[论文解读] Situation-based memory in spiking neuron-astrocyte network

Susanna Gordleeva, Yuliya Tsybina+5 more|arXiv (Cornell University)|Feb 15, 2022

Advanced Memory and Neural Computing被引用 4

一句话总结

本文提出了一种脉冲神经元-胶质细胞网络模型，实现了基于情境的记忆——在局部环境中对刺激模式进行快速、情境特定的回忆。通过采用具有胶质细胞介导调节的双网络类脑架构，该模型在检索质量方面优于标准脉冲神经网络，凸显了胶质细胞在有效情境驱动学习与记忆中的结构必要性。

ABSTRACT

Mammalian brains operate in a very special surrounding: to survive they have to react quickly and effectively to the pool of stimuli patterns previously recognized as danger. Many learning tasks often encountered by living organisms involve a specific set-up centered around a relatively small set of patterns presented in a particular environment. For example, at a party, people recognize friends immediately, without deep analysis, just by seeing a fragment of their clothes. This set-up with reduced "ontology" is referred to as a "situation". Situations are usually local in space and time. In this work, we propose that neuron-astrocyte networks provide a network topology that is effectively adapted to accommodate situation-based memory. In order to illustrate this, we numerically simulate and analyze a well-established model of a neuron-astrocyte network, which is subjected to stimuli conforming to the situation-driven environment. Three pools of stimuli patterns are considered: external patterns, patterns from the situation associative pool regularly presented to the network and learned by the network, and patterns already learned and remembered by astrocytes. Patterns from the external world are added to and removed from the associative pool. Then we show that astrocytes are structurally necessary for an effective function in such a learning and testing set-up. To demonstrate this we present a novel neuromorphic model for short-term memory implemented by a two-net spiking neural-astrocytic network. Our results show that such a system tested on synthesized data with selective astrocyte-induced modulation of neuronal activity provides an enhancement of retrieval quality in comparison to standard spiking neural networks trained via Hebbian plasticity only. We argue that the proposed set-up may offer a new way to analyze, model, and understand neuromorphic artificial intelligence systems.

研究动机与目标

• 研究神经元-胶质细胞网络如何在动态、局部化的环境中支持快速、情境特定的记忆回忆。
• 解决在有限且重复出现的刺激模式环境（即“情境”）中实现高效记忆存储与检索的挑战。
• 证明胶质细胞在提升情境驱动学习任务中记忆性能方面的必要性。
• 开发并验证一种利用胶质细胞诱导调节以改善短期记忆功能的类脑模型。
• 为建模和设计具有情境敏感记忆的类脑人工智能系统提供生物上合理的框架。

提出的方法

• 在情境驱动刺激条件下，对一个已建立的脉冲神经元-胶质细胞网络模型进行数值模拟。
• 设置三个刺激池：外部刺激、情境特定的关联模式，以及已学习的胶质细胞记忆模式。
• 采用赫布可塑性进行神经元学习，并结合胶质细胞介导的神经元活动调节以增强记忆检索。
• 设计双网络脉冲神经-胶质细胞网络架构，以模拟短期记忆功能。
• 应用选择性胶质细胞诱导调节，动态调节突触效能，提升模式识别保真度。
• 通过受控的刺激呈现与移除协议，利用合成数据评估检索质量。

实验结果

研究问题

• RQ1 神经元-胶质细胞网络如何在时间有限、局部化的环境中支持快速、情境特定的记忆回忆？
• RQ2 在基于情境的学习场景中，胶质细胞在提升记忆检索质量方面发挥何种作用？
• RQ3 具有胶质细胞调节的类脑脉冲网络是否能优于仅通过赫布可塑性训练的标准脉冲神经网络？
• RQ4 将外部刺激动态添加至并从关联池中移除，如何影响记忆性能？
• RQ5 在所提出的模型中，胶质细胞的存在在多大程度上是实现有效情境记忆功能的结构必要条件？

主要发现

• 与仅使用赫布可塑性的标准脉冲神经网络相比，引入胶质细胞介导的调节显著提升了检索质量。
• 研究发现，胶质细胞在情境记忆任务中具有结构必要性，因为移除其影响会降低记忆保真度。
• 双网络类脑模型成功实现了高精度的情境特定模式短期记忆功能。
• 当外部刺激被动态添加至并从关联池中移除时，系统表现出稳健性能，反映出现实世界环境的变化。
• 在选择性胶质细胞诱导调节下，模型实现了更优的模式识别与记忆回忆，证实其在情境敏感学习中的功能优势。
• 结果支持如下假设：由于其动态、调节性架构，神经元-胶质细胞网络在本质上适配于处理情境记忆。