检索结果-内蒙古大学图书馆

8th International Conference on Learning Representations, ICLR 2020

作者： Chen, Xinyun Wang, Lu Hang, Yizhe Ge, Heng Zha, Hongyuan Insitute for Data and Decision Analytics The Chinese University of HongKong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Department of Computer Science East China Normal University China Department of Computer Science University of Science and Technology of China China School of Mathematics and Statistics Shandong University China Georgia Institute of Technology United States College of Computing Georgia Institute of Technology United States

We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies. Recent work has shown the key role played by the state or state-action stationary distribution corrections in the infinite horizon context for off-policy policy evaluation. We propose estimated mixture policy (EMP), a partially policy-agnostic methods to accurately estimate those quantities. With careful analysis, we show that EMP gives rise to estimates with reduced variance for estimating the state stationary distribution correction while it also offers a useful induction bias for estimating the state-action stationary distribution correction. In extensive experiments with both continuous and discrete environments, we demonstrate that our algorithm offers significantly improved accuracy compared to the state-of-the-art methods. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Deployment Optimization for Wireless Sensor Networks Based on Stacked Auto Encoder and Probabilistic Neural Network

引用

Digital Communications and Networks 2024年

作者： Hui Feng Chen Xu Bo Jin Min Zhang School of Intelligent Engineering Technology Jiangsu Vocational College of Finance and Economics Huai'an 223003 China School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai 200235 China Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Coimbra 3030-290 Portugal

In the field of consumer electronics, Wireless Sensor Networks (WSNs) can be used to build large-scale IoT systems and achieve intelligent data collection and processing. This paper proposes a deep neural network model SAE-PNN by Stacked Auto Encoder (SAE) and Probabilistic Neural Network (PNN) in a stack manner. A comprehensive training algorithm of SAE-PNN based on a group of orthogonal function bases is established by introducing a time-varying input and connection weight function, based on the conventional algorithm of unsupervised layer-by-layer initialization and gradient descent of deep neural network. Our proposed SAE-PNN model is used to predict the distance from unknown nodes to known nodes. Based on the collaborative work of nodes and network coverage, an optimal set of working nodes is established to reduce the energy loss of network nodes. A balance relationship between network coverage and energy consumption has been established to solve the problem of optimizing the balance in location coverage and the contradiction between individual nodes and the overall performance of the network. The experimental results show that the proposed method can improve the coverage of the monitored area and the perceived quality of service, and uses a distributed node synchronous scheduling mechanism to reduce the overall energy consumption of the network.

关键词： Wireless sensor networks Stacked auto encoder Probabilistic neural network Deep neural network Deployment strategy Node energy consumption

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Prediction using Machine Learning and Neural Networks

Skin Cancer Prediction using Machine Learning and Neural Net...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Neha Tyagi Logeshwari Dhavamani Mohammed Saleh Al Ansari Bhasker Pant Dilip Kumar Jang Bahadur Saini Joshuva Arockia Dhanraj Department of CSE Amity University Greater Noida Uttar Pradesh India Department of Information Technology St. Joseph’s College of Engineering Chennai India Department of Chemical Engineering College of Engineering University of Bahrain Bahrain UAE Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Science and Engineering Himalayan School of Science and Technology Swami Rama Himalayan University Swami Ram Nagar Jolly Grant Dehradun Uttarakhand India Department of Automation and Robotics (ANRO) Department of Mechatronics Engineering Hindustan Institute of Technology and Science Padur Chennai India

The apparent similarities between skin conditions have made medical diagnosis difficult. Although melanoma is the most well-known type of skin cancer, other diseases have recently been responsible for a large number of fatalities. One of the biggest challenges in creating a dependable automatic categorization system is the absence of massive data. A deep learning (DL) system for identifying skin cancer is presented in this paper. The rapid development rate of melanoma skin cancer, its massive price of surgery, and its mortality rate have all heightened the need for timely diagnosis of skin disease. Most of the time, treating cancer cells requires time and careful detection. The commitment to deep learning powered by machine learning (ML) has been repeatedly shown in the medical sector. Skin cancer categorization has benefited significantly from growing study attention since it is amenable to visual pattern recognition. Studies have revealed that DL-based image classifications may be utilised to enhance skin cancer diagnosis or are on par with or even outperform human specialists. In this study, we provide a deep learning architecture that can identify skin cancer. Five state-of-the-art convolutional neural networks were trained using transfer learning to provide a simple classifier and a hierarchical (with two stages) classification that can differentiate between seven different species of moles. Experiments were conducted using data from the HAM10000 database, a huge collection of dermatoscopic pictures, with the use of data augmentation methods to boost results. The DenseNet201 network performed well in this experiment, as seen by the high classification accuracies and F-measures achieved with very few false negatives. The simple model outperformed the 2-levels model, with the best result coming from the first level, or a binary classification between nevi and non-nevi.

