用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/hiyenwong/ai_collection --skill spiking-neuron-biological-plausibility-assessment命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | spiking-neuron-biological-plausibility-assessment |
| description | 脉冲神经元生物学合理性自动化评估框架，系统化评估人工脉冲神经元与生物神经元的相似度，提供量化指标和可解释分析 |
| version | 1.0.0 |
| category | neuroscience |
| tags | ["spiking-neuron","biological-plausibility","SNN","neuron-model","interpretability","automation"] |
| arxiv | 2606.17853 |
| activation_words | ["生物学合理性","脉冲神经元","SNN评估","神经元模型","可解释性","LIF模型","Izhikevich","Hodgkin-Huxley"] |
系统化自动化评估脉冲神经元生物学合理性 - 提供量化指标和可解释分析，评估人工脉冲神经元模型与生物神经元的行为相似度。
class BiologicalPlausibilityAssessment:
def __init__(self):
self.criteria = {
'electrophysiology': ElectrophysiologyMetrics(),
'morphology': MorphologyMetrics(),
'dynamics': DynamicalBehaviorMetrics(),
'plasticity': SynapticPlasticityMetrics()
}
def assess(self, neuron_model):
scores = {}
for criterion, evaluator in self.criteria.items():
scores[criterion] = evaluator.evaluate(neuron_model)
overall_score = self.aggregate(scores)
explanations = self.explain(scores)
return {
'overall_plausibility': overall_score,
'detailed_scores': scores,
'explanations': explanations
}
| Model | Biological Features | Plausibility Score |
|---|---|---|
| LIF (Leaky Integrate-and-Fire) | 基本脉冲机制 | Medium-Low |
| Izhikevich | 多种脉冲模式 | High |
| AdEx (Adaptive Exponential) | 自适应机制 | Medium-High |
| Hodgkin-Huxley | 生物通道动力学 | Very High |
权衡定律: 生物学合理性↑ → 计算效率↓