检索结果-内蒙古大学图书馆

Hyper-Parameter-Free Latent Factor Analysis via Adaptive Moment Estimation-Incorporated Particle Swarm Optimization

学校读者我要写书评

暂无评论

Hyper-Parameter-Free Latent Factor Analysis via Adaptive Mom...

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Jiufang Chen Ye Yuan Chunlin He School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Chinese Academy of Sciences Chongqing Institute of Green and Intelligent Technology Chongqing China Chongqing School University of Chinese Academy of Sciences Chongqing China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing China School of Computer Science China West Normal University Nanchong Sichuan China

ISBN: (纸本)9781665426220

A latent factor analysis (LFA) model can efficiently address a high-dimensional and sparse (HiDS) matrix with a stochastic gradient descent (SGD) algorithm. However, an SGD-based LFA model's performance depends heavily on its hyper-parameters. The popular method is based on grid-search, which fails because of expensive computation and time-consuming. Aiming at implementing a hyper-parameter-free LFA model, this study proposes an adaptive moment estimation-incorporated particle swarm optimization (Adam-PSO) algorithm that efficiently addresses the premature issues in a PSO algorithm. With achieved the hyper-parameter adaptation in an SGD-based LFA model, an Adam-PSO-based LFA (APL) model possessing hyper-parameter-free training is further implemented. Empirical studies on four HiDS matrices indicate that compared with state-of-the-art models with hyper-parameter adaptation settings, an APL model achieves the most efficient hyper-parameter-free training and highly competitive prediction accuracy for missing data of an HiDS matrix. Hence, it fits the need of real applications with high scalability and efficiency.

关键词： Training Adaptation models Computational modeling Stochastic processes Predictive models Prediction algorithms data models

Value Function Dynamic Estimation in Reinforcement Learning based on data Adequacy 20

学校读者我要写书评

暂无评论

Value Function Dynamic Estimation in Reinforcement Learning ...

4th High Performance computing and Cluster Technologies Conference, HPCCT 2020 and the 3rd International Conference on big data and Artificial Intelligence, BDAI 2020

作者： Gao, Huifan Pan, Yinghui Tang, Jing Zeng, Yifeng Chai, Peihua Cao, Langcai Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision Department of Automation Xiamen University Xiamen China College of Computer Science and Software Engineering Shenzhen University China Newcastle Business School Northumbria University United Kingdom Department of Computer and Information Sciences Northumbria University United Kingdom

ISBN: (纸本)9781450375603

In recent years, reinforcement learning has played an important role in the study of decision problem in computer games. To solve the problem of how to better estimate the value function with limited computational resources, this paper proposes a dynamic estimation method of value function based on data adequacy. In consideration of the varying complexity of each state in the MDP model, we propose a dynamic value function estimation method which is different from the fixed value function estimation method in traditional methods. Based on the PigChase challenge of the Malmo project launched by Microsoft in 2017, we compare the new method with the existing techniques. Experimental results show that the performance of the proposed algorithm is better than traditional algorithms. © 2020 ACM.

关键词： Dynamic programming

Hybrid attention network based on progressive embedding scale-context for crowd counting

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Fusen Sang, Jun Wu, Zhongyuan Liu, Qi Sang, Nong Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing University Chongqing400044 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430000 China

The existing crowd counting methods usually adopted attention mechanism to tackle background noise, or applied multi-level features or multi-scales context fusion to tackle scale variation. However, these ap- proaches deal with these two problems separately. In this paper, we propose an Hybrid Attention Network (HAN) by employing Progressive Embedding Scale-context (PES) information, which enables the network to simultaneously suppress noise and adapt head scale variation. We build the hybrid attention mechanism through paralleling spatial attention and channel attention module, which makes the network to focus more on the human head area and reduce the interference of background objects. Besides, we embed certain scale-context to the hybrid attention along the spatial and channel dimensions for alleviating these count- ing errors caused by the variation of perspective and head scale. Finally, we propose a progressive learning strategy through cascading multiple hybrid attention modules with embedding diαerent scale-context, which can gradually integrate diαerent scale-context information into the current feature map from global to local. Ablation experiments provides that the network architecture can gradually learn multi-scale features and suppress background noise. Extensive experiments demonstrate that HANet obtain state-of-the-art counting performance on four mainstream datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

Artificial Intelligence without Restriction Surpassing Human Intelligence with Probability One: Theoretical Insight into Secrets of the Brain with AI Twins of the Brain