关键词： Deep learning Visualization Databases Sensitivity analysis Transfer learning Surgery Melanoma

来源：评论

学校读者我要写书评

暂无评论

Neural Brain: A Neuroscience-inspired Framework for Embodied Agents

arXiv

引用

arXiv 2025年

作者： Liu, Jian Shi, Xiongtao Nguyen, Thai Duy Zhang, Haitian Zhang, Tianxiang Sun, Wei Li, Yanjie Vasilakos, Athanasios V. Iacca, Giovanni Khan, Arshad Ali Kumar, Arvind Cho, Jae Won Mian, Ajmal Xie, Lihua Cambria, Erik Wang, Lin School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Robotics Hunan University China School of Intelligence Science and Engineering Harbin Institute of Technology Shenzhen China Department of Information and Communication Technology University of Agder Norway Department of Information Engineering and Computer Science University of Trento Italy Elm Company London United Kingdom Division of Computational Science and Technology KTH Royal Institute of Technology Sweden School of Artificial Intelligence and Data Science Sejong University Korea Republic of Department of Computer Science the University of Western Australia Australia College of Computing and Data Science Nanyang Technological University Singapore

The rapid evolution of artificial intelligence (AI) has shifted from static, data-driven models to dynamic systems capable of perceiving and interacting with real-world environments. Despite advancements in pattern recognition and symbolic reasoning, current AI systems, such as large language models, remain disembodied, unable to physically engage with the world. This limitation has driven the rise of embodied AI, where autonomous agents, such as humanoid robots, must navigate and manipulate unstructured environments with human-like adaptability. At the core of this challenge lies the concept of Neural Brain, a central intelligence system designed to drive embodied agents with human-like adaptability. A Neural Brain must seamlessly integrate multimodal sensing and perception with cognitive capabilities. Achieving this also requires an adaptive memory system and energy-efficient hardware-software co-design, enabling real-time action in dynamic environments. This paper introduces a unified framework for the Neural Brain of embodied agents, addressing two fundamental challenges: (1) defining the core components of Neural Brain and (2) bridging the gap between static AI models and the dynamic adaptability required for real-world deployment. To this end, we propose a biologically inspired architecture that integrates multimodal active sensing, perception-cognition-action function, neuroplasticity-based memory storage and updating, and neuromorphic hardware/software optimization. Furthermore, we also review the latest research on embodied agents across these four aspects and analyze the gap between current AI systems and human intelligence. By synthesizing insights from neuroscience, we outline a roadmap towards the development of generalizable, autonomous agents capable of human-level intelligence in real-world scenarios. Our project page is at Neural-Brain-for-Embodied-Agents. Copyright © 2025, The Authors. All rights reserved.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Efficient Random Subspace Decision Forests with A Simple Probability Dimensionality Setting Scheme

SSRN

引用

SSRN 2022年

作者： Wang, Quan Wang, Fei Li, Zhongheng Jiang, Peilin Ren, Fuji Nie, Feiping Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Applications Beijing Institute of Spacecraft System Engineering Beijing100094 China School of Software Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China Northwestern Polytechnical University Shaanxi Xi’an710072 China

The random subspace concept is widely used in decision forests. However, there is not a reasonable approach to specify the appropriate number of randomly selected features. Previous random subspace decision forests simply specify the random subspace dimensionality d s to a preset function value such as [log 2 d ] or [√ d ] where d is the number of the total feature dimensions. Actually, this preset value may be a relatively poor choice for high dimensional data sets. In this paper, a novel framework named Efficient Random Subspace decision forest (ERS) is proposed which pays attention to how to set the random subspace dimensionality for each decision tree of decision forests. Specifically, a simple discrete uniform distribution is employed to set with probability the number of randomly selected features for each tree in random subspace decision forests. The proposed Half Range Discrete Uniform distribution-based Varied Dimensionality setting (HRDUVD) method removes the hesitation of how to preset an appropriate d s for different data sets but also results in good enough classification performance along with relatively short running time. Plenty of experiments on public benchmark data sets have demonstrated the effectiveness and the efficiency of the proposed ERS. © 2022, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Delta Descriptors: Change-Based Place Representation for Robust Visual Localization

arXiv

引用

arXiv 2020年

作者： Garg, Sourav Harwood, Ben Anand, Gaurangi Milford, Michael School of Electrical Engineering and Robotics QUT Centre for Robotics Queensland University of Technology Australia Department of Electrical and Computer Systems Engineering Monash University Australia School of Computer Science Queensland University of Technology Australia

