咨询与建议

限定检索结果

文献类型

  • 27 篇 期刊文献
  • 25 篇 会议

馆藏范围

  • 52 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 38 篇 工学
    • 30 篇 计算机科学与技术...
    • 16 篇 软件工程
    • 10 篇 控制科学与工程
    • 7 篇 信息与通信工程
    • 6 篇 生物工程
    • 5 篇 电气工程
    • 4 篇 动力工程及工程热...
    • 3 篇 生物医学工程(可授...
    • 2 篇 化学工程与技术
    • 2 篇 网络空间安全
    • 1 篇 仪器科学与技术
    • 1 篇 电子科学与技术(可...
    • 1 篇 石油与天然气工程
    • 1 篇 船舶与海洋工程
    • 1 篇 环境科学与工程(可...
    • 1 篇 安全科学与工程
  • 14 篇 理学
    • 7 篇 生物学
    • 6 篇 数学
    • 4 篇 物理学
    • 4 篇 统计学(可授理学、...
    • 2 篇 化学
  • 6 篇 管理学
    • 5 篇 图书情报与档案管...
    • 1 篇 管理科学与工程(可...
  • 4 篇 医学
    • 4 篇 临床医学
    • 2 篇 基础医学(可授医学...
    • 2 篇 药学(可授医学、理...
  • 1 篇 法学
    • 1 篇 社会学

主题

  • 5 篇 reinforcement le...
  • 4 篇 deep learning
  • 3 篇 intelligent robo...
  • 3 篇 computational mo...
  • 3 篇 navigation
  • 3 篇 machine learning
  • 3 篇 training
  • 2 篇 representation l...
  • 2 篇 rendering (compu...
  • 2 篇 deep neural netw...
  • 2 篇 task analysis
  • 2 篇 safety
  • 2 篇 generative adver...
  • 2 篇 neural networks
  • 2 篇 optimization
  • 2 篇 neuromorphic com...
  • 2 篇 adversarial mach...
  • 2 篇 electrocardiogra...
  • 2 篇 location awarene...
  • 2 篇 neural coding

机构

  • 9 篇 interdisciplinar...
  • 6 篇 seoul natl univ ...
  • 6 篇 department of el...
  • 5 篇 seoul natl univ ...
  • 5 篇 seoul natl univ ...
  • 4 篇 department of el...
  • 2 篇 seoul natl univ ...
  • 2 篇 school of comput...
  • 2 篇 seoul natl univ ...
  • 2 篇 interdisciplinar...
  • 2 篇 asri inmc isrc i...
  • 2 篇 sequor robot inc
  • 2 篇 seoul natl univ ...
  • 2 篇 division of digi...
  • 2 篇 seoul natl univ ...
  • 2 篇 asri and interdi...
  • 2 篇 seoul natl univ ...
  • 2 篇 seoul natl univ ...
  • 2 篇 seoul natl univ ...
  • 2 篇 naver ai lab

作者

  • 19 篇 yoon sungroh
  • 7 篇 oh songhwai
  • 5 篇 kim heeseung
  • 5 篇 lee kyoung mu
  • 5 篇 sungroh yoon
  • 4 篇 park seongsik
  • 4 篇 min seonwoo
  • 4 篇 moon taesup
  • 4 篇 lee junseo
  • 4 篇 jung dahuin
  • 4 篇 kim siwon
  • 4 篇 choi hyun-soo
  • 4 篇 hwang uiwon
  • 3 篇 han bohyung
  • 3 篇 lee gunmin
  • 3 篇 lee saehyung
  • 3 篇 songhwai oh
  • 3 篇 lee jaerin
  • 3 篇 kwon hyeokjin
  • 3 篇 kim minsoo

