检索结果-内蒙古大学图书馆

Adaptation Through Prediction: Multisensory Active inference Torque Control

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2023年第1期15卷 32-41页

作者： Meo, Cristian Franzese, Giovanni Pezzato, Corrado Spahn, Max Lanillos, Pablo Delft Univ Technol Fac Mech Engn Dept Cognit Robot NL-2628 CD Delft Netherlands Radboud Univ Nijmegen Donders Inst Brain Cognit & Behav Dept Artificial Intelligence NL-6525 XZ Nijmegen Netherlands

Adaptation to external and internal changes is of major importance for robotic systems in uncertain environments. Here, we present a novel multisensory active inference (AIF) torque controller for industrial arms that shows how prediction can be used to resolve adaptation. Our controller, inspired by the predictive brain hypothesis, improves the capabilities of current AIF approaches by incorporating learning and multimodal integration of low- and high-dimensional sensor inputs (e.g., raw images) while simplifying the architecture. We performed a systematic evaluation of our model on a 7DoF Franka Emika Panda robot arm by comparing its behavior with previous AIF baselines and classic controllers, analyzing both qualitatively and quantitatively adaptation capabilities and control accuracy. The results showed improved control accuracy in goal-directed reaching with high noise rejection due to multimodal filtering, and adaptability to dynamical inertial changes, elasticity constraints, and human disturbances without the need to relearn the model or parameter retuning.

关键词： Robot sensing systems Robots Mathematical models Adaptation models Torque State estimation inference algorithms Bio-inspired robotics robot control representation learning

来源：评论

学校读者我要写书评

暂无评论

Noncooperative Topology inference of Wireless Networks With Monitoring Sensors

引用

IEEE INTERNET OF THINGS JOURNAL 2023年第21期10卷 19282-19295页

作者： Chen, Rui Chang, Lili Hui, Yilong Cheng, Nan Zhang, Wei Xidian Univ State Key Lab Integrated Serv Networks Xidian 710071 Peoples R China Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2052 Australia

With the widespread application of wireless networks, the importance of intelligent analysis of network behaviors is becoming increasingly prominent. In the analysis of networks behaviors, learning and reasoning about the connectivity of unknown networks is a fundamental problem. To obtain the topology information of a noncooperative wireless network that could not be accessed by the monitoring sensors, we propose a topology inference algorithm based on the network two-dimensional spatiotemporal features (TDSTFs). Specifically, the monitoring sensor network monitors the power of the noncooperative network and locates the nodes of the noncooperative network exploiting the neural network (NN)-based method. Then, the communication time and distance between the noncooperative nodes are used as characteristics to infer the topology of the noncooperative network based on K -nearest neighbors (KNNs). Simulation results validate that the proposed TDSTF topology inference algorithm outperforms other topology inference algorithms that do not consider both spatial and temporal features and can greatly improve the inference accuracy.

关键词： Network topology Topology Sensors Monitoring Location awareness inference algorithms Wireless sensor networks K-nearest neighbors (KNNs) localization monitoring sensors neural network (NN) topology inference wireless networks

来源：评论

学校读者我要写书评

暂无评论

A New Algorithm of Cubic Dynamic Uncertain Causality Graph for Speeding Up Temporal Causality inference in Fault Diagnosis

引用

IEEE TRANSACTIONS ON RELIABILITY 2023年第2期72卷 662-677页

作者： Dong, Chunling Zhou, Jing Commun Univ China Sch Comp & Cyber Sci State Key Lab Media Convergence & Commun Beijing 100024 Peoples R China

