检索结果-内蒙古大学图书馆

Correction: Humanoid robot-empowered language learning based on self-determination theory

Education and Information Technologies 2024年第5期30卷 6843-6845页

作者： Fung, Ka Yan Lee, Lik Hang Sin, Kuen Fung Song, Shenghui Qu, Huamin Interdisciplinary Programs Office (Individualized Interdisciplinary Program (IIP) Hong Kong University of Science and Technology Hong Kong China Department of Industrial and Systems Engineering (ISE) The Hong Kong Polytechnic University Hong Kong China Department of Special Education and Counselling The Education University of Hong Kong Hong Kong China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong China

来源：评论

学校读者我要写书评

暂无评论

Membership Privacy-preserving GAN 33

Membership Privacy-preserving GAN

引用

33rd British Machine Vision Conference Proceedings, BMVC 2022

作者： Ha, Heonseok Hwang, Uiwon Jang, Jaehee Bae, Ho Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Cyber Security Ewha Womans University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

A membership inference attack (MIA) identifies if an instance was included in the victim model's train dataset. Without an appropriate defense mechanism, MIA can result in serious privacy breaches. Although several methods have been proposed to protect membership privacy in discriminative models, research into generative adversarial networks (GANs), remains insufficient despite their vulnerability to MIAs. In this study, we propose a membership privacy-preserving GAN (MP-GAN), which plays an additional adversarial game for membership privacy between an auxiliary membership inference network M and a GAN. M seeks to find out whether an instance belongs to the reference or train dataset, whereas the generator and discriminator of the GAN attempt to deceive M. Our theoretical analysis results demonstrate that the MP-GAN improves membership privacy by not learning sample-specific features. We perform extensive empirical evaluations to show that the MP-GAN can successfully defend against MIAs under advantageous scenarios to the attacker (for example, white-box access to networks and small training dataset size). Furthermore, we demonstrate that the MP-GAN has several advantages over other privacy-preserving GAN training techniques. © 2022. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach

arXiv

引用

arXiv 2024年

作者： Kim, Dohyeong Kwon, Hyeokjin Kim, Junseok Lee, Gunmin Oh, Songhwai The Department of Electrical and Computer Engineering and ASRI Seoul National University Seoul08826 Korea Republic of The Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Seoul08826 Korea Republic of

As the complexity of tasks addressed through reinforcement learning (RL) increases, the definition of reward functions also has become highly complicated. We introduce an RL method aimed at simplifying the reward-shaping process through intuitive strategies. Initially, instead of a single reward function composed of various terms, we define multiple reward and cost functions within a constrained multi-objective RL (CMORL) framework. For tasks involving sequential complex movements, we segment the task into distinct stages and define multiple rewards and costs for each stage. Finally, we introduce a practical CMORL algorithm that maximizes objectives based on these rewards while satisfying constraints defined by the costs. The proposed method has been successfully demonstrated across a variety of acrobatic tasks in both simulation and real-world environments. Additionally, it has been shown to successfully perform tasks compared to existing RL and constrained RL algorithms. Our code is available at https://***/rllab-snu/Stage-Wise-CMORL. Copyright © 2024, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Neural-iLQR: A Learning-Aided Shooting Method for Trajectory Optimization

Neural-iLQR: A Learning-Aided Shooting Method for Trajectory...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Cheng, Zilong Li, Yulin Chen, Kai Duan, Jianghua Ma, Jun Lee, Tong Heng National University of Singapore Department of Electrical and Computer Engineering Singapore The Hong Kong University of Science and Technology Department of Mechanical and Aerospace Engineering Hong Kong The Hong Kong University of Science and Technology Division of Emerging Interdisciplinary Areas Hong Kong Robotics and Autonomous Systems Thrust Guangzhou China Hkust Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China

ISBN: (纸本)9798350325706

Iterative linear quadratic regulator (iLQR) has gained wide popularity in addressing trajectory optimization problems with nonlinear system models. However, as a model-based shooting method, it relies heavily on an accurate system model to update the optimal control actions and the trajectory determined with forward integration, thus becoming vulnerable to inevitable model inaccuracies. Recently, substantial research efforts in learning-based methods for optimal control problems have been progressing significantly in addressing unknown system models, particularly when the system has complex interactions with the environment. Yet an incremental machine learning method or a deep neural network is normally required to fit a substantial scale of sampling motion data. Existing works mainly focus on capturing the whole picture of the motion pattern from trial data (which is essentially noisy and hard to identify with any simple predefined structures) for complex robot systems. Instead, we present Neural-iLQR, a learning-aided shooting method over the unconstrained control space, in which a neural network with a simple structure is used to drive the optimization process towards optimal direction. Through comprehensive evaluations on two illustrative control tasks using three different kinds of lightweight network structures, the proposed method is shown to outperform the conventional iLQR significantly with fast and continuous cost convergence in the presence of inaccuracies in system models, which demonstrates the generalizability and robustness of the proposed learning-aided method. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EXOT: Exit-aware Object Tracker for Safe Robotic Manipulation of Moving Object

