This study proposes a novel dynamical mechanism for pattern recognition discovered by interpreting a recurrent neural network (RNN) trained on a simple task inspired by the SET card game. We interpreted the trained RNN as recognizing patterns via phase shifts in a low-dimensional limit cycle in a manner analogous to transitions in a finite state automaton (FSA). We further validated this interpretation by handcrafting a simple oscillatory model that reproduces the dynamics of the trained RNN. Our findings not only suggest of a potential dynamical mechanism capable of pattern recognition, but also suggest of a potential neural implementation of FSA. Above all, this work contributes to the growing discourse on deep learning model interpretability.

翻译：本研究提出了一种新的模式识别动力学机制，该机制源于对受SET纸牌游戏简单任务训练的循环神经网络（RNN）进行解释而发现。我们将训练后的RNN解释为通过低维极限环中的相位偏移来识别模式，其方式类似于有限状态自动机（FSA）中的状态转移。我们进一步通过手工构建一个简单的振荡模型来验证这一解释，该模型复现了训练后RNN的动力学行为。我们的发现不仅揭示了一种潜在的能够实现模式识别的动力学机制，还表明了FSA可能的神经实现方式。最重要的是，本研究为深度学习模型可解释性日益增长的讨论做出了贡献。