Representing and reasoning uncertain causalities have diverse applications in fault diagnosis for industrial systems. Owing to the complicated dynamics and a multitude of uncertain factors in such systems, it is hard to implement efficient diagnostic inference when a process fault occurs. The cubic dynamic uncertain causal graph was proposed for graphically modeling and reasoning about the fault spreading behaviors in the form of causal dependencies across multivariate time series. However, in certain large-scale scenarios with multiconnected and time-varying causalities, the existing inference algorithm is incapable of dealing with the logical reasoning process in an efficient manner. We, therefore, explore the solutions to enhanced computational efficiency. Causality graph decomposition and simplification, and graphical transformation, are proposed to reduce model complexity and form a minimal causality graph. An algorithm, event-oriented early logical absorption, is also presented for logical reasoning. It is mainly intended to minimize the computational costs for compulsory absorption operations in the early stage of reasoning process. The effectiveness of the proposed algorithm is verified on the secondary loop model of nuclear power plant by utilizing the fault data derived from a nuclear power plant simulator. The results show the anticipated capability of efficient fault diagnosis of the proposed algorithm for large-scale dynamic systems.

关键词： Heuristic algorithms Cognition Hidden Markov models Fault diagnosis Power generation inference algorithms Computational modeling Causal inference dynamic logic reasoning fault diagnosis probabilistic reasoning temporal causality representation

来源：评论

学校读者我要写书评

暂无评论

SmartDeal: Remodeling Deep Network Weights for Efficient inference and Training

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第10期34卷 7099-7113页

作者： Chen, Xiaohan Zhao, Yang Wang, Yue Xu, Pengfei You, Haoran Li, Chaojian Fu, Yonggan Lin, Yingyan Wang, Zhangyang Univ Texas Austin Dept Elect & Comp Engn Austin TX 78712 USA Rice Univ Dept Elect & Comp Engn Houston TX 77005 USA

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameter budgets, which leads to external dynamic random access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it nontrivial for DNN deployment on resource-constrained devices, calling for minimizing the movements of weights and data in order to improve the energy efficiency. Driven by this critical bottleneck, we present SmartDeal, a hardware-friendly algorithm framework to trade higher-cost memory storage/access for lower-cost computation, in order to aggressively boost the storage and energy efficiency, for both DNN inference and training. The core technique of SmartDeal is a novel DNN weight matrix decomposition framework with respective structural constraints on each matrix factor, carefully crafted to unleash the hardware-aware efficiency potential. Specifically, we decompose each weight tensor as the product of a small basis matrix and a large structurally sparse coefficient matrix whose nonzero elements are readily quantized to the power-of-2. The resulting sparse and readily quantized DNNs enjoy greatly reduced energy consumption in data movement as well as weight storage, while incurring minimal overhead to recover the original weights thanks to the required sparse bit-operations and cost-favorable computations. Beyond inference, we take another leap to embrace energy-efficient training, by introducing several customized techniques to address the unique roadblocks arising in training while preserving the SmartDeal structures. We also design a dedicated hardware accelerator to fully utilize the new weight structure to improve the real energy efficiency and latency performance. We conduct experiments on both vision and language tasks, with nine models, four datasets, and three settings (inference-only, adaptation, and fine-tuning). Our extensive results show that 1) being applied to inference, SmartDeal achieves up to 2.44x improvement in energy efficie

关键词： Training Matrix decomposition Costs Quantization (signal) inference algorithms Random access memory Hardware acceleration Data movement deep network training efficient machine learning hardware accelerator

来源：评论

学校读者我要写书评

暂无评论

Anti-Interference Recognition for Aerial Infrared Object Based on Convolutional Feature inference Network

引用

IEEE AEROSPACE AND ELECTRONIC SYSTEMS MAGAZINE 2023年第2期38卷 4-15页

作者： Yang, Junyan Li, Chenhui Li, Shaoyi Zhang, Xuefeng Yang, Xi Sun, Yang Northwestern Polytech Univ Xian 710072 Peoples R China Xian Aeronaut Comp Tech Res Inst Xian 710065 Peoples R China China Airborne Missile Acad Luoyang 471009 Peoples R China Xian Aeronaut Comp Tech Res Inst Xian 710065 Peoples R China