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Guang-Bin Westover, M. Brandon Tan, Eng-King Wang, Haibo Cui, Dongshun Ma, Wei-Ying Wang, Tiantong He, Qi Wei, Haikun Wang, Ning Tian, Qiyuan Lam, Kwok-Yan Yao, Xin Wong, Tien Yin School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China Beth Israel Deaconess Medical Center Harvard Medical School Boston United States Department of Neurology National Neuroscience Institute Singapore Research Centre of Big Data and Artificial Intelligence for Medicine First Affiliated Hospital of Sun Yat-Sen University Guangzhou China Duke-NUS Medical School National University of Singapore Singapore Mind PointEye Singapore Institute for AI Industry Research Tsinghua University Beijing China College of Computing and Data Science Nanyang Technological University Singapore School of Biomedical Engineering Tsinghua University Beijing China Singapore AI Safety Institute Nanyang Technological University Singapore School of Data Science Lingnan University Hong Kong School of Computer Science University of Birmingham United Kingdom Singapore Eye Research Institute Singapore National Eye Centre Singapore Tsinghua Medicine Tsinghua University Beijing China

Artificial Intelligence (AI) has apparently become one of the most important techniques discovered by humans in history while the human brain is widely recognized as one of the most complex systems in the universe. One fundamental critical question which would affect human sustainability remains open: Will artificial intelligence (AI) evolve to surpass human intelligence in the future? This paper shows that in theory new AI twins with fresh cellular level of AI techniques for neuroscience could approximate the brain and its functioning systems (e.g. perception and cognition functions) with any expected small error and AI without restrictions could surpass human intelligence with probability one in the end. This paper indirectly proves the validity of the conjecture made by Frank Rosenblatt 70 years ago about the potential capabilities of AI, especially in the realm of artificial neural networks. This paper also gives the answer to the two widely discussed fundamental questions: 1) whether AI could have potentials of discovering new principles in nature;2) whether error backpropagation (BP) algorithm commonly and efficiently used in tuning parameters in AI applications is also adopted in the brain. Intelligence is just one of fortuitous but sophisticated creations of the nature which has not been fully discovered. Like mathematics and physics, with no restrictions artificial intelligence would lead to a new subject with its self-contained systems and principles. We anticipate that this paper opens new doors for 1) AI twins and other AI techniques to be used in cellular level of efficient neuroscience dynamic analysis, functioning analysis of the brain and brain illness solutions;2) new worldwide collaborative scheme for interdisciplinary teams concurrently working on and modelling different types of neurons and synapses and different level of functioning subsystems of the brain with AI techniques;3) development of low energy of AI techniques with the aid of fundament

关键词： Neurology

Contrastive Learning for Robust Android Malware Familial Classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Yueming Dou, Shihan Zou, Deqing Yang, Wei Qiang, Weizhong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China University of Texas at Dallas Dallas United States National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these obfuscated samples through program analysis contain many useless and disguised features, which leads to many false negatives. To address the issue, in this paper, we demonstrate that obfuscation-resilient malware family analysis can be achieved through contrastive learning. The key insight behind our analysis is that contrastive learning can be used to reduce the difference introduced by obfuscation while amplifying the difference between malware and other types of malware. Based on the proposed analysis, we design a system that can achieve robust and interpretable classification of Android malware. To achieve robust classification, we perform contrastive learning on malware samples to learn an encoder that can automatically extract robust features from malware samples. To achieve interpretable classification, we transform the function call graph of a sample into an image by centrality analysis. Then the corresponding heatmaps can be obtained by visualization techniques. These heatmaps can help users understand why the malware is classified as this family. We implement IFDroid and perform extensive evaluations on two datasets. Experimental results show that IFDroid is superior to state-of-the-art Android malware familial classification systems. Moreover, IFDroid is capable of maintaining a 98.4% F1 on classifying 69,421 obfuscated malware samples. © 2021, CC0.

关键词： Android (operating system)

Regional attention with architecture-rebuilt 3D network for RGB-D gesture recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Benjia Li, Yunan Wan, Jun Macau University of Science and Technology China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China School of Computer Science and Technology Xidian Univeristy China Xi'an Key Laboratory of Big Data and Intelligent Vision China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Human gesture recognition has drawn much attention in the area of computer vision. However, the performance of gesture recognition is always influenced by some gesture-irrelevant factors like the background and the clothes of performers. Therefore, focusing on the regions of hand/arm is important to the gesture recognition. Meanwhile, a more adaptive architecture-searched network structure can also perform better than the block-fixed ones like ResNet since it increases the diversity of features in different stages of the network better. In this paper, we propose a regional attention with architecture-rebuilt 3D network (RAAR3DNet) for gesture recognition. We replace the fixed Inception modules with the automatically rebuilt structure through the network via Neural Architecture Search (NAS), owing to the different shape and representation ability of features in the early, middle, and late stage of the network. It enables the network to capture different levels of feature representations at different layers more adaptively. Meanwhile, we also design a stackable regional attention module called Dynamic-Static Attention (DSA), which derives a Gaussian guidance heatmap and dynamic motion map to highlight the hand/arm regions and the motion information in the spatial and temporal domains, respectively. Extensive experiments on two recent large-scale RGB-D gesture datasets validate the effectiveness of the proposed method and show it outperforms state-of-the-art methods. The codes of our method are available at: https://***/zhoubenjia/RAAR3DNet. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

An Original Design of Robotic-Assisted Flexible Nasotracheal Intubation System

学校读者我要写书评

暂无评论

An Original Design of Robotic-Assisted Flexible Nasotracheal...

