基于结构动态元胞自动机的学习与记忆计算模型
A Computational Model of Learning and Memory Using Structurally Dynamic Cellular Automata
AI总结：
本研究提出一种基于结构动态元胞自动机的学习记忆计算模型，以少量生物合理功能构建可计算信息空间，经实验验证其在单次训练后即可实现近最优决策、避障、探索及上下文记忆，且计算效率极高。
摘要：
在计算科学与神经科学领域，人们对学习、记忆、抽象思维和行为等关键认知功能背后的底层计算机制仍知之甚少。本文提出了一种学习与记忆的数学及计算模型，该模型基于少量具备生物合理性的功能构建，包括重合检测、信号调制以及奖惩机制。我们的理论方法提出，这些基础功能足以建立并调制一个可在其上开展计算的信息空间，生成可用于推理和行为的信号梯度。用于验证该理论的计算方法是一种结构动态元胞自动机，其具备连续取值的元胞状态，以及一系列在无向图上传播的递归步骤，记忆功能完全内嵌于图边的创建与调制过程中。实验结果表明：该玩具模型经过单次训练后，即可做出接近最优的选择以重新发现奖励状态；它能够避开复杂的惩罚配置；在稀疏奖励环境中，信号调制和网络可塑性能够产生探索行为；该模型可生成依赖于上下文的记忆表征；此外，由于其仅需最小化的单次训练要求，结合灵活且上下文相关的记忆表征，因此展现出极高的计算效率。
英文摘要：
In the fields of computation and neuroscience, much is still unknown about the underlying computations that enable key cognitive functions including learning, memory, abstraction and behavior. This paper proposes a mathematical and computational model of learning and memory based on a small set of bio-plausible functions that include coincidence detection, signal modulation, and reward/penalty mechanisms. Our theoretical approach proposes that these basic functions are sufficient to establish and modulate an information space over which computation can be carried out, generating signal gradients usable for inference and behavior. The computational method used to test this is a structurally dynamic cellular automaton with continuous-valued cell states and a series of recursive steps propagating over an undirected graph with the memory function embedded entirely in the creation and modulation of graph edges. The experimental results show: that the toy model can make near-optimal choices to re-discover a reward state after a single training run; that it can avoid complex penalty configurations; that signal modulation and network plasticity can generate exploratory behaviors in sparse reward environments; that the model generates context-dependent memory representations; and that it exhibits high computational efficiency because of its minimal, single-pass training requirements combined with flexible and contextual memory representation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
