有限大脑如何无界泛化：作为通用计算机的空间记忆
How Finite Brains Generalize Without Bound: Spatial Memory as a Universal Computer
AI 导读
一篇 arXiv 论文提出，学习者若只读取“重合”（等价关系）而非坐标，有限经验即可固定适用于任意长度的规则，其记忆由循环构成：循环对应网格细胞，检测回归的细胞对应位置细胞，记录对应海马索引，前额叶控制器移动循环却不感知它们。
正文 · 原文
Abstract:A child who learns to add small numbers adds numbers of any length. LSTMs and Transformers trained on short sequences fail on longer ones. We trace the difference to what a learner reads when it decides. A position, a count or a time keeps taking new values as the input grows: it is a coordinate, and a learner that reads one meets in every long input values its experience never covered. Whether two things are the same has the same two answers at every size: it is a coincidence, and a learner that reads only coincidences finds in a long input nothing that short inputs lacked, so finite experience fixes its rule for every size. The memory carries the size of the input and the rule stays finite, and this determines the memory a generalizing brain can have: a memory that grows while what the learner reads of it stays finite has to look the same from every place, so it is made of cycles, and the past is reached by asking what happened when the cycles last stood where they stand now. The cycles are the grid modules, the cells that detect their return the place cells, the records the hippocampal index; a prefrontal controller moves the cycles and never sees them. Reading only coincidences costs no power: what finite experience fixes in such a learner is what Turing machines compute in step with their input, which is why a circuit that evolved to find the way home can learn arithmetic and grammar. In a network of neurons this machine of cycles is the dynamics seen through its symmetry, and symbols are its invariants. Trained on strings up to 40 symbols, the machine is at least 99% correct, on average over lengths 41 to 500, on nine of fifteen benchmark tasks, five of them tasks that no LSTM or Transformer solves; given new cycles after training it reverses strings of 15,015 symbols without error and fails beyond that on the curve the theory predicts; and its controllers run unchanged on neurons.
| Comments: | 57 pages, including appendices |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07920 [cs.AI] |
| (or arXiv:2611.07920v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07920 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuhang He [view email]
[v1]
Thu, 5 Nov 2026 12:30:06 UTC (741 KB)
来源：arXiv cs.AI · arxiv.org