Lateral recurrence dynamically refines visual representations for task performance
Amirhossein Farzmahdi, Hossein Adeli, Wang Boran, Chase King, Nikolaus Kriegeskorte
This study shows that lateral recurrence in neural networks enhances identity separability in trained domains through dynamic refinement of representational geometry.
bioRxiv · Oct 9, 2026 · PreprintNeuroscience