IEEE International Conference on Robotics and Biomimetics

作者： He Liu Shi-Qi Liu Xiao-Liang Xie Ye Li Xiao-Hu Zhou Zhen-Qiu Feng Guo-Tao Li Xi-Yao Ma Zeng-Guang Hou Yong-Yi Yuan Yong Cui Yu-Hong Tian Pu Dai State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Joint Engineering Research Center for Health Big Data Intelligent Analysis Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China College of Otolaryngology Head and Neck Surgery The Sixth Medical Center of PLA General Hospital Beijing China Department of Otolaryngology The 983th Hospital of Joint Logistic Support Force Tianjin China

Nasotracheal intubation is a crucial emergency procedure that can improve the survival rate of injured patients. Compared to orotracheal intubation, nasotracheal intubation offers greater stability and comfort. However, due to the large curvature of the cavity, the procedure is highly challenging and requires skilled medical staff, which can be a shortage in emergencies and delay patient rescue. To solve this problem, a flexible and portable robot for nasotracheal intubation has been developed in this paper. The robot incorporates a continuum catheter, allowing the shape of the endotracheal tube’s distal section to be controllable and making it easier to pass through the nasal cavity into the trachea. An endoscope is integrated into the distal section of the catheter to make the intubation process more intuitive, allowing doctors to observe the injuries through endoscopic images and adjust the treatment plan. Additionally, the robot is designed with a quick-detachable structure, enabling aseptic and low-cost intubation procedures. The structure and circuitry of the robot are designed for portability, with a smaller size and lower power consumption, which can work for a long time just powered by batteries. Finally, experiments on a mannequin validate that the robotic system effectively reduces the difficulty of tracheal intubation, enabling even non-medically trained operators to complete the procedure with the assistance of the robot.

关键词：

A Path-Driven Fluid Routing and Scheduling Method for Continuous-Flow Microfluidic Biochips with Delay Time Optimization

学校读者我要写书评

暂无评论

Micromachines 2025年第6期16卷 625页

作者： Zhisheng Chen Bowen Liu Hongjin Su Zhen Chen Genggeng Liu Xing Huang School of Informatics Xiamen University Xiamen 361004 China. College of Computer and Data Science Fuzhou University Fuzhou 350116 China. Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou University Fuzhou 350116 China. Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou 350116 China. School of Big Data Fuzhou University of International Studies and Trade Fuzhou 350202 China.

Routing and application mapping are critical stages in the design of continuous-flow microfluidic biochips (CFMBs). The routing stage determines the channel network connecting components and ports, while application mapping schedules fluid transportation and wash operations based on the designed biochip architecture. Existing methods typically handle these stages separately: routing focuses solely on physical metrics without considering subsequent scheduling requirements, while application mapping adopts one-shot scheduling strategies that can lead to suboptimal solutions. This paper proposes an integrated path-driven methodology that jointly optimizes routing and application mapping. For routing, we develop a hybrid particle swarm optimization algorithm that incorporates conflict awareness and channel utilization strategies. For application mapping, we introduce an iterative approach that leverages historical scheduling information to progressively optimize fluidic-handling and wash operations. Experimental results on both real and synthetic benchmarks demonstrate significant improvements over state-of-the-art methods, achieving reductions of 22.05% in total channel length, 21.79% in intersections, 21.97% in total delay time, and 8.30% in biochemical reaction completion time. The proposed methodology provides an effective solution for the automated design of CFMBs with enhanced physical and operational efficiency.

关键词： application mapping conflict awareness continuous-flow microfluidic biochips particle swarm optimization routing

Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Haoming Ma, Ke Jia, Xiaojun Sun, Yingfei Xu, Qianqian Huang, Qingming School of Electronic Electrical and communication Engineering UCAS Beijing China Nanyang Technological University Singapore Sun Yat-sen University Shenzhen Campus China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of computer science and Technology UCAS Beijing China Key Laboratory of Big Data Mining and Knowledge management UCAS Beijing China

Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies often rely on brute-force optimization or manual design, failing to uncover potential risks in real-world scenarios. To address this, we propose a novel jailbreak attack framework, ICRT, inspired by heuristics and biases in human cognition. Leveraging the simplicity effect, we employ cognitive decomposition to reduce the complexity of malicious prompts. Simultaneously, relevance bias is utilized to reorganize prompts, enhancing semantic alignment and inducing harmful outputs effectively. Furthermore, we introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm by employing ranking aggregation methods such as Elo, HodgeRank, and Rank Centrality to comprehensively quantify the harmfulness of generated content. Experimental results show that our approach consistently bypasses mainstream LLMs’ safety mechanisms and generates high-risk content, providing insights into jailbreak attack risks and contributing to stronger defense strategies. © 2025, CC BY.

关键词： Semantics