Grow-Prune-Freeze网络：用于嗅觉导航的自适应与持续学习技术

Kordel K. France, Ovidiu Daescu

2026

摘要

本文提出Grow-Prune-Freeze (GPF)网络框架，使智能体能够通过生长、剪枝和冻结策略早期层来持续适应环境复杂度。基于非线性随机矩阵理论，该方法在湍流羽流导航任务中达到94%的成功率，并展示了在强化学习、图像分类和语言模型等任务中的泛化潜力。

continual learningolfactory navigationadaptive networksgrow-prune-freezenonlinear random matrix theory

LEARNING

开放获取📊 1 引用

Keyi Shen, Glen Chou

2026

LEARNING

📊 0 引用

Xiwei Wu, Wei Wu, Qiqi Chen 等 9 位作者

Robotics and Computer-Integrated Manufacturing · 2026

LEARNING

📊 0 引用

Hedi Boukamcha, Anas Neumann, Monia Rekik 等 6 位作者

Robotics and Computer-Integrated Manufacturing · 2026

LEARNING

📊 0 引用

Jiaxin Liu, Xiaofeng Zhou, Suyang Yu 等 8 位作者

Robotics and Computer-Integrated Manufacturing · 2026