DS-AL: A dual-stream analytic learning for exemplar-free class-incremental learning

[PDF] arxiv.org

Locality Sensitive Sparse Encoding for Learning World Models Online

Z Liu, C Du, WS Lee, M Lin - arXiv preprint arXiv:2401.13034, 2024 - arxiv.org
Acquiring an accurate world model online for model-based reinforcement learning (MBRL)
is challenging due to data nonstationarity, which typically causes catastrophic forgetting for …
被引用次数：1 相关文章 所有 3 个版本
[PDF] arxiv.org

Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Task

H Zhuang, D Fang, K Tong, Y Liu, Z Zeng… - arXiv preprint arXiv …, 2024 - arxiv.org
In the field of autonomous driving, even a meticulously trained model can encounter failures
when faced with unfamiliar sceanrios. One of these scenarios can be formulated as an …
相关文章 所有 2 个版本
[PDF] arxiv.org

Analytic Federated Learning

H Zhuang, R He, K Tong, D Fang, H Sun, H Li… - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper, we introduce analytic federated learning (AFL), a new training paradigm that
brings analytical (ie, closed-form) solutions to the federated learning (FL) community. Our …
相关文章 所有 2 个版本