Scholarlink

<p>Conventional end-to-end deep neural networks often degrade under domain shifts and require costly retraining when deployed in unpredictable, noisy environments. Inspired by biological brains, we propose a modular framework where each module is a recurrent neural network pretrained via a simple, task-agnostic protocol to learn robust, transferable features. This shapes stable yet flexible low-dimensional representations as invariant input-driven continuous attractor manifolds embedded in high-dimensional latent space across different tasks, supporting robust transfer and resilience to temporal perturbations. At deployment, only a lightweight adapter needs training, allowing rapid adaptation to new tasks. Validated on gesture and rehabilitation action recognition tasks, our framework achieves accuracy competitive with state-of-the-art methods, especially in few-shot settings, while requiring an order of magnitude fewer parameters and minimal training. By integrating biologically inspired attractor dynamics with cortical-like modular composition, the framework offers a practical path toward robust, continual adaptation in real-world information processing.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Representation Transfer via Invariant Input-driven Continuous Attractors for Fast Domain Adaptation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月4日

查看全文
  • Tie Xu,
  • Shengdun Wu,
  • Junwen Luo,
  • Yao Yang,
  • Feng Lin,
  • Junjie Jiang,
  • Guozhang Chen,
  • Dongping Yang

摘要

Conventional end-to-end deep neural networks often degrade under domain shifts and require costly retraining when deployed in unpredictable, noisy environments. Inspired by biological brains, we propose a modular framework where each module is a recurrent neural network pretrained via a simple, task-agnostic protocol to learn robust, transferable features. This shapes stable yet flexible low-dimensional representations as invariant input-driven continuous attractor manifolds embedded in high-dimensional latent space across different tasks, supporting robust transfer and resilience to temporal perturbations. At deployment, only a lightweight adapter needs training, allowing rapid adaptation to new tasks. Validated on gesture and rehabilitation action recognition tasks, our framework achieves accuracy competitive with state-of-the-art methods, especially in few-shot settings, while requiring an order of magnitude fewer parameters and minimal training. By integrating biologically inspired attractor dynamics with cortical-like modular composition, the framework offers a practical path toward robust, continual adaptation in real-world information processing.