Recurrent Neural Network Replicates Brain's Perceptual Grouping and Predicts Human Reaction Times
Brown University's Thomas Serre team, with Pieter Roelfsema's lab, released a preprint showing a recurrent vision model that groups objects in natural scenes and predicts human reaction times, with early grouping driven by local boundary signals and later sharpened by top-down identity feedback.
2026-10-13 ~ 2026-10-13 · 3 related posts
- Brain-inspired recurrent networks explain perceptual grouping dynamics in natural scenes — tserre · 2026-10-13
- New preprint: recurrent vision models group objects and predict human reaction times — tserre · 2026-10-13
- Brown Team's Vision Model Groups Objects and Predicts Human Reaction Times — tserre · 2026-10-13