjian Wu, Jie Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China Baidu Res Big Data Lab Beijing 100193 Peoples R China Temple Univ Dept Comp & Informat Sci Philadelphia PA 19122 USA

Mobile CrowdSensing (MCS) is a popular data collection paradigm which usually faces the problem of sparse sensed data because of the limited sensing cost. In order to address the situation of sparse data, sparse MCS recruits users to sense important areas and infers completed data by data completion, which is crucial in sparse MCS for urban sensing applications (e.g. enhancing data expression, improving urban analysis, guiding city planning, etc.) To achieve accurate completion results, previous methods usually utilize the universal similarity and conventional tendency while incorporating only a single dataset to infer the full map. However, in real-world scenarios, there may exist many kinds of data (inter-data), that could help to complement each other. Moreover, for each kind of data (intra-data), there usually exist a few but important outliers caused by the special events (e.g., parking peak, traffic congestion, or festival parade), which may behave in a different way as the statistical patterns. These outliers cannot be ignored, while it is difficult to detect and recover them in data completion because of the following challenges: 1) the infrequency and unpredictability of outliers' occurrence, 2) the large deviations against the means compared to normal values, and 3) the complex spatiotemporal relations among inter-data. To this end, focusing on spatiotemporal data with both intra-and inter-data correlations, we propose a matrix completion method that takes outliers' effects into consideration and exploits both intra-and inter-data correlations for enhancing performance. Specifically, we first conduct the Deep Matrix Factorization (DMF) with multiple auxiliary Neural Networks, which named Stacked Deep Matrix Factorization (SDMF). Note that the loss function of SDMF is no longer the previous MSE loss function, but replaced with an Outlier Value Loss (OVL) function to effectively detect and recover the outliers. Moreover, a spatiotemporal outlier value memory

关键词： Correlation Spatiotemporal phenomena Sensors Sparse matrices Crowdsensing Data models inference algorithms Sparse mobile crowdsensing matrix completion intra-and inter-data correlation outlier

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：