The Role of Training Paradigms in Shaping Connectivity and Dynamics: A Comparison of Gradient-Based and Evolutionary Methods in Recurrent Neural Network Models
Ivyer Qu, Jiayue Dora Li, Yuqing Zhu
This paper compares gradient-based and evolutionary training methods in RNNs, showing they produce distinct connectivity and dynamics, especially in working memory tasks.
bioRxiv · Jul 15, 2026 · PreprintNeuroscience