立场论文：神经递质作为人工神经网络中缺失的维度
Position Paper: Neurotransmitters as a Missing Dimension in Artificial Neural Networks
浏览论文内容
中文总结 AI 辅助
本文提出神经递质神经调节作为人工神经网络学习的第三轴，主张将其显式建模以增强自适应和持续学习能力，弥补现有网络缺乏生物灵活性的不足。
中文摘要 AI 辅助
人工神经网络（ANNs）作为现代深度学习（DL）系统的核心组成部分，缺乏生物系统所表现出的自适应灵活性和长期稳定性。这一局限性主要源于传统人工神经网络依赖于统一、局部且基于梯度的参数更新，而忽略了诸如神经递质信号传导或神经可塑性等生物机制的内在学习原则。因此，许多现有方法侧重于架构扩展或数学微调技术，如正则化或参数隔离。受哺乳动物大脑卓越适应性和可塑性的启发，我们主张神经递质介导的神经调节构成学习的第三轴，与神经活动和突触可塑性互补，并应在人工神经网络中显式建模。在这篇立场论文中，我们认为将神经调节原则纳入人工神经网络设计代表了一个有前景且未被充分探索的研究方向，并倡导在自适应和持续学习系统的开发中更加关注这一视角。
英文摘要
Artificial neural networks (ANNs), as core components of modern deep learning (DL) systems, lack the adaptive flexibility and long-term stability exhibited by biological systems. This limitation largely stems from the fact that conventional ANNs rely on uniform, local, and gradient-based parameter updates, while neglecting internal learning principles that are biological mechanisms such as neurotransmitters signalling or neuroplasticity. Consequently, many existing approaches focus on architectural expansion or mathematical fine-tuning techniques such as regularisation or parameter isolation. Inspired by the superior adaptability and plasticity of mammalian brains, we posit that neuromodulation with neurotransmitters constitutes a third axis of learning, complementary to neural activity and synaptic plasticity, and should be explicitly modelled in artificial neural networks. In this positional paper, we argue that incorporating neuromodulatory principles into ANN design represents a promising and underexplored research direction, and we advocate for greater attention to this perspective in the development of adaptive and continual learning systems.
发表机构
- Imperial College London（帝国理工学院）
- Technical University of Munich（慕尼黑工业大学）
- Johns Hopkins Whiting School of Engineering（约翰斯·霍普金斯大学怀廷工程学院）
机构由 AI 辅助整理，请以论文原文为准。