The infrared decoy countermeasure technology develops along with the infrared imaging guidance technology. The release of infrared decoys can block the object and destroy the integrity of the object features. The traditional statistical approach based on feature fusion matching for pattern recognition is not effective in handling this problem. To improve the characterization ability of the invariant detail features in the infrared object domain and improve the classification accuracy of the probability identification model, this article proposes an inference recognition model that combines the convolutional features and the Bayesian network. The proposed model exploits the convolutional neural network to extract the detailed feature information of the object in the infrared image. Then, it uses the 2DPCANet screening mechanism to reduce the dimensionality and select more obvious detailed information in the candidate region. Based on the combination of human prior knowledge and posterior data, an infrared object recognition probability model is established through the application of the Bayesian network. The performance of the proposed algorithm is tested on the complex air combat simulation image dataset. The experimental results indicate that the recognition rate of the proposed anti-interference recognition algorithm reaches 94.17%.

关键词： Feature extraction Bayes methods Object recognition Interference Convolution Missiles inference algorithms object recognition anti-interference convolution feature inference 2DPCANet Bayesian network

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Urban inference and Prediction in Sparse Mobile CrowdSensing: A Graph Neural Network Approach

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2023年第11期22卷 6784-6799页

作者： Wang, En Liu, Weiting Liu, Wenbin Yang, Yongjian Yang, Bo Wu, Jie Jilin Univ Dept Comp Sci & Technol Changchun 130012 Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun 130012 Peoples R China Temple Univ Dept Comp & Informat Sci Philadelphia PA 19122 USA

Mobile CrowdSensing (MCS) has recently become a promising data acquisition paradigm, which recruits a large number of users to collect data from the target sensing areas. Obviously, with the increase of sensing scale and the decrease of sensing granularity, traditional MCS cannot fully cover the required sensing areas especially the inaccessible areas. As a variant, Sparse MCS can utilize the spatiotemporal correlations in sensing data to infer the whole sensing map only by sensing a few subareas. However, in many real-world scenarios, such as traffic congestion prediction or parking occupancy detection, inferring the current unsensed data may not be the final goal. By comparison, it is more important to get the future information through the sparse sensed data. In this paper, we turn attention from inferring the current unsensed data to predicting the future unknown data and propose an urban inference and prediction framework in Sparse MCS. To deal with the sparse sensed data, we first present a bipartite-graph-based matrix completion algorithm with spatiotemporal constraints to accurately recover the current full map. Then, by exploiting spatiotemporal correlations based on the inferred full map, we present a Graph Convolutional Networks (GCN) with spatiotemporal attention to predict the future maps. Furthermore, we design a spatiotemporal iterative method to repeatedly update the spatiotemporal attentions and constraints, in order to connect the urban inference and prediction to improve the accuracy of the whole framework. Extensive experiments have been conducted on two types of typical urban sensing tasks with four real-world data sets, which verify the effectiveness of our proposed algorithms in improving the inference and prediction accuracy with the sparse sensed data.

关键词： Sensors Spatiotemporal phenomena Correlation inference algorithms Task analysis Sparse matrices Prediction algorithms Mobile crowdsensing matrix completion graph convolution networks spatiotemporal correlations

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Multiuser Edge inference With Batching and Early Exiting

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2023年第4期41卷 1186-1200页

作者： Liu, Zhiyan Lan, Qiao Huang, Kaibin Univ Hong Kong Dept Elect & Elect Engn Hong Kong Peoples R China

