Trustworthy decentralized AI for large-scale IoT representation learning
用于大规模物联网表征学习的值得信赖的去中心化人工智能
基本信息
- 批准号:22KJ0878
- 负责人:
- 金额:$ 1.09万
- 依托单位:
- 依托单位国家:日本
- 项目类别:Grant-in-Aid for JSPS Fellows
- 财政年份:2023
- 资助国家:日本
- 起止时间:2023-03-08 至 2024-03-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
The project aims to address the fundamental challenges of decentralized deep learning (DDL) to make AI feasible and scalable for everyone. The proliferation of edge AI applications has been reshaping the contours of future high-performance edge computing, and DDL is a key enabler that would benefit society through distributed model training and globally shared knowledge. In the first phase of the project, we focused on developing collaborative representation learning techniques for different neural network models at the edge. We identified critical challenges and proposed new solutions to privacy protection, edge heterogeneity, and adversarial attacks and defenses in DDL. The proposed methods enable improved model generality to unseen data and robustness against adversarial attacks.
该项目旨在解决去中心化深度学习(Decentralized Deep Learning,简称DAI)的基本挑战,使AI对每个人都可行且可扩展。边缘人工智能应用的激增正在重塑未来高性能边缘计算的轮廓,而边缘计算是一个关键的推动因素,它将通过分布式模型训练和全球共享知识使社会受益。在项目的第一阶段,我们专注于为边缘的不同神经网络模型开发协作表示学习技术。我们确定了关键的挑战,并提出了新的解决方案,以保护隐私,边缘异质性,对抗性攻击和防御。所提出的方法能够提高模型对未知数据的通用性和对对抗性攻击的鲁棒性。
项目成果
期刊论文数量(10)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Meta Learning in Decentralized Neural Networks Through the Lens of Global Workspace Theory
通过全局工作空间理论的视角进行去中心化神经网络的元学习
- DOI:
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Sun Yuwei;Ochiai Hideya;Esaki Hiroshi;Yuwei Sun;Yuwei Sun
- 通讯作者:Yuwei Sun
Federated Phish Bowl: LSTM-Based Decentralized Phishing Email Detection
Federated Phish Bowl:基于 LSTM 的去中心化网络钓鱼电子邮件检测
- DOI:
- 发表时间:2022
- 期刊:
- 影响因子:0
- 作者:Yuwei Sun;Ng Chong;and Hideya Ochiai
- 通讯作者:and Hideya Ochiai
Federated Reinforcement Learning for the Building Facilities
- DOI:10.1109/coins54846.2022.9854959
- 发表时间:2022-08
- 期刊:
- 影响因子:0
- 作者:Koki Fujita;Shugo Fujimura;Yuwei Sun;H. Esaki;H. Ochiai
- 通讯作者:Koki Fujita;Shugo Fujimura;Yuwei Sun;H. Esaki;H. Ochiai
Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthiness
- DOI:10.1109/tai.2021.3133819
- 发表时间:2021-07
- 期刊:
- 影响因子:0
- 作者:Yuwei Sun;H. Ochiai;H. Esaki
- 通讯作者:Yuwei Sun;H. Ochiai;H. Esaki
Meta Learning in Decentralized Neural Networks: Towards More General AI
- DOI:10.48550/arxiv.2302.01020
- 发表时间:2023-02
- 期刊:
- 影响因子:0
- 作者:Yuwei Sun
- 通讯作者:Yuwei Sun
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
SUN YUWEI其他文献
SUN YUWEI的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
相似海外基金
EAGER: Search-Accelerated Markov Chain Monte Carlo Algorithms for Bayesian Neural Networks and Trillion-Dimensional Problems
EAGER:贝叶斯神经网络和万亿维问题的搜索加速马尔可夫链蒙特卡罗算法
- 批准号:
2404989 - 财政年份:2024
- 资助金额:
$ 1.09万 - 项目类别:
Standard Grant
Collaborative Research: Spintronics Enabled Stochastic Spiking Neural Networks with Temporal Information Encoding
合作研究:自旋电子学支持具有时间信息编码的随机尖峰神经网络
- 批准号:
2333881 - 财政年份:2024
- 资助金额:
$ 1.09万 - 项目类别:
Standard Grant
Collaborative Research: Spintronics Enabled Stochastic Spiking Neural Networks with Temporal Information Encoding
合作研究:自旋电子学支持具有时间信息编码的随机尖峰神经网络
- 批准号:
2333882 - 财政年份:2024
- 资助金额:
$ 1.09万 - 项目类别:
Standard Grant
DMS-EPSRC: Asymptotic Analysis of Online Training Algorithms in Machine Learning: Recurrent, Graphical, and Deep Neural Networks
DMS-EPSRC:机器学习中在线训练算法的渐近分析:循环、图形和深度神经网络
- 批准号:
EP/Y029089/1 - 财政年份:2024
- 资助金额:
$ 1.09万 - 项目类别:
Research Grant
SkyANN: Skyrmionic Artificial Neural Networks
SkyANN:Skyrmionic 人工神经网络
- 批准号:
10108371 - 财政年份:2024
- 资助金额:
$ 1.09万 - 项目类别:
EU-Funded
CAREER: Rethinking Spiking Neural Networks from a Dynamical System Perspective
职业:从动态系统的角度重新思考尖峰神经网络
- 批准号:
2337646 - 财政年份:2024
- 资助金额:
$ 1.09万 - 项目类别:
Continuing Grant
RII Track-4:@NASA: Automating Character Extraction for Taxonomic Species Descriptions Using Neural Networks, Transformer, and Computer Vision Signal Processing Architectures
RII Track-4:@NASA:使用神经网络、变压器和计算机视觉信号处理架构自动提取分类物种描述的字符
- 批准号:
2327168 - 财政年份:2024
- 资助金额:
$ 1.09万 - 项目类别:
Standard Grant
Neural Networks for Stationary and Evolutionary Variational Problems
用于稳态和进化变分问题的神经网络
- 批准号:
2424801 - 财政年份:2024
- 资助金额:
$ 1.09万 - 项目类别:
Continuing Grant
Organic optoelectronic neural networks
有机光电神经网络
- 批准号:
EP/Y020596/1 - 财政年份:2024
- 资助金额:
$ 1.09万 - 项目类别:
Research Grant
Approximation theory of structured neural networks
结构化神经网络的逼近理论
- 批准号:
DP240101919 - 财政年份:2024
- 资助金额:
$ 1.09万 - 项目类别:
Discovery Projects