EXOT: Exit-aware Object Tracker for Safe Robotic Manipulatio...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Hyunseo Kim Hye Jung Yoon Minji Kim Dong-Sig Han Byoung-Tak Zhang Interdisciplinary Program in Neuroscience Seoul National University Seoul Korea Interdisciplinary Program in Artificial Intelligence Seoul National University Dept. of Computer Science and Engineering Seoul National University AIIS Seoul National University

Current robotic hand manipulation narrowly operates with objects in predictable positions in limited environments. Thus, when the location of the target object deviates severely from the expected location, a robot sometimes responds in an unexpected way, especially when it operates with a human. For safe robot operation, we propose the EXit-aware Object Tracker (EXOT) on a robot hand camera that recognizes an object's absence during manipulation. The robot decides whether to proceed by examining the tracker's bounding box output containing the target object. We adopt an out-of-distribution classifier for more accurate object recognition since trackers can mistrack a background as a target object. To the best of our knowledge, our method is the first approach of applying an out-of-distribution classification technique to a tracker output. We evaluate our method on the first-person video benchmark dataset, TREK-150, and on the custom dataset, RMOT-223, that we collect from the UR5e robot. Then we test our tracker on the UR5e robot in real-time with a conveyor-belt sushi task, to examine the tracker's ability to track target dishes and to determine the exit status. Our tracker shows 38% higher exit-aware performance than a baseline method. The dataset and the code will be released at https://***/hskAlena/EXOT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Transfer Learning-Based Model with Data Augmentation for Brain Tumor Detection

An Improved Transfer Learning-Based Model with Data Augmenta...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Rizal Dwi Prayogo Nur Hamid Hidetaka Nambo Division of Electrical Engineering and Computer Science Graduate School of Natural Science and Technology Kanazawa University Kanazawa Japan Faculty of Transdisciplinary Sciences Institute of Philosophy in Interdisciplinary Sciences Kanazawa University Kanazawa Japan

Current advances in deep learning have brought various breakthroughs in processing medical data. However, dealing with a limited number of medical datasets remains a challenge in deep learning and often leads to overfitting. To solve this research gap, here we show a new approach to improve the performance of a transfer learning-based model for brain tumor detection from 253 brain magnetic resonance imaging (MRI) sample images. The concept of transfer learning has been applied using a pretrained Inception V3combined with data augmentation. Modified layers using dropout and regularization have been additionally utilized to deal with overfitting. The proposed method shows an increase in accuracy of 6.430%, a precision of 5.531 %, a recall of 10.545%, and an F1-score of 8.040% compared to the baseline method. We show that our proposed method has been able to effectively enhance performance and reduce overfitting, even with a small number of datasets. Moreover, our proposed method outperforms state-of-the-art brain tumor detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards

arXiv

引用

arXiv 2024年

作者： Kwon, Hyeokjin Lee, Gunmin Lee, Junseo Oh, Songhwai Interdisciplinary Program in Artificial Intelligence ASRI Seoul National University Seoul08826 Korea Republic of Department of Electrical and Computer Engineering ASRI Seoul National University Seoul08826 Korea Republic of

In the realm of autonomous agents, ensuring safety and reliability in complex and dynamic environments remains a paramount challenge. Safe reinforcement learning addresses these concerns by introducing safety constraints, but still faces challenges in navigating intricate environments such as complex driving situations. To overcome these challenges, we present the safe constraint reward (Safe CoR) framework, a novel method that utilizes two types of expert demonstrations—reward expert demonstrations focusing on performance optimization and safe expert demonstrations prioritizing safety. By exploiting a constraint reward (CoR), our framework guides the agent to balance performance goals of reward sum with safety constraints. We test the proposed framework in diverse environments, including the safety gym, metadrive, and the real-world Jackal platform. Our proposed framework enhances the performance of algorithms by 39% and reduces constraint violations by 88% on the real-world Jackal platform, demonstrating the framework’s efficacy. Through this innovative approach, we expect significant advancements in real-world performance, leading to transformative effects in the realm of safe and reliable autonomous agents. Copyright © 2024, The Authors. All rights reserved.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

