CAREER: Towards Biologically Inspired Lifelong Learning with Multimodal Association

职业生涯：通过多模式关联迈向受生物启发的终身学习

• 批准号: 2325863
• 负责人: Bo Tang
• 金额: $ 50万
• 依托单位: Worcester Polytechnic Institute
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-01-01 至 2026-07-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2325863&HistoricalAwards=false
• 关键词: CAREER; Towards; Biologically; Inspired; Lifelong

Humans have the ability to continuously learn, accumulate and fine-tune knowledge and skills from a sequence of tasks over their lifetimes. Such lifelong learning is also crucial for computational systems to achieve high levels of performance, flexibility, and adaptation when they interact with real world environments and process streaming sensory data. This project will develop biologically inspired lifelong learning architectures and methods that integrate functions and characteristics of a mammalian brain, which is arguably the best learning system the world has seen. The success of this research will advance fundamental knowledge in computational lifelong learning and will have the potential to transform how the field creates human-like artificial intelligence with lifelong learning capabilities. In addition, the outcome of this research will be integrated into a new curriculum, and opportunities will be provided to students from under-represented groups to participate in computational intelligence research.The project will explore a new machine learning paradigm to address many critical challenges facing current deep neural networks when learning is performed from sequential tasks and different sources. The proposed research will introduce a lifelong learning framework consisting of a feature learning network, a convertible short-term and long-term memory network, and a memory replay network. To achieve effective lifelong learning, this project will address the following three research challenges: (1) learning to memorize -- achieving the optimal balance between plasticity and stability of neural connections to improve the efficiency of both learning and memory networks; (2) learning to recall -- optimizing cue effectiveness in both learning and memory replay networks to address the problem of catastrophic forgetting; and (3) learning to associate -- enabling multimodality association at the memory level. Since the proposed models mimic the hierarchical architecture, short- and long-term memory mechanisms, and feedback function of the mammalian brain, they have the potential to contribute to an artificial general intelligence that better accumulates knowledge without interference, learns multimodality association, and even predicts the future.This project is jointly funded by Robust Intelligence and the Established Program to Stimulate Competitive Research (EPSCoR).This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人类有能力在一生中从一系列任务中不断学习、积累和调整知识和技能。这种终身学习对于计算系统在与现实世界环境交互和处理流式传感数据时实现高水平的性能、灵活性和适应性也至关重要。该项目将开发受生物学启发的终身学习架构和方法，整合哺乳动物大脑的功能和特征，这可以说是世界上见过的最好的学习系统。这项研究的成功将推进计算终身学习的基础知识，并将有可能改变该领域创建具有终身学习能力的类人人工智能的方式。此外，这项研究成果将被整合到新课程中，并为代表性不足群体的学生提供参与计算智能研究的机会。该项目将探索一种新的机器学习范式，以解决面临的许多关键挑战当前的深度神经网络是从顺序任务和不同来源执行学习的。拟议的研究将引入一个终身学习框架，该框架由特征学习网络、可转换的短期和长期记忆网络以及记忆重放网络组成。为了实现有效的终身学习，该项目将解决以下三个研究挑战：（1）学习记忆——实现神经连接的可塑性和稳定性之间的最佳平衡，以提高学习和记忆网络的效率； (2) 学习回忆——优化学习和记忆重放网络中的线索有效性，以解决灾难性遗忘问题； (3) 学习联想——在记忆层面实现多模态联想。由于所提出的模型模仿了哺乳动物大脑的层次结构、短期和长期记忆机制以及反馈功能，因此它们有可能有助于通用人工智能，更好地在不受干扰的情况下积累知识，学习多模态关联，甚至预测未来。该项目由 Robust Intelligence 和刺激竞争研究既定计划 (EPSCoR) 联合资助。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的评估进行评估，认为值得支持。影响审查标准。

项目成果

FedLGA: Toward System-Heterogeneity of Federated Learning via Local Gradient Approximation

FedLGA：通过局部梯度近似实现联邦学习的系统异构性

• DOI: 10.1109/tcyb.2023.3247365
• 发表时间: 2021-12-22
• 期刊: IEEE Transactions on Cybernetics
• 影响因子: 11.8
• 作者: Xingyu Li;Zhe Qu;Bo Tang;Zhuo Lu
• 通讯作者: Zhuo Lu

On the Convergence of Multi-Server Federated Learning with Overlapping Area

具有重叠区域的多服务器联邦学习的收敛性研究

• DOI: 10.1109/tmc.2022.3200016
• 发表时间: 2022-08
• 期刊: IEEE Transactions on Mobile Computing
• 影响因子: 7.9
• 作者: Qu, Zhe;Li, Xingyu;Xu, Jie;Tang, Bo;Lu, Zhuo;Liu, Yao
• 通讯作者: Liu, Yao

Generalized Federated Learning via Sharpness Aware Minimization

通过锐度感知最小化的广义联合学习

• DOI: 10.48550/arxiv.2206.02618
• 发表时间: 2022-06-06
• 作者: Zhe Qu;Xingyu Li;Rui Duan;Yaojiang Liu;Bo Tang;Zhuo Lu
• 通讯作者: Zhuo Lu