Visual place recognition is challenging because there are so many factors that can cause the appearance of a place to change, from day-night cycles to seasonal change to atmospheric conditions. In recent years a large range of approaches have been developed to address this challenge including deep-learnt image descriptors, domain translation, and sequential filtering, all with shortcomings including generality and velocity-sensitivity. In this paper we propose a novel descriptor derived from tracking changes in any learned global descriptor over time, dubbed Delta Descriptors. Delta Descriptors mitigate the offsets induced in the original descriptor matching space in an unsupervised manner by considering temporal differences across places observed along a route. Like all other approaches, Delta Descriptors have a shortcoming - volatility on a frame to frame basis - which can be overcome by combining them with sequential filtering methods. Using two benchmark datasets, we first demonstrate the high performance of Delta Descriptors in isolation, before showing new state-of-the-art performance when combined with sequence-based matching. We also present results demonstrating the approach working with a second different underlying descriptor type, and two other beneficial properties of Delta Descriptors in comparison to existing techniques: their increased inherent robustness to variations in camera motion and a reduced rate of performance degradation as dimensional reduction is applied. Source code will be released upon publication. Copyright © 2020, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Flexible Semi-Cylindrical Valve for Seamless Integration in Soft Robots Based on the Giant Electrorheological Fluid

SSRN

引用

SSRN 2022年

作者： Huang, Tiantian Xu, Denan Zhang, Hang Bai, Ou Aravelli, Aparna Zhou, Xiaoxiao Han, Bin School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430070 China Human Cyber-Physical Systems Laboratory The Department of Electrical and Computer Engineering Florida International University Florida33174 United States Applied Research Center Florida International University Florida33174 United States Guangdong Intelligent Robotics Institute Dongguan523808 China

Complete compliance of soft robots is a trending research topic. One significant aspect is the control element. In the current work, a flexible electro-rheological (ER) valve development is chosen due to the advantage of its dynamic power density, convenient electronic control mode and no mechanical moving parts. These properties enable the ER valve to be miniaturized and easily integrated into a fluid-driven soft robot. However, the integration effect of the existing flexible ER valve configuration in soft robots is not ideal. In this study, a novel concentric semi-cylindrical flexible giant ER (GER) valve with a dual flowing direction is proposed for a soft robot to enable a larger deformation bending motion with multiple motion modes. The resulting valve has an overall volume of 50 mm 3 , a mass of 0.88 g, and a maximum controlling pressure of 84 kPa with a pressure change rate of 13.9, which is suitable for most soft robot applications. The pressure difference calculation method for the concentric semi-cylindrical GER valve is discussed. The effects of size, voltages, and flow rates on the valve’s static and dynamic performances, as well as the characteristics of the two pressure regulation modes, are investigated through simulations and experiments. The seamless integration and flexibility of the proposed valve are demonstrated by controlling a typical network actuator with six motion modes. Finally, a soft robot composed of two actuators is fabricated and realized the grasping of multiple everyday objects using different motion modes. © 2022, The Authors. All rights reserved.

关键词： Nanofluidics

来源：评论

学校读者我要写书评

暂无评论

The Unconstrained Ear Recognition Challenge 2023: Maximizing Performance and Minimizing Bias*

The Unconstrained Ear Recognition Challenge 2023: Maximizing...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Ž. Emeršić T. Ohki M. Akasaka T. Arakawa S. Maeda M. Okano Y. Sato A. George S. Marcel I. I. Ganapathi S. S. Ali S. Javed N. Werghi S. G. Işık E. Sarıtaş H. K. Ekenel V. Hudovernik J. N. Kolf F. Boutros N. Damer G. Sharma A. Kamboj A. Nigam D. K. Jain G. Cámara-Chávez P. Peer V. Štruc University of Ljubljana (UL SI) Shizuoka University (SU JP) Idiap Research Institute (IDIAP CH) Electrical Engineering and Computer Science Department Khalifa University (KU UAE) Department of Computer Engineering (ITU TR) Istanbul Technical University Microelectronic Guidance and Electro-Optical Group ASELSAN Fraunhofer Institute for Computer Graphics Research IGD (IGD DE) Technische Universität Darmstadt (TUD DE) Indian Institute of Technology Mandi (IIT IN) HCL Imaging and Robotics R&D Lab (HCL IN) School of Artificial Intelligence Dalian University of Technology (DLUT CN) Federal University of Ouro Preto (UFOP BR)