The deployment of inference services at the network edge, called edge inference, offloads computation-intensive inference tasks from mobile devices to edge servers, thereby enhancing the former's capabilities and battery lives. In a multiuser system, the joint allocation of communication-and-computation (C-2) resources (i.e., scheduling and bandwidth allocation) is made challenging by adopting efficient inference techniques, batching and early exiting, and further complicated by the heterogeneity in users' requirements on accuracy and latency. Batching groups multiple tasks into a single batch for parallel processing to reduce time-consuming memory access and thereby boosts the throughput (i.e., completed task per second). On the other hand, early exiting allows a task to exit from a deep-neural network without traversing the whole network, thereby supporting a tradeoff between accuracy and latency. In this work, we study optimal C-2 resource allocation with batching and early exiting, which is an NP-complete integer programming problem. A set of efficient algorithms are designed under the criterion of maximum throughput by tackling the challenge. First, consider the case with batching but without early exiting. The target problem is solved optimally using a proposed best-shelf-packing algorithm that nests a threshold-based scheme, which selects users with the best channels and meeting the computation-time constraints, in a sequential search for the maximum batch size. Next, consider the general case with batching and early exiting. A low-complexity sub-optimal algorithm for C-2 resource allocation is developed by modifying the preceding algorithm to exploit early exiting for latency reduction. On the other hand, the optimal approach is developed based on nesting a depth-first tree-search with intelligent online pruning into a sequential search for the maximum batch size. The key idea is to derive pruning criteria based on the simple greedy solution for the target p

关键词： Task analysis Resource management Throughput Servers inference algorithms Computational modeling Bandwidth Edge inference radio resource management multiuser edge computing

来源：评论

学校读者我要写书评

暂无评论

Bayesian inference for Stochastic Multipath Radio Channel Models

引用

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION 2023年第4期71卷 3460-3472页

作者： Hirsch, Christian Bharti, Ayush Pedersen, Troels Waagepetersen, Rasmus Aarhus Univ Dept Math DK-8000 Aarhus Denmark Aalto Univ Dept Comp Sci Espoo 02150 Finland Aalborg Univ Dept Elect Syst DK-9220 Aalborg Denmark Aalborg Univ Dept Math Sci DK-9220 Aalborg Denmark

Stochastic radio channel models based on underlying point processes of multipath components (MPCs) have been studied intensively since the seminal papers of Turin and Saleh-Valenzuela (SV). Despite this, inference regarding parameters of these models has remained a major challenge. Current methods typically have a somewhat ad hoc flavor involving a multitude of steps requiring user specification of tuning parameters. In this article, we propose to instead adopt the principled framework of Bayesian inference to conduct inference for the SV model. The posterior distribution is not analytically tractable and we therefore compute approximations of the posterior using Markov chain Monte Carlo (MCMC) methods specific to point processes. To demonstrate the flexibility of our approach, we additionally propose a new multipath model and apply our inference method to it. The resulting inference methodology is computationally demanding and our successful implementation relies critically on our novel MPC updates within the MCMC sampler. We demonstrate the usefulness of our approach on simulated and real radio channel data.

关键词： Computational modeling Delays Bayes methods Monte Carlo methods Kernel Analytical models inference algorithms Bayesian inference Markov chain Monte Carlo (MCMC) sampling multipath propagation parameter estimation radio channel modeling

来源：评论

学校读者我要写书评

暂无评论

CoGNN: An Algorithm-Hardware Co-Design Approach to Accelerate GNN inference With Minibatch Sampling

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2023年第12期42卷 4883-4896页

作者： Zhong, Kai Zeng, Shulin Hou, Wentao Dai, Guohao Zhu, Zhenhua Zhang, Xuecang Xiao, Shihai Yang, Huazhong Wang, Yu Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Univ Wisconsin Comp Sci Dept Madison WI USA Shanghai Jiao Tong Univ Qing Yuan Res Inst Shanghai 200240 Peoples R China Huawei Technol Co Ltd 2012 Lab Shenzhen 518063 Peoples R China

