Learning to see: genetic and environmental influences on visual development
Learning to see: genetic and environmental influences on visual development
Object recognition by artificial cortical maps
Neural Networks
A connectionist architecture for the evolution of rhythms
EuroGP'06 Proceedings of the 2006 international conference on Applications of Evolutionary Computing
Hi-index | 0.01 |
Primary visual cortex (V1) contains overlaid feature maps for orientation (OR), motion direction selectivity (DR), and ocular dominance (OD). Neurons in these maps are connected laterally in patchy, long-range patterns that follow the feature preferences. Using the LISSOM model, we show for the first time how realistic laterally connected joint OR/OD/DR maps can self-organize from Hebbian learning of moving natural images. The model predicts that lateral connections will link neurons of either eye preference and with similar DR and OR preferences. These results suggest that a single self-organizing system may underlie the development of spatiotemporal feature preferences and lateral connectivity.