arXiv cs.AI· Kate M. O'Neill, Ian Whitehouse, Adam N. McCaughan, Ryan O'Loughlin, Sonia Buckley, Wolfgang Losert·· 4 小时前AI 评分48
星形胶质细胞生物计算:星形胶质细胞对神经网络计算的贡献
Astrocyte Biocomputing: Astrocytic Contributions to Neural Network Computation
AI 导读
星形胶质细胞约占大脑细胞的 50%,虽不产生电信号,却可能在学习、记忆和信息处理等认知功能中起关键作用。该研究据此提出两类仿星形胶质细胞算法:基于同时调控数千个突触能力的监督学习算法可加快训练并增强抗噪能力;基于星形胶质细胞缓慢节律性通信的算法可实现快速异常检测适应并防止灾难性遗忘。作者发现这些算法显著优于以神经元为中心的算法,可弥补当前最先进 ML 模型的关键短板。
正文 · 原文
Abstract:Conductors are critical for the performance of an orchestra even though they do not emit sound. Basic research and clinical studies in the last decade are revealing that astrocytes may be the "conductors" of the "orchestra" that is the brain network: astrocytes make up approximately $50\%$ of all brain cells but do not emit electrical signals. Nevertheless, they may play critical roles in important cognitive brain functions, specifically learning, memory, and information processing. Here we consider the implications of these discoveries for brain-inspired machine learning (ML), where analogy is typically drawn between neurons and their electrical interactions. We highlight specific algorithms for two key astrocyte characteristics. The first characteristic is the ability to link to and modulate thousands of synapses simultaneously. A model based on this characteristic yields faster training and makes the network more robust to noise, providing a supervised learning algorithm that can be applied to any existing neural network. The second characteristic we focus on is that the non-electrical communication among astrocytes includes slow, rhythmic dynamics. The rhythmic sharing algorithm we developed based on this premise yields rapid anomaly detection adaptation and prevents catastrophic forgetting. Overall, we find that astrocyte-derived algorithms outperform neurocentric algorithms significantly and remediate critical weaknesses of current state-of-the-art ML models.
| Comments: | 11 pages, 3 figures, in journal review |
| Subjects: | Artificial Intelligence (cs.AI); Biological Physics (physics.bio-ph); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2611.17532 [cs.AI] |
| (or arXiv:2611.17532v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17532 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ian Whitehouse [view email]
[v1]
Thu, 12 Nov 2026 21:35:43 UTC (7,257 KB)
来源:arXiv cs.AI · arxiv.org