MERNet: Multimodal Emotion Recognition in Conversation Network via Cross-Modal Knowledge Distillation and Contrastive Learning

MERNet: Multimodal Emotion Recognition in Conversation Netwo...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Sooyeon Hwang Gahgene Gweon Eunseong Kwon Interdisciplinary Program in Artificial Intelligence Seoul National University South Korea Graduate School of Convergence Science and Technology Seoul National University South Korea Dept. of Computer Science and Engineering POSTECH South Korea

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

Multimodal Emotion Recognition in Conversation (ERC) is a task of predicting the emotion of each utterance in a conversation by utilizing both verbal and non-verbal modalities. However, existing approaches often struggle to bridge cross-modal gaps, resulting in misaligned features and frequent misclassification of minority emotions into semantically similar majority emotions. To address these challenges, we propose MERNet, a framework that employs cross-modal knowledge distillation and contrastive learning to align multimodal features and effectively distinguish subtle emotions in conversations. Our framework consists of two stages: 1) guiding non-verbal modalities with the text modality to transfer knowledge and align their features, and 2) applying contrastive learning with emotion labels as anchors to distinguish subtle differences between similar emotions and address the class imbalance problem. Experiments conducted on two benchmark datasets, IEMOCAP and MELD, demonstrate that our MERNet outperforms existing state-of-the-art models.

关键词： Knowledge engineering Bridges Emotion recognition Visualization Computational modeling Contrastive learning Benchmark testing Linguistics Big Data

来源：评论

学校读者我要写书评

暂无评论

Investigating the Benefits of Adopting Secure Shell (SSH) in Wireless Network Security

Investigating the Benefits of Adopting Secure Shell (SSH) in...

引用

2023 IEEE International Conference on Paradigm Shift in Information Technologies with Innovative Applications in Global Scenario, ICPSITIAGS 2023

作者： Gavathri, C. Patil, Vivek D. Singh, Dhiraj Kumar Kumar, Ritesh Narmadha, T. Kalra, Hitesh Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka 562112 India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350329773

cozy Shell is an encrypted network protocol that has become increasingly popular in network security. Using SSH, organizations can defend their wireless networks from community penetration and malicious interest. SSH affords encryption for statistics transfers, thus stopping records robbery and interception of better-level protocols, which includes statistics confidentiality, integrity, and authentication. Similarly, complex SSH configurations can offer defense in opposition to assaults such as phishing, malware dissemination, and man-in-the-middle attacks. This paper will examine the feasibility and effectiveness of SSH for use in Wi-FiWi-Fi network safety. It will discuss the benefits of SSH for defensive a Wi-FiWi-Fi network and the demanding situations related to its implementation. Additionally, the paper will become aware of the metrics used to degree the overall performance of an SSH-blanketed community and suggest a secure framework for SSH implementation. In the end, this paper will explore the potential for further research within the region of wireless network protection using SSH. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Exploiting Deep Learning Architectures for Effective Real-Time Data Analysis in Machine Learning 3

Exploiting Deep Learning Architectures for Effective Real-Ti...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Shreenidhi, H.S. Rajarajeswari, S. Bhagwat, Suvarna R. Sharma, Khushboo Seth, Kanika Yadav, Rakesh Kumar Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Ramnagar562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350319125

This paper seeks to discover how deep state-of-the-art architectures can be leveraged for robust actual-time information evaluation in device studying packages. The paper begins by supplying a comprehensive assessment of contemporary the modern-day in deep brand new-based totally facts evaluation technology. It then examines case research state-of-the-art real-time records analysis programs to illustrate the viability and blessings of modern-day existing deep latest architectures. programs encompass self-driving vehicle generation, laptop vision, natural language processing, and time-collection evaluation. This targeted evaluation is supplemented by assessing ultra-modern capability shortcomings and demanding situations associated with using these architectures in actual-time scenarios. Subsequently, the paper provides a set of modern-day pointers and first-rate practices to help practitioners efficiently leverage deep trendy architectures for actual-time information evaluation. With the aid of combining a comprehensive review of current deep-gaining knowledge state modern-based records evaluation technology, a detailed dialogue present day its utility guiding ideas, and a summary of the latest potential shortcomings and demanding situations, this paper offers a practical manual to the effective of deep learning architectures for real-time data analysis. © 2023 IEEE.

关键词： architectures challenges combining recommendations shortcomings

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：