语言

  • 48 篇 英文
  • 4 篇 其他
检索条件"机构=ASRI and Interdisciplinary Program in Artificial Intelligence"
52 条 记 录,以下是1-10 订阅
排序:
On Task-Relevant Loss Functions in Meta-Reinforcement Learning  6
On Task-Relevant Loss Functions in Meta-Reinforcement Learni...
收藏 引用
6th Annual Learning for Dynamics and Control Conference
作者: Shin, Jaeuk Kim, Giho Lee, Howon Han, Joonho Yang, Insoon Seoul Natl Univ Dept Elect & Comp Engn ASRI Seoul South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence ASRI Seoul South Korea
Designing a competent meta-reinforcement learning (meta-RL) algorithm in terms of data usage remains a central challenge to be tackled for its successful real-world applications. In this paper, we propose a sample-eff... 详细信息
来源: 评论
Regularizing Hard Examples Improves Adversarial Robustness
收藏 引用
JOURNAL OF MACHINE LEARNING RESEARCH 2025年 26卷
作者: Lee, Hyungyu Lee, Saehyung Bae, Ho Yoon, Sungroh Seoul Natl Univ Elect & Comp Engn Interdisciplinary Program Artificial Intelligence Seoul 08826 South Korea Ewha Womans Univ Dept Cyber Secur Seoul 03760 South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Elect & Comp Engn AIISASRIINMC Seoul 08826 South Korea Seoul Natl Univ ISRC Seoul 08826 South Korea
Recent studies have validated that pruning hard-to-learn examples from training improves the generalization performance of neural networks (NNs). In this study, we investigate this intriguing phenomenon-the negative e... 详细信息
来源: 评论
Adversarial Environment Design via Regret-Guided Diffusion Models  38
Adversarial Environment Design via Regret-Guided Diffusion M...
收藏 引用
38th Conference on Neural Information Processing Systems, NeurIPS 2024
作者: Chung, Hojun Lee, Junseo Kim, Minsoo Kim, Dohyeong Oh, Songhwai Interdisciplinary Program in Artificial Intelligence ASRI Seoul National University Korea Republic of Department of Electrical and Computer Engineering ASRI Seoul National University Korea Republic of
Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generat...
来源: 评论
RNR-Nav: A Real-World Visual Navigation System Using Renderable Neural Radiance Maps
RNR-Nav: A Real-World Visual Navigation System Using Rendera...
收藏 引用
2024 International Conference on Intelligent Robots and Systems
作者: Kim, Minsoo Kwon, Obin Jun, Howoong Oh, Songhwai Interdisciplinary Program Artificial Intelligence Seoul South Korea ASRI Seoul South Korea Seoul Natl Univ Dept Elect & Comp Engn ECE Seoul South Korea Sequor Robot Inc Seoul South Korea
We propose a novel visual localization and navigation framework for real-world environments directly integrating observed visual information into the bird-eye-view map. While the renderable neural radiance map (RNR-Ma... 详细信息
来源: 评论
Safe Receding Horizon Motion Planning with Infinitesimal Update Interval
Safe Receding Horizon Motion Planning with Infinitesimal Upd...
收藏 引用
IEEE International Conference on Robotics and Automation (ICRA)
作者: Jang, Inkyu Hwang, Sunwoo Byun, Jeonghyun Kim, H. Jin Seoul Natl Univ Dept Aerosp Engn Seoul South Korea Seoul Natl Univ Automat & Syst Res Inst ASRI Seoul South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea
Safety verification in motion planning is known to be computationally burdensome, despite its importance in robotics. In this paper, we investigate the behavior of safe receding horizon motion planners when the update... 详细信息
来源: 评论
Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards
Safe CoR: A Dual-Expert Approach to Integrating Imitation Le...
收藏 引用
2024 International Conference on Intelligent Robots and Systems
作者: Kwon, Hyeokjin Lee, Gunmin Lee, Junseo Oh, Songhwai Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul 08826 South Korea Seoul Natl Univ ASRI Seoul 08826 South Korea Seoul Natl Univ Dept Elect & Comp Engn Seoul 08826 South Korea
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 constrai... 详细信息
来源: 评论
Grokfast: Accelerated Grokking by Amplifying Slow Gradients
arXiv
收藏 引用
arXiv 2024年
作者: Lee, Jaerin Kang, Bong Gyun Kim, Kihoon Lee, Kyoung Mu ASRI Department of ECE Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of
One puzzling artifact in machine learning dubbed grokking is where delayed generalization is achieved tenfolds of iterations after near perfect overfitting to the training data. Focusing on the long delay itself on be... 详细信息
来源: 评论
A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges
收藏 引用
artificial intelligence REVIEW 2025年 第7期58卷 1-95页
作者: Kim, Jongseon Kim, Hyungjoon Kim, Hyungi Lee, Dongjun Yoon, Sungroh Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ AIIS ASRI Seoul South Korea Seoul Natl Univ INMC Seoul South Korea R&D Dept LG Chem Seoul South Korea Samsung SDI R&D Dept Yongin South Korea
Time series forecasting is a critical task that provides key information for decision-making across various fields, such as economic planning, supply chain management, and medical diagnosis. After the use of tradition... 详细信息
来源: 评论
Adversarial Environment Design via Regret-Guided Diffusion Models
arXiv
收藏 引用
arXiv 2024年
作者: Chung, Hojun Lee, Junseo Kim, Minsoo Kim, Dohyeong Oh, Songhwai Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Korea Republic of Department of Electrical and Computer Engineering and ASRI Seoul National University Korea Republic of
Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generat... 详细信息
来源: 评论
Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards
Safe CoR: A Dual-Expert Approach to Integrating Imitation Le...
收藏 引用
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
作者: Hyeokjin Kwon Gunmin Lee Junseo Lee Songhwai Oh Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Seoul Korea Department of Electrical and Computer Engineering and ASRI Seoul National University Seoul Korea
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 constrai... 详细信息
来源: 评论