Optic-flow-CNNs-MLPs-15x15
Collection
CNNs and MLPs trained on ~6k 15x15 optic flow patterns generated by uniformly sampled combinations of translation (T) and rotation (R).
•
12 items
•
Updated
From our paper: Layton, Peng, & Steinmetz (2024). ReLU, Sparseness, and the Encoding of Optic Flow in Neural Networks. Sensors.