Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Models
This work addresses the problem of interpretability in bio-inspired AI models for researchers and practitioners, though it appears incremental as it builds on existing methods with specific enhancements.
The paper tackled the challenge of making dense, all-to-all recurrent neural network policies more interpretable by introducing a unified framework with liquid-capacitance-extended models and chemical synapses, resulting in improved accuracy and interpretability as demonstrated on a lane-keeping control task with multiple evaluation metrics.
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.