The paper provides a summary of the 2023 Unconstrained Ear Recognition Challenge (UERC), a benchmarking effort focused on ear recognition from images acquired in uncontrolled environments. The objective of the challenge was to evaluate the effectiveness of current ear recognition techniques on a challenging ear dataset while analyzing the techniques from two distinct aspects, i.e., verification performance and bias with respect to specific demographic factors, i.e., gender and ethnicity. Seven research groups participated in the challenge and submitted a seven distinct recognition approaches that ranged from descriptor-based methods and deep-learning models to ensemble techniques that relied on multiple data representations to maximize performance and minimize bias. A comprehensive investigation into the performance of the submitted models is presented, as well as an in-depth analysis of bias and associated performance differentials due to differences in gender and ethnicity. The results of the challenge suggest that a wide variety of models (e.g., transformers, convolutional neural networks, ensemble models) is capable of achieving competitive recognition results, but also that all of the models still exhibit considerable performance differentials with respect to both gender and ethnicity. To promote further development of unbiased and effective ear recognition models, the starter kit of UERC 2023 together with the baseline model, and training and test data is made available from: http://***/

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multilayer Fuzzy Neural Networks for Image Clustering

SSRN

引用

SSRN 2022年

作者： Wang, Yifan Ishibuchi, Hisao Er, Meng Joo Zhu, Jihua School of Software Engineering Xi’an Jiaotong University Xi’an710049 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation China College of Marine Electrical Engineering Dalian Maritime University Dalian116026 China Institute of Artificial Intelligence Marine Robotics China

Nowadays, labeling a huge number of images is still a very challenging task. To tackle the problem of unlabeled data, unsupervised learning has been proposed. Among many unsupervised learning algorithms, K-means is the most popular algorithm. However, in a low-dimensional space, fuzzy c-means, which is more robust and less sensitive to initialization, has several advantages over K-means clustering. On the other hand, stacked convolutional pooling structures and manifold representation play pivotal roles in image clustering. In this paper, we proposed an unsupervised multilayer fuzzy neural network for image clustering, which unifies fuzzy systems, multilayer convolutional structures and manifold representation. The main contributions of this work are: First, we extend fuzzy systems to unsupervised tasks by introducing the manifold representation. Next, we proposed the idea of using only a small number of attributes with the largest variances to compute firing strengths. This is to prevent the firing strengths from falling to zero in clustering high-dimensional data. Then, randomly generated convolutional weights are used to extract features, which is a good choice for data without labels. It is demonstrated on a wide range of image datasets that the proposed approach is superior to existing fuzzy and non-fuzzy clustering algorithms. © 2022, The Authors. All rights reserved.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Security Practices for Microservices Systems

arXiv

引用

arXiv 2021年

作者： Ali, Rezaei Nasab Mojtaba, Shahin Ali, Hoseyni Raviz Seyed Peng, Liang Amir, Mashmool Valentina, Lenarduzzi School of Computer Science Wuhan University Wuhan430072 China School of Computing Technologies RMIT University Melbourne3000 Australia Department of Computer Science Bioengineering Robotics and System Engineering University of Genoa Genoa16126 Italy Faculty of Information Technology and Electrical Engineering University of Oulu OuluFI-90014 Finland

Despite the numerous benefits of microservices systems, security has been a critical issue in such systems. Several factors explain this difficulty, including a knowledge gap among microservices practitioners on properly securing a microservices system. To (partially) bridge this gap, we conducted an empirical study. We first manually analyzed 861 microservices security points, including 567 issues, 9 documents, and 3 wiki pages from 10 GitHub open-source microservices systems and 306 Stack Overflow posts concerning security in microservices systems. In this study, a microservices security point is referred to as "a GitHub issue, a Stack Overflow post, a document, or a wiki page that entails 5 or more microservices security paragraphs". Our analysis led to a catalog of 28 microservices security practices. We then ran a survey with 74 microservices practitioners to evaluate the usefulness of these 28 practices. Our findings demonstrate that the survey respondents affirmed the usefulness of the 28 practices. We believe that the catalog of microservices security practices can serve as a valuable resource for microservices practitioners to more effectively address security issues in microservices systems. It can also inform the research community of the required or less explored areas to develop microservices-specific security practices and tools. © 2021, CC BY.

关键词： Open systems

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：