As a new algorithm of graph embedding, graph neural networks (GNNs) have been widely used in many fields. However, GNN computing has the characteristics of both sparse graph processing and dense neural network, which make it difficult to be deployed efficiently on the existing graph processing accelerators or neural network accelerators. Recently, some GNN accelerators have been proposed, but the following challenges have not been fully solved: 1) the minibatch GNN inference scenario has the potential of software and hardware co-design, which can bring 30% computation amount reduction, and this is not well utilized. Besides, the cost of message flow graph construction is large and may account for more than 50% of the total delay;2) the feature aggregation has a large amount of data access and relatively small amount of computation, which leads to low on-chip data reuse, only 10% of dense computing;and 3) without the optimization of sparse computing units, simple memory bank and cross bar architecture can easily lead to bank access conflict and load imbalance, reducing the utilization of computing units to less than 60%. In order to solve the above problems, we propose a algorithm-hardware co-design scheme to accelerate GNN inference, which includes three technologies: 1) a reuse-aware sampling method is proposed for minibatch inference scenarios, which reduces 30% of the calculation and improves the on-chip reusability of local data;2) through the nodewise parallelism-aware quantization, the features and weights are quantized to integers with eight or four bits, which reduces the amount of memory access by at least four times;and 3) an accelerator supporting the above technologies is designed and evaluated, and different operations are supported by the sampling-inference integration architecture. The multibank on-chip memory pool is designed to support data reuse, and edge stream reordering is used to reduce data access conflicts, improving the utilization of comput

关键词： Neural networks Graph neural networks Computer architecture System-on-chip Quantization (signal) inference algorithms Hardware acceleration Accelerator graph neural network (GNN) quantization sampling

来源：评论

学校读者我要写书评

暂无评论

Large Deviations for Products of Non-Identically Distributed Network Matrices With Applications to Communication-Efficient Distributed Learning and inference

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2023年 71卷 1319-1333页

作者： Petrovic, Nemanja Bajovic, Dragana Kar, Soummya Jakovetic, Dusan Sahu, Anit Kumar Univ Novi Sad Fac Tech Sci Dept Fundamental Sci Novi Sad 21000 Serbia Univ Novi Sad Fac Tech Sci Dept Power Elect & Commun Engn Novi Sad 21000 Serbia Carnegie Mellon Univ Dept Elect & Comp Engn Pittsburgh PA 15213 USA Univ Novi Sad Fac Sci Dept Math & Informat Novi Sad 21000 Serbia Amazon Com Inc Alexa AI Pittsburgh PA 15232 USA

This paper studies products of independent but non-identically distributed random network matrices that arise as weight matrices in distributed consensus-type computation and inference procedures in peer-to-peer multi-agent networks. The non-identically distributed matrices studied in this paper model various application scenarios in which the agent communication network is time-varying, either naturally or engineered to achieve communication efficiency in computational procedures. First, under broad conditions on the statistics of the network matrix sequence, the product of the sequence is shown to converge almost surely to the consensus matrix and explicit large deviations rate of convergence are obtained. Specifically, given the admissible graph of interconnections modeling the base network topology, it is shown that the large deviations rate of consensus equals the minimum limiting value of the fluctuating graph cuts, where the edge costs are assigned through the current probabilities of the inter-agent communications. Secondly, an application of the above large deviations principle is studied in the context of distributed detection in time-varying networks with sequential observations. By adopting a consensus+innovations type distributed detection algorithm, as a by-product of this result, error exponents are obtained for the performance of distributed detection. It is shown that slow starts (slow increase) of inter-agent communication probabilities yield the same asymptotic error rate - and hence the same distributed detection performance, as if the communications were at their nominal levels from the beginning. As an important special case it is shown that when all the intermittent graph cuts have a link the probability of which increases to one, the performance of distributed detection is asymptotically optimal - i.e., equivalent to a centralized setup having access to all network data at all times.

关键词： Convergence Peer-to-peer computing inference algorithms Electronic mail Signal processing algorithms Limiting Estimation Distributed inference stochastic matrices error exponents inaccuracy rates large deviations consensus

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：