通过仿生神经网络提升可解释性，融合化学突触与激活机制
Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Models
- 引入液态电容扩展模型，增强全连接循环网络的可解释性
- 结合化学突触与突触激活，显著提升模型准确率与可解释性
- 适用于自动驾驶等需高透明度决策的场景
本文提出统一框架，用于理解各类仿生模型在结构与功能上的差异。我们发现，液态电容扩展模型即使在密集的全连接循环神经网络（RNN）策略中也能实现可解释行为。进一步证明，引入化学突触可提升可解释性，而将化学突触与突触激活相结合，能构建出最准确且可解释的RNN模型。为评估这些RNN策略的准确性与可解释性，我们采用具有挑战性的车道保持控制任务，在多个指标上进行评估：包括转向加权验证损失、驾驶过程中的神经活动、神经活动与道路轨迹的绝对相关性、网络注意力的显著性图，以及显著性图的结构相似性指数所衡量的鲁棒性。
原文摘要 · Abstract (English)
In this paper, we present a unified framework for various bio-inspired models to better understand their structural and functional differences. We show that liquid-capacitance-extended models lead to interpretable behavior even in dense, all-to-all recurrent neural network (RNN) policies. We further demonstrate that incorporating chemical synapses improves interpretability and that combining chemical synapses with synaptic activation yields the most accurate and interpretable RNN models. To assess the accuracy and interpretability of these RNN policies, we consider the challenging lane-keeping control task and evaluate performance across multiple metrics, including turn-weighted validation loss, neural activity during driving, absolute correlation between neural activity and road trajectory, saliency maps of the networks' attention, and the robustness of their saliency maps measured by the structural similarity index.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。