Files
myWiki/concepts/spiking-neural-networks.md

23 lines
786 B
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
title: "Spiking Neural Networks (SNN)"
created: 2026-05-15
updated: 2026-05-15
type: concept
tags: [neural-architecture, biological-plausibility, event-driven]
confidence: medium
---
# Spiking Neural Networks (SNN)
**脉冲神经网络** 是一类使用离散脉冲spike而非连续值进行通信的神经网络在时间编码和事件驱动计算方面更接近生物神经元。
## 与 CTM 的关系
CTM 和 SNN 共享**生物学灵感**但路径不同:
- **SNN**:离散脉冲 + 事件驱动 + 脉冲时序依赖可塑性STDP
- **CTM**:连续值 NLM + 梯度优化 + 同步作为表示
两者都认为**时间是神经计算的核心**,但 CTM 选择了更适合现代深度学习的抽象层次。
> 📝 占位页面 — 待完整 ingest 后更新